acl acl2013 acl2013-61 knowledge-graph by maker-knowledge-mining
Source: pdf
Author: Stephen Tratz ; Eduard Hovy
Abstract: The English ’s possessive construction occurs frequently in text and can encode several different semantic relations; however, it has received limited attention from the computational linguistics community. This paper describes the creation of a semantic relation inventory covering the use of ’s, an inter-annotator agreement study to calculate how well humans can agree on the relations, a large collection of possessives annotated according to the relations, and an accurate automatic annotation system for labeling new examples. Our 21,938 example dataset is by far the largest annotated possessives dataset we are aware of, and both our automatic classification system, which achieves 87.4% accuracy in our classification experiment, and our annotation data are publicly available.
Reference: text
sentIndex sentText sentNum sentScore
1 mi l Abstract The English ’s possessive construction occurs frequently in text and can encode several different semantic relations; however, it has received limited attention from the computational linguistics community. [sent-5, score-0.45]
2 Our 21,938 example dataset is by far the largest annotated possessives dataset we are aware of, and both our automatic classification system, which achieves 87. [sent-7, score-0.44]
3 4% accuracy in our classification experiment, and our annotation data are publicly available. [sent-8, score-0.076]
4 1 Introduction The English ’s possessive construction occurs frequently in text—approximately 1. [sent-9, score-0.398]
5 , 1993)—and can encode a number of different semantic relations including ownership (John ’s car), part-of-whole (John ’s arm), extent (6 hours ’ drive), and location (America ’s rivers). [sent-11, score-0.234]
6 Accurate automatic possessive interpretation could aid many natural language processing (NLP) applications, especially those that build semantic representations for text understanding, text generation, question answering, or information extraction. [sent-12, score-0.537]
7 These interpretations could be valuable for machine translation to or from languages that allow different semantic relations to be encoded by †The authors Sciences Institute affiliated with the USC Information at the time this work was performed. [sent-13, score-0.174]
8 This paper presents an inventory of 17 semantic relations expressed by the English ’s-construction, a large dataset annotated according to the this inventory, and an accurate automatic classification system. [sent-16, score-0.335]
9 The final inter-annotator agreement study achieved a strong level of agreement, 0. [sent-17, score-0.094]
10 78 Fleiss’ Kappa (Fleiss, 1971) and the dataset is easily the largest manually annotated dataset of possessive constructions created to date. [sent-18, score-0.525]
11 2 Background Although the linguistics field has devoted significant effort to the English possessive (§6. [sent-21, score-0.398]
12 Badulescu and Moldovan (2009) investigate both ’s-constructions and of constructions in the same context using a list of 36 semantic relations (including OTHER). [sent-24, score-0.217]
13 They take their examples from a collection of 20,000 randomly selected sentences from Los Angeles Times news articles used in TREC-9. [sent-25, score-0.098]
14 For the 960 extracted ’s-possessive examples, only 20 of their semantic relations are observed, including OTHER, with 8 of the observed relations occurring fewer than 10 times. [sent-26, score-0.296]
15 c A2s0s1o3ci Aatsiosonc fioartio Cno fmorpu Ctoamtiopnuatalt Lioin gauli Lsitnicgsu,i psatgices 372–381, prior to annotation and by their expertise in Lexical Semantics. [sent-31, score-0.044]
16 They find that their semantic scattering technique significantly outperforms their comparison systems with its F-measure score of 78. [sent-33, score-0.106]
17 25% accuracy— suprisingly low, especially considering that 220 of the 960 ’s examples have the same label. [sent-36, score-0.067]
18 Also, it is sometimes difficult to understand the meaning of the semantic relations, partly because most relations are only described by a single example and, to a lesser extent, because the bulk of the given examples are of-constructions. [sent-38, score-0.241]
19 For example, why President of Bolivia warrants a SOURCE/FROM relation but University of Texas is assigned to LOCATION/SPACE is unclear. [sent-39, score-0.077]
20 Their relations and pro- vided examples are presented below in Table 1. [sent-40, score-0.189]
21 ) of dollars THEME acquisition of the holding RESULT result of the review OTHER state of emergency Table 1: The 20 (out of an original 36) semantic relations observed by Badulescu and Moldovan (2009) along with their examples. [sent-42, score-0.174]
22 Of the 2Email requests asking for relation definitions and the data were not answered, and, thus, we are unable to provide an informative comparison with their work. [sent-44, score-0.133]
23 Another 5,266 examples are from The History of the Decline and Fall of the Roman Empire (Gibbon, 1776), a non-fiction work, and 1,342 are from The Jungle Book (Kipling, 1894), a collection of fictional short stories. [sent-47, score-0.098]
24 For the Penn Treebank, we extracted the examples using the provided gold standard parse trees, whereas, for the latter cases, we used the output of an open source parser (Tratz and Hovy, 2011). [sent-48, score-0.067]
25 4 Semantic Relation Inventory The initial semantic relation inventory for possessives was created by first examining some of the relevant literature on possessives, including work by Badulescu and Moldovan (2009), Barker (1995), Quirk et al. [sent-49, score-0.54]
26 Similar examples were grouped together to form initial categories, and groups that were considered more difficult were later reexamined in greater detail. [sent-51, score-0.067]
27 Once all the examples were assigned to initial categories, the process of refining the definitions and annotations began. [sent-52, score-0.123]
28 In total, 17 relations were created, not including OTHER. [sent-53, score-0.122]
29 They are shown in Table 3 along with approximate (best guess) mappings to relations defined by others, specifically those of Quirk et al. [sent-54, score-0.122]
30 (1985), whose relations are presented in Table 2, as well as Badulescu and Moldovan’s (2009) rela- tions. [sent-55, score-0.122]
31 ing the annotation of a random set of 50 examples. [sent-63, score-0.044]
32 Each set of examples was extracted such that no two examples had an identical possessee word. [sent-64, score-0.439]
33 For a given example, annotators were instructed to select the most appropriate option but could also record a second-best choice to provide additional feedback. [sent-65, score-0.049]
34 After the annotation was complete for a given round, agreement and entropy figures were calculated and changes were made to the relation definitions and dataset. [sent-67, score-0.351]
35 The number of refinement rounds was arbitrarily limited to five. [sent-68, score-0.076]
36 The agreement and entropy figures for these five intermediate annotation rounds are given in Table 4. [sent-70, score-0.211]
37 In all the possessive annotation tables, Annotator A refers to the primary author and the labels B and C refer to two additional annotators. [sent-71, score-0.442]
38 To calculate a final measure of inter-annotator agreement, we randomly drew 150 examples from the dataset not used in the previous refinement iterations, with 50 examples coming from each of used for annotation. [sent-72, score-0.221]
39 All three annotators initially agreed on 82 of the 150 examples, leaving 68 examples with at least some disagreement, including 17 for which all three annotators disagreed. [sent-74, score-0.165]
40 Annotators then engaged in a new task in which they re-annotated these 68 examples, in each case being able to select only from the definitions previously chosen for each example by at least one annotator. [sent-75, score-0.056]
41 No indication of who or how many people had previously selected the definitions was 374 Figure 2: Semantic relation distribution for the dataset presented in this work. [sent-76, score-0.175]
42 After the revision process, all three annotators agreed in 109 cases and all three disagreed in only 6 cases. [sent-80, score-0.098]
43 During the revision process, Annotator A made 8 changes, B made 20 changes, and C made 33 changes. [sent-81, score-0.049]
44 Annotator A likely made the fewest changes because he, as the primary author, spent a significant amount of time thinking about, writing, and re-writing the definitions used for the various iterations. [sent-82, score-0.094]
45 Annotator C’s annotation work tended to be less consis- tent in general than Annotator B’s throughout this work as well as in a different task not discussed within this paper, which probably why Annotator C made more changes than Annotator B. [sent-83, score-0.082]
46 Prior to this revision process, the three-way Fleiss’ Kappa score was 0. [sent-84, score-0.049]
47 The inter-annotator agreement and entropy figures for before and after this revision process, including pairwise scores between individual annotators, are presented in Tables 5 and 6. [sent-87, score-0.185]
48 2 Distribution of Relations The distribution of semantic relations varies somewhat by the data source. [sent-89, score-0.174]
49 The Jungle Book’s distribution is significantly different from the oth3Of course, if three definitions were present, it could be inferred that all three annotators had initially disagreed. [sent-90, score-0.105]
50 For instance, the LOCATION and TEMPORAL relations almost never occur in The History of the Decline and Fall of the Roman Empire. [sent-93, score-0.122]
51 The distribution of relations for each data source is presented in Figure 2. [sent-95, score-0.122]
52 Though it is harder to compare across datasets using different annotation schemes, there are at least a couple notable differences between the distribution of relations for Badulescu and Moldovan’s (2009) dataset and the distribution of relations used in this work. [sent-96, score-0.33]
53 Another difference is a higher incidence of the KINSHIP relation (6. [sent-100, score-0.077]
54 3 Encountered Ambiguities One of the problems with creating a list of relations expressed by ’s-constructions is that some examples can potentially fit into multiple cate- gories. [sent-105, score-0.189]
55 For example, Joe ’s resentment encodes 375 both SUBJECTIVE relation and MENTAL EXPERIENCER relations and UK’s cities encodes both PARTITIVE and LOCATION relations. [sent-106, score-0.24]
56 A representative list of these types of issues along with examples designed to illustrate them is presented in Table 7. [sent-107, score-0.067]
57 2 Feature Generation For feature generation, we conflated the possessive pronouns ‘his’, ‘her’, ‘my’, and ‘your’ to ‘person. [sent-116, score-0.398]
58 • • • • • The possessor word The possessee word The syntactic governor of the possessee word The set of words between the possessor and possessee word (e. [sent-121, score-1.282]
59 , first in John ’s first kiss) The word to the right of the possessee The following feature templates are used to gener- ate features from the above words. [sent-123, score-0.305]
60 cognition) Set of words from the WordNet definitions (gloss terms) The list of words connected via WordNet part-of links (part words) The word’s text (the word itself) A collection of affix features (e. [sent-131, score-0.087]
61 The fact that the score for The Jungle Book was the lowest is somewhat surprising considering it contains a high percentage ofbody part and kinship terms, which tend to be straightforward, but this may be because the other sources comprise approximately 94% of the training examples. [sent-140, score-0.144]
62 Given that human agreement typically represents an upper bound on machine performance in classification tasks, the 87. [sent-141, score-0.126]
63 One explanation is that the examples pulled out for the inter-annotator agreement study each had a unique possessee word. [sent-143, score-0.466]
64 For example, “expectations”, as in “ana- lyst’s expectations”, occurs 26 times as the possessee in the dataset, but, for the inter-annotator agreement study, at most one of these examples could be included. [sent-144, score-0.466]
65 More importantly, when the initial relations were being defined, the data were first sorted based upon the possessee and then the possessor in order to create blocks of similar examples. [sent-145, score-0.59]
66 Doing this allowed multiple examples to be assigned to a category more quickly because one can decide upon a category for the whole lot at once and thenjust extract the few, if any, that belong to other categories. [sent-146, score-0.067]
67 C82763406 Table 4: Intermediate results for the possessives refinement work. [sent-157, score-0.369]
68 5117 Table 5: Final possessives annotation agreement figures before revisions. [sent-190, score-0.504]
69 4685 Table 6: Final possessives annotation agreement figures after revisions. [sent-222, score-0.504]
70 This advantage did not exist in the inter-annotator agreement study. [sent-250, score-0.094]
71 Based upon the leave-one-out and only-one feature evaluation experiment results, it appears that the possessee word is more important to classification than the possessor word. [sent-253, score-0.5]
72 The possessor word is still valuable though, with it likely being more 5. [sent-254, score-0.163]
73 Curiously, although hypernyms are commonly used as features in NLP classification tasks, gloss terms, which are rarely used for these tasks, are approximately as useful, at least in this particular context. [sent-262, score-0.065]
74 1 Linguistics Semantic relation inventories for the English ’sconstruction have been around for some time; Taylor (1996) mentions a set of 6 relations enumerated by Poutsma (1914–1916). [sent-265, score-0.239]
75 Curiously, there is not a single dominant semantic relation inventory for possessives. [sent-266, score-0.216]
76 A representative example of semantic relation inventories for ’s-constructions is the one given by Quirk et al. [sent-267, score-0.169]
77 Interestingly, the set of relations expressed by possessives varies by language. [sent-269, score-0.446]
78 For example, Classical Greek permits a standard of comparison relation (e. [sent-270, score-0.077]
79 , “better than Plato”) (Nikiforidou, 1991), and, in Japanese, some relations are ex- pressed in the opposite direction (e. [sent-272, score-0.122]
80 To explain how and why such seemingly different relations as whole+part and cause+effect are expressed by the same linguistic phenomenon, Nikiforidou (1991) pursues an approach of metaphorical structuring in line with the work of Lakoff and Johnson (1980) and Lakoff (1987). [sent-277, score-0.122]
81 She thus proposes a variety of such metaphors as THINGS THAT HAPPEN (TO US) ARE (OUR) POSSESSIONS and CAUSES ARE ORIGINS to explain how the different relations expressed by possessives extend from one another. [sent-278, score-0.446]
82 Certainly, not all, or even most, of the linguistics literature on English possessives focuses on creating lists of semantic relations. [sent-279, score-0.376]
83 They split lexical possession into four types: inherent, part-whole, agentive, and control, with agentive and control encompassing many, if not most, of the cases involving sortal nouns. [sent-285, score-0.097]
84 A variety of other issues related to possessives considered by the linguistics literature include adjectival modifiers that significantly alter interpretation (e. [sent-286, score-0.411]
85 , cases where the possessee is omitted, as in “Eat at Joe’s”), possessive compounds (e. [sent-292, score-0.788]
86 , driver’s license), the syntactic structure of possessives, definitiveness, changes over the course of history, and differences between languages in terms of which relations may be expressed by the genitive. [sent-294, score-0.16]
87 , 2010), disambiguating preposition senses (Litkowski and Hargraves, 2007), or annotating the relation between nominals in more arbitrary constructions within the same sentence (Hendrickx et al. [sent-298, score-0.12]
88 In these tasks, participating systems recover the implicit predicate between the nouns in noun compounds by creating potentially unique paraphrases for each example. [sent-304, score-0.137]
89 For instance, a system might generate the paraphrase made of for the noun com378 Table 8: Results for leave-one-out and only-one feature template ablation experiment results for all feature templates sorted by the only-one case. [sent-305, score-0.052]
90 L, R, C, G, B, and N stand for left word (possessor), right word (possessee), pairwise combination of outputs for possessor and possessee, syntactic governor of possessee, all tokens between possessor and possessee, and the word next to the possessee (on the right), respectively. [sent-306, score-0.672]
91 This approach could be applied to possessives interpretation as well. [sent-310, score-0.411]
92 , 2004) provides coarse annotations for some of the possessive constructions in the Penn Treebank, but only those that meet their criteria. [sent-313, score-0.441]
93 We explain our methodology for building this inventory and dataset and report a strong level of inter-annotator agreement, reaching 0. [sent-315, score-0.129]
94 It is the only large fully-annotated publiclyavailable collection of possessive examples that we are aware of. [sent-318, score-0.496]
95 4% accuracy—the highest automatic possessive interpretation accuracy figured reported to date. [sent-320, score-0.485]
96 These high results suggest that SVMs are a good choice for automatic possessive interpre379 tation systems, in contrast to Moldovan and Badulescu (2005) findings. [sent-321, score-0.398]
97 8 Future Work Going forward, we would like to examine the various ambiguities of possessives described in Section 4. [sent-326, score-0.324]
98 Instead of trying to find the one-best interpretation for a given possessive example, we would like to produce a list of all appropriate intepretations. [sent-328, score-0.485]
99 Another avenue for future research is to study variation in possessive use across genres, including scientific and technical genres. [sent-329, score-0.398]
100 Similarly, one could automatically process large volumes of text from various time periods to investigate changes in the use of the possessive over time. [sent-330, score-0.436]
wordName wordTfidf (topN-words)
[('possessive', 0.398), ('possessives', 0.324), ('possessee', 0.305), ('badulescu', 0.216), ('moldovan', 0.178), ('possessor', 0.163), ('partitive', 0.162), ('jungle', 0.144), ('kinship', 0.144), ('joe', 0.141), ('butnariu', 0.122), ('experiencer', 0.122), ('relations', 0.122), ('roman', 0.114), ('aghdha', 0.108), ('empire', 0.108), ('decline', 0.106), ('agreement', 0.094), ('book', 0.091), ('qb', 0.09), ('inventory', 0.087), ('interpretation', 0.087), ('compounds', 0.085), ('recipient', 0.083), ('hendrickx', 0.081), ('relation', 0.077), ('tratz', 0.071), ('nakov', 0.069), ('preslav', 0.069), ('examples', 0.067), ('fall', 0.064), ('producer', 0.062), ('history', 0.061), ('hdfre', 0.061), ('sortal', 0.061), ('vikner', 0.061), ('fleiss', 0.061), ('location', 0.06), ('subjective', 0.058), ('diarmuid', 0.057), ('relational', 0.057), ('stan', 0.057), ('definitions', 0.056), ('kappa', 0.055), ('penn', 0.054), ('libya', 0.054), ('scattering', 0.054), ('noun', 0.052), ('semantic', 0.052), ('szpakowicz', 0.051), ('nam', 0.051), ('quirk', 0.051), ('annotator', 0.051), ('mental', 0.05), ('barker', 0.05), ('annotators', 0.049), ('revision', 0.049), ('wordnet', 0.048), ('jb', 0.047), ('tony', 0.046), ('refinement', 0.045), ('lakoff', 0.045), ('annotation', 0.044), ('constructions', 0.043), ('temporal', 0.043), ('dataset', 0.042), ('figures', 0.042), ('cristina', 0.041), ('governor', 0.041), ('adelphi', 0.041), ('boa', 0.041), ('bolivia', 0.041), ('curiously', 0.041), ('genitives', 0.041), ('litkowski', 0.041), ('nikiforidou', 0.041), ('partee', 0.041), ('resentment', 0.041), ('rosenbach', 0.041), ('inventories', 0.04), ('compound', 0.039), ('objective', 0.039), ('attribute', 0.038), ('changes', 0.038), ('chicago', 0.038), ('possession', 0.036), ('achievements', 0.036), ('ptb', 0.034), ('kim', 0.034), ('treebank', 0.033), ('arm', 0.033), ('nombank', 0.033), ('sidney', 0.033), ('gloss', 0.033), ('classification', 0.032), ('hovy', 0.032), ('things', 0.031), ('collection', 0.031), ('rounds', 0.031), ('siegel', 0.031)]
simIndex simValue paperId paperTitle
same-paper 1 1.0000001 61 acl-2013-Automatic Interpretation of the English Possessive
Author: Stephen Tratz ; Eduard Hovy
Abstract: The English ’s possessive construction occurs frequently in text and can encode several different semantic relations; however, it has received limited attention from the computational linguistics community. This paper describes the creation of a semantic relation inventory covering the use of ’s, an inter-annotator agreement study to calculate how well humans can agree on the relations, a large collection of possessives annotated according to the relations, and an accurate automatic annotation system for labeling new examples. Our 21,938 example dataset is by far the largest annotated possessives dataset we are aware of, and both our automatic classification system, which achieves 87.4% accuracy in our classification experiment, and our annotation data are publicly available.
2 0.07897266 291 acl-2013-Question Answering Using Enhanced Lexical Semantic Models
Author: Wen-tau Yih ; Ming-Wei Chang ; Christopher Meek ; Andrzej Pastusiak
Abstract: In this paper, we study the answer sentence selection problem for question answering. Unlike previous work, which primarily leverages syntactic analysis through dependency tree matching, we focus on improving the performance using models of lexical semantic resources. Experiments show that our systems can be consistently and significantly improved with rich lexical semantic information, regardless of the choice of learning algorithms. When evaluated on a benchmark dataset, the MAP and MRR scores are increased by 8 to 10 points, compared to one of our baseline systems using only surface-form matching. Moreover, our best system also outperforms pervious work that makes use of the dependency tree structure by a wide margin.
3 0.074142769 306 acl-2013-SPred: Large-scale Harvesting of Semantic Predicates
Author: Tiziano Flati ; Roberto Navigli
Abstract: We present SPred, a novel method for the creation of large repositories of semantic predicates. We start from existing collocations to form lexical predicates (e.g., break ∗) and learn the semantic classes that best f∗it) tahned ∗ argument. Taon idco this, we extract failtl thhee ∗ occurrences ion Wikipedia ewxthraiccht match the predicate and abstract its arguments to general semantic classes (e.g., break BODY PART, break AGREEMENT, etc.). Our experiments show that we are able to create a large collection of semantic predicates from the Oxford Advanced Learner’s Dictionary with high precision and recall, and perform well against the most similar approach.
4 0.069816746 339 acl-2013-Temporal Signals Help Label Temporal Relations
Author: Leon Derczynski ; Robert Gaizauskas
Abstract: Automatically determining the temporal order of events and times in a text is difficult, though humans can readily perform this task. Sometimes events and times are related through use of an explicit co-ordination which gives information about the temporal relation: expressions like “before ” and “as soon as”. We investigate the r oˆle that these co-ordinating temporal signals have in determining the type of temporal relations in discourse. Using machine learning, we improve upon prior approaches to the problem, achieving over 80% accuracy at labelling the types of temporal relation between events and times that are related by temporal signals.
5 0.065597847 242 acl-2013-Mining Equivalent Relations from Linked Data
Author: Ziqi Zhang ; Anna Lisa Gentile ; Isabelle Augenstein ; Eva Blomqvist ; Fabio Ciravegna
Abstract: Linking heterogeneous resources is a major research challenge in the Semantic Web. This paper studies the task of mining equivalent relations from Linked Data, which was insufficiently addressed before. We introduce an unsupervised method to measure equivalency of relation pairs and cluster equivalent relations. Early experiments have shown encouraging results with an average of 0.75~0.87 precision in predicting relation pair equivalency and 0.78~0.98 precision in relation clustering. 1
6 0.060006633 152 acl-2013-Extracting Definitions and Hypernym Relations relying on Syntactic Dependencies and Support Vector Machines
7 0.058122303 169 acl-2013-Generating Synthetic Comparable Questions for News Articles
8 0.057915706 67 acl-2013-Bi-directional Inter-dependencies of Subjective Expressions and Targets and their Value for a Joint Model
9 0.057321165 43 acl-2013-Align, Disambiguate and Walk: A Unified Approach for Measuring Semantic Similarity
10 0.056759905 83 acl-2013-Collective Annotation of Linguistic Resources: Basic Principles and a Formal Model
11 0.056318551 368 acl-2013-Universal Dependency Annotation for Multilingual Parsing
12 0.055057004 373 acl-2013-Using Conceptual Class Attributes to Characterize Social Media Users
13 0.053829547 52 acl-2013-Annotating named entities in clinical text by combining pre-annotation and active learning
14 0.051989071 41 acl-2013-Aggregated Word Pair Features for Implicit Discourse Relation Disambiguation
15 0.051909886 212 acl-2013-Language-Independent Discriminative Parsing of Temporal Expressions
16 0.04923062 245 acl-2013-Modeling Human Inference Process for Textual Entailment Recognition
17 0.049032874 116 acl-2013-Detecting Metaphor by Contextual Analogy
18 0.048239429 22 acl-2013-A Structured Distributional Semantic Model for Event Co-reference
19 0.048167862 98 acl-2013-Cross-lingual Transfer of Semantic Role Labeling Models
20 0.04785997 96 acl-2013-Creating Similarity: Lateral Thinking for Vertical Similarity Judgments
topicId topicWeight
[(0, 0.151), (1, 0.057), (2, -0.03), (3, -0.077), (4, -0.032), (5, 0.003), (6, -0.037), (7, -0.012), (8, 0.05), (9, 0.013), (10, -0.008), (11, 0.023), (12, -0.057), (13, -0.001), (14, -0.063), (15, -0.02), (16, -0.035), (17, -0.015), (18, -0.038), (19, -0.025), (20, -0.01), (21, -0.005), (22, -0.021), (23, 0.038), (24, 0.052), (25, 0.043), (26, -0.055), (27, -0.024), (28, -0.053), (29, 0.018), (30, 0.001), (31, 0.041), (32, 0.01), (33, -0.046), (34, 0.063), (35, -0.009), (36, 0.047), (37, 0.012), (38, 0.026), (39, -0.018), (40, 0.001), (41, 0.028), (42, 0.004), (43, 0.043), (44, 0.069), (45, -0.031), (46, 0.007), (47, 0.002), (48, 0.016), (49, -0.007)]
simIndex simValue paperId paperTitle
same-paper 1 0.9195013 61 acl-2013-Automatic Interpretation of the English Possessive
Author: Stephen Tratz ; Eduard Hovy
Abstract: The English ’s possessive construction occurs frequently in text and can encode several different semantic relations; however, it has received limited attention from the computational linguistics community. This paper describes the creation of a semantic relation inventory covering the use of ’s, an inter-annotator agreement study to calculate how well humans can agree on the relations, a large collection of possessives annotated according to the relations, and an accurate automatic annotation system for labeling new examples. Our 21,938 example dataset is by far the largest annotated possessives dataset we are aware of, and both our automatic classification system, which achieves 87.4% accuracy in our classification experiment, and our annotation data are publicly available.
2 0.69371998 367 acl-2013-Universal Conceptual Cognitive Annotation (UCCA)
Author: Omri Abend ; Ari Rappoport
Abstract: Syntactic structures, by their nature, reflect first and foremost the formal constructions used for expressing meanings. This renders them sensitive to formal variation both within and across languages, and limits their value to semantic applications. We present UCCA, a novel multi-layered framework for semantic representation that aims to accommodate the semantic distinctions expressed through linguistic utterances. We demonstrate UCCA’s portability across domains and languages, and its relative insensitivity to meaning-preserving syntactic variation. We also show that UCCA can be effectively and quickly learned by annotators with no linguistic background, and describe the compilation of a UCCAannotated corpus.
Author: Guido Boella ; Luigi Di Caro
Abstract: In this paper we present a technique to reveal definitions and hypernym relations from text. Instead of using pattern matching methods that rely on lexico-syntactic patterns, we propose a technique which only uses syntactic dependencies between terms extracted with a syntactic parser. The assumption is that syntactic information are more robust than patterns when coping with length and complexity of the sentences. Afterwards, we transform such syntactic contexts in abstract representations, that are then fed into a Support Vector Machine classifier. The results on an annotated dataset of definitional sentences demonstrate the validity of our approach overtaking current state-of-the-art techniques.
4 0.67695367 242 acl-2013-Mining Equivalent Relations from Linked Data
Author: Ziqi Zhang ; Anna Lisa Gentile ; Isabelle Augenstein ; Eva Blomqvist ; Fabio Ciravegna
Abstract: Linking heterogeneous resources is a major research challenge in the Semantic Web. This paper studies the task of mining equivalent relations from Linked Data, which was insufficiently addressed before. We introduce an unsupervised method to measure equivalency of relation pairs and cluster equivalent relations. Early experiments have shown encouraging results with an average of 0.75~0.87 precision in predicting relation pair equivalency and 0.78~0.98 precision in relation clustering. 1
5 0.67299449 364 acl-2013-Typesetting for Improved Readability using Lexical and Syntactic Information
Author: Ahmed Salama ; Kemal Oflazer ; Susan Hagan
Abstract: We present results from our study ofwhich uses syntactically and semantically motivated information to group segments of sentences into unbreakable units for the purpose of typesetting those sentences in a region of a fixed width, using an otherwise standard dynamic programming line breaking algorithm, to minimize raggedness. In addition to a rule-based baseline segmenter, we use a very modest size text, manually annotated with positions of breaks, to train a maximum entropy classifier, relying on an extensive set of lexical and syntactic features, which can then predict whether or not to break after a certain word position in a sentence. We also use a simple genetic algorithm to search for a subset of the features optimizing F1, to arrive at a set of features that delivers 89.2% Precision, 90.2% Recall (89.7% F1) on a test set, improving the rule-based baseline by about 11points and the classifier trained on all features by about 1point in F1. 1 Introduction and Motivation Current best practice in typography focuses on several interrelated factors (Humar et al., 2008; Tinkel, 1996). These factors include typeface selection, the color of the type and its contrast with the background, the size of the type, the length of the lines of type in the body of the text, the media in which the type will live, the distance between each line of type, and the appearance of the justified or ragged right side edge of the paragraphs, which should maintain either the appearance of a straight line on both sides of the block of type (justified) or create a gentle wave on the ragged right side edge. cmu .edu hagan @ cmu .edu This paper addresses one aspect of current “best practice,” concerning the alignment of text in a paragraph. While current practice values that gentle “wave,” which puts the focus on the elegant look of the overall paragraph, it does so at the expense of meaning-making features. Meaningmaking features enable typesetting to maintain the integrity of phrases within sentences, giving those interests equal consideration with the overall look of the paragraph. Figure 1 (a) shows a text fragment typeset without any regard to natural breaks while (b) shows an example of a typesetting that we would like to get, where many natural breaks are respected. While current practice works well enough for native speakers, fluency problems for non-native speakers lead to uncertainty when the beginning and end of English phrases are interrupted by the need to move to the next line of the text before completing the phrase. This pause is a potential problem for readers because they try to interpret content words, relate them to their referents and anticipate the role of the next word, as they encounter them in the text (Just and Carpenter, 1980). While incorrect anticipation might not be problematic for native speakers, who can quickly re-adjust, non-native speakers may find inaccurate anticipation more troublesome. This problem could be more significant because English as a second language (ESL) readers are engaged not only in understanding a foreign language, but also in processing the “anticipated text” as they read a partial phrase, and move to the next line in the text, only to discover that they anticipated meaning incorrectly. Even native speakers with less skill may experience difficulty comprehending text and work with young readers suggests that ”[c]omprehension difficulties may be localized at points of high processing demands whether from syntax or other sources” (Perfetti et al., 2005). As ESL readers process a partial phrase, and move to 719 ProceedingSsof oifa, th Beu 5l1gsarti Aan,An uuaglu Mste 4e-ti9n2g 0 o1f3 t.he ?c A2s0s1o3ci Aatsiosonc fioartio Cno fmorpu Ctoamtiopnuatalt Lioinngauli Lsitnicgsu,i psatgices 719–724, the next line in the text, instances of incorrectly anticipated meaning would logically increase processing demands to a greater degree. Additionally, as readers make meaning, we assume that they don’t parse their thoughts using the same phrasal divisions “needed to diagram a sentence.” Our perspective not only relies on the immediacy assumption, but also develops as an outgrowth of other ways that we make meaning outside of the form or function rules of grammar. Specifically, Halliday and Hasan (1976) found that rules of grammar do not explain how cohesive principals engage readers in meaning making across sentences. In order to make meaning across sentences, readers must be able to refer anaphorically backward to the previous sentence, and cataphorically forward to the next sentence. Along similar lines, readers of a single sentence assume that transitive verbs will include a direct object, and will therefore speculate about what that object might be, and sometimes get it wrong. Thus proper typesetting of a segment of text must explore ways to help readers avoid incorrect anticipation, while also considering those moments in the text where readers tend to pause in order to integrate the meaning of a phrase. Those decisions depend on the context. A phrasal break between a one-word subject and its verb tends to be more unattractive, because the reader does not have to make sense of relationships between the noun/subject and related adjectives before moving on to the verb. In this case, the reader will be more likely to anticipate the verb to come. However, a break between a subject preceded by multiple adjectives and its verb is likely to be more useful to a reader (if not ideal), because the relationships between the noun and its related adjectives are more likely to have thematic importance leading to longer gaze time on the relevant words in the subject phrase (Just and Carpenter, 1980). We are not aware of any prior work for bringing computational linguistic techniques to bear on this problem. A relatively recent study (Levasseur et al., 2006) that accounted only for breaks at commas and ends of sentences, found that even those breaks improved reading fluency. While the participants in that study were younger (7 to 9+ years old), the study is relevant because the challenges those young participants face, are faced again when readers of any age encounter new and complicated texts that present words they do not know, and ideas they have never considered. On the other hand, there is ample work on the basic algorithm to place a sequence of words in a typesetting area with a certain width, commonly known as the optimal line breaking problem (e.g., Plass (1981), Knuth and Plass (1981)). This problem is quite well-understood and basic variants are usually studied as an elementary example application of dynamic programming. In this paper we explore the problem of learning where to break sentences in order to avoid the problems discussed above. Once such unbreakable segments are identified, a simple application of the dynamic programming algorithm for optimal line breaking, using unbreakable segments as “words”, easily typesets the text to a given width area. 2 Text Breaks The rationale for content breaks is linked to our interest in preventing inaccurate anticipation, which is based on the immediacy assumption. The immediacy assumption (Just and Carpenter, 1980) considers, among other things, the reader’s interest in trying to relate content words to their referents as soon as possible. Prior context also encourages the reader to anticipate a particular role or case for the next word, such as agent or the manner in which something is done.Therefore, in defining our breaks, we consider not only the need to maintain the syntactic integrity of phrases, such as the prepositional phrase, but also the semantic integrity across syntactical divisions. For example, semantic integrity is important when transitive verbs anticipate direct objects. Strictly speaking, we define a bad break as one that will cause (i) unintended anaphoric collocation, (ii) unintended cataphoric collocation, or (iii) incorrect anticipation. Using these broad constraints, we derived a set of about 30 rules that define acceptable and nonacceptable breaks, with exceptions based on context and other special cases. Some of the rules are very simple and are only related to the word posi- tion in the sentence: • • Break at the end of a sentence. Keep the first and last words of a sentence wKietehp pth teh rest sotf a aint.d The rest of the rule set are more complex and depend on the structure of the sentence in question, 720 . s anct ions and UN charge s o f gro s s right s abuse s Mi l ary tens i it ons on the Korean peninsula have risen to the i highe st level for years r with the communi st st ate under the youthful Kim threatening nuclear war in re sponse t o UN s anct i s impo s ed a ft e r it s thi rd at omi c t e st l on ast month . It ha s al s o (a) Text with standard typesetting from US s anct i s and UN charge s o f gro s s right s abu s e s . Mi l ary t en s i s on it on on the Ko rean penin sul a have r i en t o the i highe st l s r eve l for year s with the communi st st at e unde r the youthful Kim threat ening nuc l ear war in re spon s e t o UN s anct i s impo s ed a ft e r it s thi rd at omi c t e st l on ast month . (b) Text with syntax-directed typesetting , , Figure 1: Short fragment of text with standard typesetting (a) and with syntax and semantics motivated typesetting (b), both in a 75 character width. e.g.: • • • Keep a single word subject with the verb. Keep an appositive phrase with the noun it renames. Do not break inside a prepositional phrase. • • • Keep marooned prepositions with the word they modify. Keep the verb, the object and the preposition together ei nv a phrasal bvjeercbt phrase. Keep a gerund clause with its adverbial complement. There are exceptions to these rules in certain cases such as overly long phrases. 3 Experimental Setup Our data set consists of a modest set of 150 sentences (3918 tokens) selected from four different documents and manually annotated by a human expert relying on the 30 or so rules. The annotation consists of marking after each token whether one is allowed to break at that position or not.1 We developed three systems for predicting breaks: a rule-based baseline system, a maximumentropy classifier that learns to classify breaks us- ing about 100 lexical, syntactic and collocational features, and a maximum entropy classifier that uses a subset of these features selected by a simple genetic algorithm in a hill-climbing fashion. We evaluated our classifiers intrinsically using the usual measures: 1We expect to make our annotated data available upon the publication of the paper. • Precision: Percentage of the breaks posited tPhraetc were actually ctaogrere octf bthreeak bsre aink tshe p goldstandard hand-annotated data. It is possible to get 100% precision by putting a single break at the end. • Recall: Percentage of the actual breaks correctly posited. tIatg ies possible ttou get 1e0ak0%s c recall by positing a break after each token. F1: The geometric mean of precision and recFall divided by their average. It should be noted that when a text is typeset into an area of width of a certain number of characters, an erroneous break need not necessarily lead to an actual break in the final output, that is an error may • not be too bad. On the other hand, a missed break while not hurting the readability of the text may actually lead to a long segment that may eventually worsen raggedness in the final typesetting. Baseline Classifier We implemented a subset of the rules (those that rely only on lexical and partof-speech information), as a baseline rule-based break classifier. The baseline classifier avoids breaks: • • • after the first word in a sentence, quote or parentheses, before the last word in a sentence, quote or parentheses, asntd w between a punctuation mark following a bweotrwde or b aet wpueennct two nco nmsearckuti vfoel punctuation marks. It posits breaks (i) before a word following a punctuation, and (ii) before prepositions, auxiliary verbs, coordinating conjunctions, subordinate conjunctions, relative pronouns, relative adverbs, conjunctive adverbs, and correlative conjunctions. 721 Maximum Entropy Classifier We used the CRF++ Tool2 but with the option to run it only as a maximum entropy classifier (Berger et al., 1996), to train a classifier. We used a large set of about 100 features grouped into the following categories: • • Lexical features: These features include the tLoekxeinca aln fde athtuer ePsO:S T tag efo fre athtuer previous, current and the next word. We also encode whether the word is part of a compound noun or a verb, or is an adjective that subcategorizes a specific preposition in WordNet, (e.g., familiar with). Constituency structure features: These are Cunolnesxtiictauleinzecdy f setarutucrtuers eth faeat ttaurkees i:nt To aecsecou anret in the parse tree, for a word and its previous and next words, the labels of the parent, the grandparent and their siblings, and number of siblings they have. We also consider the label of the closest common ancestor for a word and its next word. • • Dependency structure features: These are unlDeexipceanldizeendc yfe satrtuurcteus eth faeat essentially capture the number of dependency relation links that cross-over a given word boundary. The motivation for these comes from the desire to limit the amount of information that would need to be carried over that boundary, assuming this would be captured by the number of dependency links over the break point. Baseline feature: This feature reflects Bwahseethlienre the rule-based baseline break classifier posits a break at this point or not. We use the following tools to process the sentences to extract some of these features: • Stanford constituency and dependency parsers, (De Marneffe et al., 2006; Klein and Manning, 2002; Klein and Manning, 2003), • • lemmatization tool in NLTK (Bird, 2006), WordNet for compound (Fellbaum, 1998). nouns and verbs 2Available at http : / / crfpp . googlecode .com/ svn /t runk / doc / index . html . TabPFRle1r c:ailsRoenultsBfra78os09me.l491inBaeslMin89eE078-a.nA382dlMaxi98mE09-.uG27mAEntropy break classifiers Maximum Entropy Classifier with GA Feature Selection We used a genetic algorithm on a development data set, to select a subset of the features above. Basically, we start with a randomly selected set of features and through mutation and crossover try to obtain feature combinations that perform better over the development set in terms of F1 score. After a few hundred generations of this kind of hill-climbing, we get a subset of features that perform the best. 4 Results Our current evaluation is only intrinsic in that we measure our performance in getting the break and no-break points correctly in a test set. The results are shown in Table 1. The column ME-All shows the results for a maximum entropy classifier using all the features and the column ME-GA shows the results for a maximum entropy classifier using about 50 of the about 100 features available, as selected by the genetic algorithm. Our best system delivers 89.2% precision and 90.2% recall (with 89.7% F1), improving the rulebased baseline by about 11points and the classifier trained on all features by about 1point in F1. After processing our test set with the ME-GA classifier, we can feed the segments into a standard word-wrapping dynamic programming algorithm (along with a maximum width) and obtain a typeset version with minimum raggedness on the right margin. This algorithm is fast enough to use even dynamically when resizing a window if the text is displayed in a browser on a screen. Figure 1 (b) displays an example of a small fragment of text typeset using the output of our best break classifier. One can immediately note that this typesetting has more raggedness overall, but avoids the bad breaks in (a). We are currently in the process of designing a series of experiments for extrinsic evaluation to determine if such typeset text helps comprehension for secondary language learners. 722 4.1 Error Analysis An analysis of the errors our best classifier makes (which may or may not be translated into an actual error in the final typesetting) shows that the majority of the errors basically can be categorized into the following groups: • Incorrect breaks posited for multiword colloIcnatcioornrse (e.g., akcst *po of weda fr,o3r rmuulel*ti of law, far ahead* of, raining cats* and dogs, etc.) • Missed breaks after a verb (e.g., calls | an act of war, proceeded to | implement, etc.) Missed breaks before or after prepositions or aMdvisesrebdia blsre (e.g., ethfoer day after | tehpeo wsitoiroldns realized, every .kgi.n,d th | of interference) We expect to overcome such cases by increasing our training data size significantly by using our classifier to break new texts and then have a human annotator to manually correct the breaks. • 5 Conclusions and Future Work We have used syntactically motivated information to help in typesetting text to facilitate better understanding of English text especially by secondary language learners, by avoiding breaks which may cause unnecessary anticipation errors. We have cast this as a classification problem to indicate whether to break after a certain word or not, by taking into account a variety of features. Our best system maximum entropy framework uses about 50 such features, which were selected using a genetic algorithm and performs significantly better than a rule-based break classifier and better than a maximum entropy classifier that uses all available features. We are currently working on extending this work in two main directions: We are designing a set of experiments to extrinsically test whether typesetting by our system improves reading ease and comprehension. We are also looking into a break labeling scheme that is not binary but based on a notion of “badness” perhaps quantized into 3-4 grades, that would allow flexibility between preventing bad breaks and minimizing raggedness. For instance, breaking a noun-phrase right after an initial the may be considered very bad. On the other hand, although it is desirable to keep an object NP together with the preceding transitive verb, – 3* indicates a spurious incorrect break, | indicates a misse*d i nbrdeiacka.t breaking before the object NP, could be OK, if not doing so causes an inordinate amount of raggedness. Then the final typesetting stage can optimize a combination of raggedness and the total “bad- ness” of all the breaks it posits. Acknowledgements This publication was made possible by grant NPRP-09-873-1-129 from the Qatar National Research Fund (a member of the Qatar Foundation). Susan Hagan acknowledges the generous support of the Qatar Foundation through Carnegie Mellon University’s Seed Research program. The statements made herein are solely the responsibility of this author(s), and not necessarily those of the Qatar Foundation. References Adam Berger, Stephen Della Pietra, and Vincent Della Pietra. 1996. A maximum entropy approach to natural language processing. Computational Linguistics, 22(1):39–71. Steven Bird. 2006. NLTK: The natural language toolkit. In Proceedings of the COLING/ACL, pages 69–72. Association for Computational Linguistics. Marie-Catherine De Marneffe, Bill MacCartney, and Christopher D Manning. 2006. Generating typed dependency parses from phrase structure parses. In Proceedings of LREC, volume 6, pages 449–454. Christiane Fellbaum. 1998. WordNet: An electronic lexical database. The MIT Press. M. A. K. Halliday and R. Hasan. 1976. Cohesion in English. Longman, London. I. Humar, M. Gradisar, and T. Turk. 2008. The impact of color combinations on the legibility of a web page text presented on crt displays. International Journal of Industrial Ergonomics, 38(1 1-12):885–899. Marcel A. Just and Patricia A. Carpenter. 1980. A theory of reading: From eye fixations to comprehension. Psychological Review, 87:329–354. Dan Klein and Christopher D. Manning. 2002. Fast exact inference with a factored model for natural language parsing. Advances in Neural Information Processing Systems, 15(2003):3–10. Dan Klein and Christopher D. Manning. 2003. Accurate unlexicalized parsing. In Proceedings of the 41st Annual Meeting on Association for Computational Linguistics-Volume 1, pages 423–430. Asso- ciation for Computational Linguistics. 723 Donald E Knuth and Michael F. Plass. 1981. Breaking paragraphs into lines. Software: Practice and Experience, 11(11): 1119–1 184. Valerie Marciarille Levasseur, Paul Macaruso, Laura Conway Palumbo, and Donald Shankweiler. 2006. Syntactically cued text facilitates oral reading fluency in developing readers. Applied Psycholinguistics, 27(3):423–445. C. A. Perfetti, N. Landi, and J. Oakhill. 2005. The acquisition of reading comprehension skill. In M. J. Snowling and C. Hulme, editors, The science of reading: A handbook, pages 227–247. Blackwell, Oxford. Michael Frederick Plass. 1981. Optimal Pagination Techniques for Automatic Typesetting Systems. Ph.D. thesis, Stanford University. K. Tinkel. 1996. Taking it in: What makes type easier to read. Adobe Magazine, pages 40–50. 724
6 0.66656613 302 acl-2013-Robust Automated Natural Language Processing with Multiword Expressions and Collocations
7 0.65626067 232 acl-2013-Linguistic Models for Analyzing and Detecting Biased Language
8 0.6381216 161 acl-2013-Fluid Construction Grammar for Historical and Evolutionary Linguistics
9 0.63666785 30 acl-2013-A computational approach to politeness with application to social factors
10 0.63551158 298 acl-2013-Recognizing Rare Social Phenomena in Conversation: Empowerment Detection in Support Group Chatrooms
11 0.6297822 52 acl-2013-Annotating named entities in clinical text by combining pre-annotation and active learning
12 0.61845845 6 acl-2013-A Java Framework for Multilingual Definition and Hypernym Extraction
13 0.61623538 170 acl-2013-GlossBoot: Bootstrapping Multilingual Domain Glossaries from the Web
14 0.60511237 159 acl-2013-Filling Knowledge Base Gaps for Distant Supervision of Relation Extraction
15 0.60058987 186 acl-2013-Identifying English and Hungarian Light Verb Constructions: A Contrastive Approach
16 0.60019583 340 acl-2013-Text-Driven Toponym Resolution using Indirect Supervision
17 0.59856057 65 acl-2013-BRAINSUP: Brainstorming Support for Creative Sentence Generation
18 0.59580243 365 acl-2013-Understanding Tables in Context Using Standard NLP Toolkits
19 0.5916096 83 acl-2013-Collective Annotation of Linguistic Resources: Basic Principles and a Formal Model
20 0.59012085 88 acl-2013-Computational considerations of comparisons and similes
topicId topicWeight
[(0, 0.031), (6, 0.033), (7, 0.011), (11, 0.4), (15, 0.014), (24, 0.039), (26, 0.04), (28, 0.014), (35, 0.077), (42, 0.042), (48, 0.041), (70, 0.034), (88, 0.034), (90, 0.026), (95, 0.047), (99, 0.011)]
simIndex simValue paperId paperTitle
1 0.98360294 170 acl-2013-GlossBoot: Bootstrapping Multilingual Domain Glossaries from the Web
Author: Flavio De Benedictis ; Stefano Faralli ; Roberto Navigli
Abstract: We present GlossBoot, an effective minimally-supervised approach to acquiring wide-coverage domain glossaries for many languages. For each language of interest, given a small number of hypernymy relation seeds concerning a target domain, we bootstrap a glossary from the Web for that domain by means of iteratively acquired term/gloss extraction patterns. Our experiments show high performance in the acquisition of domain terminologies and glossaries for three different languages.
2 0.98277307 75 acl-2013-Building Japanese Textual Entailment Specialized Data Sets for Inference of Basic Sentence Relations
Author: Kimi Kaneko ; Yusuke Miyao ; Daisuke Bekki
Abstract: This paper proposes a methodology for generating specialized Japanese data sets for textual entailment, which consists of pairs decomposed into basic sentence relations. We experimented with our methodology over a number of pairs taken from the RITE-2 data set. We compared our methodology with existing studies in terms of agreement, frequencies and times, and we evaluated its validity by investigating recognition accuracy.
3 0.97444749 26 acl-2013-A Transition-Based Dependency Parser Using a Dynamic Parsing Strategy
Author: Francesco Sartorio ; Giorgio Satta ; Joakim Nivre
Abstract: We present a novel transition-based, greedy dependency parser which implements a flexible mix of bottom-up and top-down strategies. The new strategy allows the parser to postpone difficult decisions until the relevant information becomes available. The novel parser has a ∼12% error reduction in unlabeled attach∼ment score over an arc-eager parser, with a slow-down factor of 2.8.
Author: Tirthankar Dasgupta
Abstract: In this work we present psycholinguistically motivated computational models for the organization and processing of Bangla morphologically complex words in the mental lexicon. Our goal is to identify whether morphologically complex words are stored as a whole or are they organized along the morphological line. For this, we have conducted a series of psycholinguistic experiments to build up hypothesis on the possible organizational structure of the mental lexicon. Next, we develop computational models based on the collected dataset. We observed that derivationally suffixed Bangla words are in general decomposed during processing and compositionality between the stem . and the suffix plays an important role in the decomposition process. We observed the same phenomena for Bangla verb sequences where experiments showed noncompositional verb sequences are in general stored as a whole in the ML and low traces of compositional verbs are found in the mental lexicon. 1 IInnttrroodduuccttiioonn Mental lexicon is the representation of the words in the human mind and their associations that help fast retrieval and comprehension (Aitchison, 1987). Words are known to be associated with each other in terms of, orthography, phonology, morphology and semantics. However, the precise nature of these relations is unknown. An important issue that has been a subject of study for a long time is to identify the fundamental units in terms of which the mental lexicon is i itkgp .ernet . in organized. That is, whether lexical representations in the mental lexicon are word based or are they organized along morphological lines. For example, whether a word such as “unimaginable” is stored in the mental lexicon as a whole word or do we break it up “un-” , “imagine” and “able”, understand the meaning of each of these constituent and then recombine the units to comprehend the whole word. Such questions are typically answered by designing appropriate priming experiments (Marslen-Wilson et al., 1994) or other lexical decision tasks. The reaction time of the subjects for recognizing various lexical items under appropriate conditions reveals important facts about their organization in the brain. (See Sec. 2 for models of morphological organization and access and related experiments). A clear understanding of the structure and the processing mechanism of the mental lexicon will further our knowledge of how the human brain processes language. Further, these linguistically important and interesting questions are also highly significant for computational linguistics (CL) and natural language processing (NLP) applications. Their computational significance arises from the issue of their storage in lexical resources like WordNet (Fellbaum, 1998) and raises the questions like, how to store morphologically complex words, in a lexical resource like WordNet keeping in mind the storage and access efficiency. There is a rich literature on organization and lexical access of morphologically complex words where experiments have been conducted mainly for derivational suffixed words of English, Hebrew, Italian, French, Dutch, and few other languages (Marslen-Wilson et al., 2008; Frost et al., 1997; Grainger, et al., 1991 ; Drews and Zwitserlood, 1995). However, we do not know of any such investigations for Indian languages, which 123 Sofia, BuPrlgoacreiead, iAngusgu osft 4h-e9 A 2C01L3 S.tu ?c d2en0t1 3Re Ases aorc hiat Wio nrk fsohro Cp,om papguesta 1ti2o3n–a1l2 L9in,guistics are morphologically richer than many of their Indo-European cousins. Moreover, Indian languages show some distinct phenomena like, compound and composite verbs for which no such investigations have been conducted yet. On the other hand, experiments indicate that mental representation and processing of morphologically complex words are not quite language independent (Taft, 2004). Therefore, the findings from experiments in one language cannot be generalized to all languages making it important to conduct similar experimentations in other languages. This work aims to design cognitively motivated computational models that can explain the organization and processing of Bangla morphologically complex words in the mental lexicon. Presently we will concentrate on the following two aspects: OOrrggaanniizzaattiioonn aanndd pprroocceessssiinngg ooff BBaannggllaa PPo o l yy-mmoorrpphheemmiicc wwoorrddss:: our objective here is to determine whether the mental lexicon decomposes morphologically complex words into its constituent morphemes or does it represent the unanalyzed surface form of a word. OOrrggaanniizzaattiioonn aanndd pprroocceessssiinngg ooff BBaannggllaa ccoomm-ppoouunndd vveerrbbss ((CCVV)) :: compound verbs are the subject of much debate in linguistic theory. No consensus has been reached yet with respect to the issue that whether to consider them as unitary lexical units or are they syntactically assembled combinations of two independent lexical units. As linguistic arguments have so far not led to a consensus, we here use cognitive experiments to probe the brain signatures of verb-verb combinations and propose cognitive as well as computational models regarding the possible organization and processing of Bangla CVs in the mental lexicon (ML). With respect to this, we apply the different priming and other lexical decision experiments, described in literature (Marslen-Wilson et al., 1994; Bentin, S. and Feldman, 1990) specifically for derivationally suffixed polymorphemic words and compound verbs of Bangla. Our cross-modal and masked priming experiment on Bangla derivationally suffixed words shows that morphological relatedness between lexical items triggers a significant priming effect, even when the forms are phonologically/orthographically unrelated. These observations are similar to those reported for English and indicate that derivationally suffixed words in Bangla are in general accessed through decomposition of the word into its constituent morphemes. Further, based on the experimental data we have developed a series of computational models that can be used to predict the decomposition of Bangla polymorphemic words. Our evaluation result shows that decom- position of a polymorphemic word depends on several factors like, frequency, productivity of the suffix and the compositionality between the stem and the suffix. The organization of the paper is as follows: Sec. 2 presents related works; Sec. 3 describes experiment design and procedure; Sec. 4 presents the processing of CVs; and finally, Sec. 5 concludes the paper by presenting the future direction of the work. 2 RReellaatteedd WWoorrkkss 2. . 11 RReepprreesseennttaattiioonn ooff ppoollyymmoorrpphheemmiicc wwoorrddss Over the last few decades many studies have attempted to understand the representation and processing of morphologically complex words in the brain for various languages. Most of the studies are designed to support one of the two mutually exclusive paradigms: the full-listing and the morphemic model. The full-listing model claims that polymorphic words are represented as a whole in the human mental lexicon (Bradley, 1980; Butterworth, 1983). On the other hand, morphemic model argues that morphologically complex words are decomposed and represented in terms of the smaller morphemic units. The affixes are stripped away from the root form, which in turn are used to access the mental lexicon (Taft and Forster, 1975; Taft, 1981 ; MacKay, 1978). Intermediate to these two paradigms is the partial decomposition model that argues that different types of morphological forms are processed separately. For instance, the derived morphological forms are believed to be represented as a whole, whereas the representation of the inflected forms follows the morphemic model (Caramazza et al., 1988). Traditionally, priming experiments have been used to study the effects of morphology in language processing. Priming is a process that results in increase in speed or accuracy of response to a stimulus, called the target, based on the occurrence of a prior exposure of another stimulus, called the prime (Tulving et al., 1982). Here, subjects are exposed to a prime word for a short duration, and are subsequently shown a target word. The prime and target words may be morphologically, phonologically or semantically re124 lated. An analysis of the effect of the reaction time of subjects reveals the actual organization and representation of the lexicon at the relevant level. See Pulvermüller (2002) for a detailed account of such phenomena. It has been argued that frequency of a word influences the speed of lexical processing and thus, can serve as a diagnostic tool to observe the nature and organization of lexical representations. (Taft, 1975) with his experiment on English inflected words, argued that lexical decision responses of polymorphemic words depends upon the base word frequency. Similar observation for surface word frequency was also observed by (Bertram et al., 2000;Bradley, 1980;Burani et al., 1987;Burani et al., 1984;Schreuder et al., 1997; Taft 1975;Taft, 2004) where it has been claimed that words having low surface frequency tends to decompose. Later, Baayen(2000) proposed the dual processing race model that proposes that a specific morphologically complex form is accessed via its parts if the frequency of that word is above a certain threshold of frequency, then the direct route will win, and the word will be accessed as a whole. If it is below that same threshold of frequency, the parsing route will win, and the word will be accessed via its parts. 2. . 22 RReepprreesseennttaattiioonn ooff CCoommppoouunndd A compound verb (CV) consists of two verbs (V1 and V2) acting as and expresses a single expression For example, in the sentence VVeerrbbss a sequence of a single verb of meaning. রুটিগুল ো খেল খেল ো (/ruTigulo kheYe phela/) ―bread-plural-the eat and drop-pres. Imp‖ ―Eat the breads‖ the verb sequence “খেল খেল ো (eat drop)” is an example of CV. Compound verbs are a special phenomena that are abundantly found in IndoEuropean languages like Indian languages. A plethora of works has been done to provide linguistic explanations on the formation of such word, yet none so far has led to any consensus. Hook (1981) considers the second verb V2 as an aspectual complex comparable to the auxiliaries. Butt (1993) argues CV formations in Hindi and Urdu are either morphological or syntactical and their formation take place at the argument struc- ture. Bashir (1993) tried to construct a semantic analysis based on “prepared” and “unprepared mind”. Similar findings have been proposed by Pandharipande (1993) that points out V1 and V2 are paired on the basis of their semantic compatibility, which is subject to syntactic constraints. Paul (2004) tried to represent Bangla CVs in terms of HPSG formalism. She proposes that the selection of a V2 by a V1 is determined at the semantic level because the two verbs will unify if and only if they are semantically compatible. Since none of the linguistic formalism could satisfactorily explain the unique phenomena of CV formation, we here for the first time drew our attention towards psycholinguistic and neurolinguistic studies to model the processing of verb-verb combinations in the ML and compare these responses with that of the existing models. 3 TThhee PPrrooppoosseedd AApppprrooaacchheess 3. . 11 TThhee ppssyycchhoolliinngguuiissttiicc eexxppeerriimmeennttss We apply two different priming experiments namely, the cross modal priming and masked priming experiment discussed in (Forster and Davis, 1984; Rastle et al., 2000;Marslen-Wilson et al., 1994; Marslen-Wilson et al., 2008) for Bangla morphologically complex words. Here, the prime is morphologically derived form of the target presented auditorily (for cross modal priming) or visually (for masked priming). The subjects were asked to make a lexical decision whether the given target is a valid word in that language. The same target word is again probed but with a different audio or visual probe called the control word. The control shows no relationship with the target. For example, baYaska (aged) and baYasa (age) is a prime-target pair, for which the corresponding control-target pair could be naYana (eye) and baYasa (age). Similar to (Marslen-Wilson et al., 2008) the masked priming has been conducted for three different SOA (Stimulus Onset Asynchrony), 48ms, 72ms and 120ms. The SOA is measured as the amount of time between the start the first stimulus till the start of the next stimulus. TCM abl-’+ Sse-+ O1 +:-DatjdgnmAshielbatArDu)f(osiAMrawnteihmsgcdaoe)lEx-npgmAchebamr)iD-gnatmprhdiYlbeaA(n ftrTsli,ae(+gnrmdisc)phroielctn)osrelated, and - implies unrelated. There were 500 prime-target and controltarget pairs classified into five classes. Depending on the class, the prime is related to the target 125 either in terms of morphology, semantics, orthography and/or Phonology (See Table 1). The experiments were conducted on 24 highly educated native Bangla speakers. Nineteen of them have a graduate degree and five hold a post graduate degree. The age of the subjects varies between 22 to 35 years. RReessuullttss:: The RTs with extreme values and incorrect decisions were excluded from the data. The data has been analyzed using two ways ANOVA with three factors: priming (prime and control), conditions (five classes) and prime durations (three different SOA). We observe strong priming effects (p<0.05) when the target word is morphologically derived and has a recognizable suffix, semantically and orthographically related with respect to the prime; no priming effects are observed when the prime and target words are orthographically related but share no morphological or semantic relationship; although not statistically significant (p>0.07), but weak priming is observed for prime target pairs that are only semantically related. We see no significant difference between the prime and control RTs for other classes. We also looked at the RTs for each of the 500 target words. We observe that maximum priming occurs for words in [M+S+O+](69%), some priming is evident in [M+S+O-](51%) and [M'+S-O+](48%), but for most of the words in [M-S+O-](86%) and [M-S-O+](92%) no priming effect was observed. 3. . 22 FFrreeqquueennccyy DDiissttrriibbuuttiioonn MMooddeellss ooff MMoo rrpphhoo-llooggiiccaall PPrroocceessssiinngg From the above results we saw that not all polymorphemic words tend to decompose during processing, thus we need to further investigate the processing phenomena of Bangla derived words. One notable means is to identify whether the stem or suffix frequency is involved in the processing stage of that word. For this, we apply different frequency based models to the Bangla polymorphemic words and try to evaluate their performance by comparing their predicted results with the result obtained through the priming experiment. MMooddeell --11:: BBaassee aanndd SSuurrffaaccee wwoorrdd ffrreeqquueennccyy ee ff-ffeecctt -- It states that the probability of decomposition of a Bangla polymorphemic word depends upon the frequency of its base word. Thus, if the stem frequency of a polymorphemic word crosses a given threshold value, then the word will decomposed into its constituent morpheme. Similar claim has been made for surface word frequency model where decomposition depends upon the frequency of the surface word itself. We have evaluated both the models with the 500 words used in the priming experiments discussed above. We have achieved an accuracy of 62% and 49% respectively for base and surface word frequency models. MMooddeell --22:: CCoommbbiinniinngg tthhee bbaassee aanndd ssuurrffaaccee wwoorrdd ffrreeq quueennccyy -- In a pursuit towards an extended model, we combine model 1 and 2 together. We took the log frequencies of both the base and the derived words and plotted the best-fit regression curve over the given dataset. The evaluation of this model over the same set of 500 target words returns an accuracy of 68% which is better than the base and surface word frequency models. However, the proposed model still fails to predict processing of around 32% of words. This led us to further enhance the model. For this, we analyze the role of suffixes in morphological processing. MMooddeell -- 33:: DDeeggrreeee ooff AAffffiixxaattiioonn aanndd SSuuffffiixx PPrroodd-uuccttiivviittyy:: we examine whether the regression analysis between base and derived frequency of Bangla words varies between suffixes and how these variations affect morphological decomposition. With respect to this, we try to compute the degree of affixation between the suffix and the base word. For this, we perform regression analysis on sixteen different Bangla suffixes with varying degree of type and token frequencies. For each suffix, we choose 100 different derived words. We observe that those suffixes having high value of intercept are forming derived words whose base frequencies are substantially high as compared to their derived forms. Moreover we also observe that high intercept value for a given suffix indicates higher inclination towards decomposition. Next, we try to analyze the role of suffix type/token ratio and compare them with the base/derived frequency ratio model. This has been done by regression analysis between the suffix type-token ratios with the base-surface frequency ratio. We further tried to observe the role of suffix productivity in morphological processing. For this, we computed the three components of productivity P, P* and V as discussed in (Hay and Plag, 2004). P is the “conditioned degree of productivity” and is the probability that we are encountering a word with an affix and it is representing a new type. P* is the “hapaxedconditioned degree of productivity”. It expresses the probability that when an entirely new word is 126 encountered it will contain the suffix. V is the “type frequency”. Finally, we computed the productivity of a suffix through its P, P* and V values. We found that decomposition of Bangla polymorphemic word is directly proportional to the productivity of the suffix. Therefore, words that are composed of productive suffixes (P value ranges between 0.6 and 0.9) like “-oYAlA”, “-giri”, “-tba” and “-panA” are highly decomposable than low productive suffixes like “-Ani”, “-lA”, “-k”, and “-tama”. The evaluation of the proposed model returns an accuracy of 76% which comes to be 8% better than the preceding models. CCoommbbiinniinngg MMooddeell --22 aanndd MMooddeell -- 33:: One important observation that can be made from the above results is that, model-3 performs best in determining the true negative values. It also possesses a high recall value of (85%) but having a low precision of (50%). In other words, the model can predict those words for which decomposition will not take place. On the other hand, results of Model-2 posses a high precision of 70%. Thus, we argue that combining the above two models can better predict the decomposition of Bangla polymorphemic words. Hence, we combine the two models together and finally achieved an overall accuracy of 80% with a precision of 87% and a recall of 78%. This surpasses the performance of the other models discussed earlier. However, around 22% of the test words were wrongly classified which the model fails to justify. Thus, a more rigorous set of experiments and data analysis are required to predict access mechanisms of such Bangla polymorphemic words. 3. . 33 SStteemm- -SSuuffffiixx CCoommppoossiittiioonnaalliittyy Compositionality refers to the fact that meaning of a complex expression is inferred from the meaning of its constituents. Therefore, the cost of retrieving a word from the secondary memory is directly proportional to the cost of retrieving the individual parts (i.e the stem and the suffix). Thus, following the work of (Milin et al., 2009) we define the compositionality of a morphologically complex word (We) as: C(We)=α 1H(We)+α α2H(e)+α α3H(W|e)+ α4H(e|W) Where, H(x) is entropy of an expression x, H(W|e) is the conditional entropy between the stem W and suffix e and is the proportionality factor whose value is computed through regression analysis. Next, we tried to compute the compositionality of the stem and suffixes in terms of relative entropy D(W||e) and Point wise mutual information (PMI). The relative entropy is the measure of the distance between the probability distribution of the stem W and the suffix e. The PMI measures the amount of information that one random variable (the stem) contains about the other (the suffix). We have compared the above three techniques with the actual reaction time data collected through the priming and lexical decision experiment. We observed that all the three information theoretic models perform much better than the frequency based models discussed in the earlier section, for predicting the decomposability of Bangla polymorphemic words. However, we think it is still premature to claim anything concrete at this stage of our work. We believe much more rigorous experiments are needed to be per- formed in order to validate our proposed models. Further, the present paper does not consider factors related to age of acquisition, and word familiarity effects that plays important role in the processing of morphologically complex words. Moreover, it is also very interesting to see how stacking of multiple suffixes in a word are processed by the human brain. 44 OOrrggaanniizzaattiioonn aanndd PPrroocceessssiinngg ooff CCoomm-ppoouunndd VVeerrbbss iinn tthhee MMeennttaall LLeexxiiccoonn Compound verbs, as discussed above, are special type of verb sequences consisting of two or more verbs acting as a single verb and express a single expression of meaning. The verb V1 is known as pole and V2 is called as vector. For example, “ওঠে পড়া ” (getting up) is a compound verb where individual words do not entirely reflects the meaning of the whole expression. However, not all V1+V2 combinations are CVs. For example, expressions like, “নিঠে য়াও ”(take and then go) and “ নিঠে আঠ ়া” (return back) are the examples of verb sequences where meaning of the whole expression can be derived from the mean- ing of the individual component and thus, these verb sequences are not considered as CV. The key question linguists are trying to identify for a long time and debating a lot is whether to consider CVs as a single lexical units or consider them as two separate units. Since linguistic rules fails to explain the process, we for the first time tried to perform cognitive experiments to understand the organization and processing of such verb sequences in the human mind. A clear understanding about these phenomena may help us to classify or extract actual CVs from other verb 127 sequences. In order to do so, presently we have applied three different techniques to collect user data. In the first technique, we annotated 4500 V1+V2 sequences, along with their example sentences, using a group of three linguists (the expert subjects). We asked the experts to classify the verb sequences into three classes namely, CV, not a CV and not sure. Each linguist has received 2000 verb pairs along with their respective example sentences. Out of this, 1500 verb sequences are unique to each of them and rest 500 are overlapping. We measure the inter annotator agreement using the Fleiss Kappa (Fleiss et al., 1981) measure (κ) where the agreement lies around 0.79. Next, out of the 500 common verb sequences that were annotated by all the three linguists, we randomly choose 300 V1+V2 pairs and presented them to 36 native Bangla speakers. We ask each subjects to give a compositionality score of each verb sequences under 1-10 point scale, 10 being highly compositional and 1 for noncompositional. We found an agreement of κ=0.69 among the subjects. We also observe a continuum of compositionality score among the verb sequences. This reflects that it is difficult to classify Bangla verb sequences discretely into the classes of CV and not a CV. We then, compare the compositionality score with that of the expert user’s annotation. We found a significant correlation between the expert annotation and the compositionality score. We observe verb sequences that are annotated as CVs (like, খেঠে খিল )কঠে খি ,ওঠে পড ,have got low compositionality score (average score ranges between 1-4) on the other hand high compositional values are in general tagged as not a cv (নিঠে য়া (come and get), নিঠে আে (return back), তুঠল খেঠেনি (kept), গনিঠে পিল (roll on floor)). This reflects that verb sequences which are not CV shows high degree of compositionality. In other words non CV verbs can directly interpret from their constituent verbs. This leads us to the possibility that compositional verb sequences requires individual verbs to be recognized separately and thus the time to recognize such expressions must be greater than the non-compositional verbs which maps to a single expression of meaning. In order to validate such claim we perform a lexical decision experiment using 32 native Bangla speakers with 92 different verb sequences. We followed the same experimental procedure as discussed in (Taft, 2004) for English polymorphemic words. However, rather than derived words, the subjects were shown a verb sequence and asked whether they recognize them as a valid combination. The reaction time (RT) of each subject is recorded. Our preliminarily observation from the RT analysis shows that as per our claim, RT of verb sequences having high compositionality value is significantly higher than the RTs for low or noncompositional verbs. This proves our hypothesis that Bangla compound verbs that show less compositionality are stored as a hole in the mental lexicon and thus follows the full-listing model whereas compositional verb phrases are individually parsed. However, we do believe that our experiment is composed of a very small set of data and it is premature to conclude anything concrete based only on the current experimental results. 5 FFuuttuurree DDiirreeccttiioonnss In the next phase of our work we will focus on the following aspects of Bangla morphologically complex words: TThhee WWoorrdd FFaammiilliiaarriittyy EEffffeecctt:: Here, our aim is to study the role of familiarity of a word during its processing. We define the familiarity of a word in terms of corpus frequency, Age of acquisition, the level of language exposure of a person, and RT of the word etc. RRoollee ooff ssuuffffiixx ttyyppeess iinn mmoorrpphhoollooggiiccaall ddeeccoo mm ppoo-ssiittiioonn:: For native Bangla speakers which morphological suffixes are internalized and which are just learnt in school, but never internalized. We can compare the representation of Native, Sanskrit derived and foreign suffixes in Bangla words. CCoommppuuttaattiioonnaall mmooddeellss ooff oorrggaanniizzaattiioonn aanndd pprroocceessssiinngg ooff BBaannggllaa ccoommppoouunndd vveerrbbss :: presently we have performed some small set of experiments to study processing of compound verbs in the mental lexicon. In the next phase of our work we will extend the existing experiments and also apply some more techniques like, crowd sourcing and language games to collect more relevant RT and compositionality data. Finally, based on the collected data we will develop computational models that can explain the possible organizational structure and processing mechanism of morphologically complex Bangla words in the mental lexicon. Reference Aitchison, J. (1987). ―Words in the mind: An introduction to the mental lexicon‖. Wiley-Blackwell, 128 Baayen R. H. (2000). ―On frequency, transparency and productivity‖. G. Booij and J. van Marle (eds), Yearbook of Morphology, pages 181-208, Baayen R.H. (2003). ―Probabilistic approaches to morphology‖. Probabilistic linguistics, pages 229287. Baayen R.H., T. Dijkstra, and R. Schreuder. (1997). ―Singulars and plurals in dutch: Evidence for a parallel dual-route model‖. Journal of Memory and Language, 37(1):94-1 17. Bashir, E. (1993), ―Causal Chains and Compound Verbs.‖ In M. K. Verma ed. (1993). Bentin, S. & Feldman, L.B. (1990). The contribution of morphological and semantic relatedness to repetition priming at short and long lags: Evidence from Hebrew. Quarterly Journal of Experimental Psychology, 42, pp. 693–71 1. Bradley, D. (1980). Lexical representation of derivational relation, Juncture, Saratoga, CA: Anma Libri, pp. 37-55. Butt, M. (1993), ―Conscious choice and some light verbs in Urdu.‖ In M. K. Verma ed. (1993). Butterworth, B. (1983). Lexical Representation, Language Production, Vol. 2, pp. 257-294, San Diego, CA: Academic Press. Caramazza, A., Laudanna, A. and Romani, C. (1988). Lexical access and inflectional morphology. Cognition, 28, pp. 297-332. Drews, E., and Zwitserlood, P. (1995).Morphological and orthographic similarity in visual word recognition. Journal of Experimental Psychology:HumanPerception andPerformance, 21, 1098– 1116. Fellbaum, C. (ed.). (1998). WordNet: An Electronic Lexical Database, MIT Press. Forster, K.I., and Davis, C. (1984). Repetition priming and frequency attenuation in lexical access. Journal of Experimental Psychology: Learning, Memory, and Cognition, 10, 680–698. Frost, R., Forster, K.I., & Deutsch, A. (1997). What can we learn from the morphology of Hebrew? A masked-priming investigation of morphological representation. Journal of Experimental Psychology: Learning, Memory, and Cognition, 23, 829–856. Grainger, J., Cole, P., & Segui, J. (1991). Masked morphological priming in visual word recognition. Journal of Memory and Language, 30, 370–384. Hook, P. E. (1981). ―Hindi Structures: Intermediate Level.‖ Michigan Papers on South and Southeast Asia, The University of Michigan Center for South and Southeast Studies, Ann Arbor, Michigan. Joseph L Fleiss, Bruce Levin, and Myunghee Cho Paik. 1981. The measurement of interrater agreement. Statistical methods for rates and proportions,2:212–236. MacKay,D.G.(1978), Derivational rules and the internal lexicon. Journal of Verbal Learning and Verbal Behavior, 17, pp.61-71. Marslen-Wilson, W.D., & Tyler, L.K. (1997). Dissociating types of mental computation. Nature, 387, pp. 592–594. Marslen-Wilson, W.D., & Tyler, L.K. (1998). Rules, representations, and the English past tense. Trends in Cognitive Sciences, 2, pp. 428–435. Marslen-Wilson, W.D., Tyler, L.K., Waksler, R., & Older, L. (1994). Morphology and meaning in the English mental lexicon. Psychological Review, 101, pp. 3–33. Marslen-Wilson,W.D. and Zhou,X.( 1999). Abstractness, allomorphy, and lexical architecture. Language and Cognitive Processes, 14, 321–352. Milin, P., Kuperman, V., Kosti´, A. and Harald R., H. (2009). Paradigms bit by bit: an information- theoretic approach to the processing of paradigmatic structure in inflection and derivation, Analogy in grammar: Form and acquisition, pp: 214— 252. Pandharipande, R. (1993). ―Serial verb construction in Marathi.‖ In M. K. Verma ed. (1993). Paul, S. (2004). An HPSG Account of Bangla Compound Verbs with LKB Implementation, Ph.D. Dissertation. CALT, University of Hyderabad. Pulvermüller, F. (2002). The Neuroscience guage. Cambridge University Press. of Lan- Stolz, J.A., and Feldman, L.B. (1995). The role of orthographic and semantic transparency of the base morpheme in morphological processing. In L.B. Feldman (Ed.) Morphological aspects of language processing. Hillsdale, NJ: Lawrence Erlbaum Associates Inc. Taft, M., and Forster, K.I.(1975). Lexical storage and retrieval of prefix words. Journal of Verbal Learning and Verbal Behavior, Vol.14, pp. 638-647. Taft, M.(1988). A morphological decomposition model of lexical access. Linguistics, 26, pp. 657667. Taft, M. (2004). Morphological decomposition and the reverse base frequency effect. Quarterly Journal of Experimental Psychology, 57A, pp. 745-765 Tulving, E., Schacter D. L., and Heather A.(1982). Priming Effects in Word Fragment Completion are independent of Recognition Memory. Journal of Experimental Psychology: Learning, Memory and Cognition, vol.8 (4). 129
5 0.9690522 50 acl-2013-An improved MDL-based compression algorithm for unsupervised word segmentation
Author: Ruey-Cheng Chen
Abstract: We study the mathematical properties of a recently proposed MDL-based unsupervised word segmentation algorithm, called regularized compression. Our analysis shows that its objective function can be efficiently approximated using the negative empirical pointwise mutual information. The proposed extension improves the baseline performance in both efficiency and accuracy on a standard benchmark.
6 0.96108568 376 acl-2013-Using Lexical Expansion to Learn Inference Rules from Sparse Data
7 0.94433415 71 acl-2013-Bootstrapping Entity Translation on Weakly Comparable Corpora
same-paper 8 0.92519552 61 acl-2013-Automatic Interpretation of the English Possessive
9 0.86251748 245 acl-2013-Modeling Human Inference Process for Textual Entailment Recognition
10 0.78000367 156 acl-2013-Fast and Adaptive Online Training of Feature-Rich Translation Models
11 0.77238268 358 acl-2013-Transition-based Dependency Parsing with Selectional Branching
12 0.76623166 242 acl-2013-Mining Equivalent Relations from Linked Data
13 0.75131977 27 acl-2013-A Two Level Model for Context Sensitive Inference Rules
14 0.71244854 154 acl-2013-Extracting bilingual terminologies from comparable corpora
15 0.70393932 208 acl-2013-Joint Inference for Heterogeneous Dependency Parsing
16 0.70246524 169 acl-2013-Generating Synthetic Comparable Questions for News Articles
17 0.69370592 202 acl-2013-Is a 204 cm Man Tall or Small ? Acquisition of Numerical Common Sense from the Web
18 0.68643153 387 acl-2013-Why-Question Answering using Intra- and Inter-Sentential Causal Relations
19 0.68168557 132 acl-2013-Easy-First POS Tagging and Dependency Parsing with Beam Search
20 0.67815143 274 acl-2013-Parsing Graphs with Hyperedge Replacement Grammars