acl acl2013 acl2013-170 knowledge-graph by maker-knowledge-mining
Source: pdf
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.
Reference: text
sentIndex sentText sentNum sentScore
1 GlossBoot: Bootstrapping Multilingual Domain Glossaries from the Web flavio Flavio De Benedictis, Stefano Faralli and Roberto Navigli Dipartimento di Informatica Sapienza Universit a` di Roma . [sent-1, score-0.198]
2 it i Abstract We present GlossBoot, an effective minimally-supervised approach to acquiring wide-coverage domain glossaries for many languages. [sent-5, score-0.708]
3 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. [sent-6, score-1.067]
4 Our experiments show high performance in the acquisition of domain terminologies and glossaries for three different languages. [sent-7, score-0.763]
5 1 Introduction Much textual content, such as that available on the Web, contains a great deal of information fo- cused on specific areas of knowledge. [sent-8, score-0.113]
6 However, it is not infrequent that, when reading a domainspecific text, we humans do not know the meaning of one or more terms. [sent-9, score-0.108]
7 To help the human understanding of specialized texts, repositories of textual definitions for technical terms, called glossaries, are compiled as reference resources within each domain of interest. [sent-10, score-0.38]
8 Interestingly, electronic glossaries have been shown to be key resources not only for humans, but also in Natural Language Processing (NLP) tasks such as Question Answering (Cui et al. [sent-11, score-0.552]
9 , 2007), Word Sense Disambiguation (Duan and Yates, 2010; Faralli and Navigli, 2012) and ontology learning (Navigli et al. [sent-12, score-0.025]
10 Today large numbers of glossaries are available on the Web. [sent-15, score-0.552]
11 However most such glossaries are small-scale, being made up of just some hundreds of definitions. [sent-16, score-0.552]
12 Consequently, individual glossaries typically provide a partial view of a given domain. [sent-17, score-0.552]
13 Moreover, there is no easy way of retrieving the subset of Web glossaries which appertains to a domain of interest. [sent-18, score-0.712]
14 Although online services such as Google Define allow the user to retrieve defi- nitions for an input term, such definitions are extracted from Web glossaries and put together for the given term regardless of their domain. [sent-19, score-0.723]
15 As a result, gathering a large-scale, full-fledged domain glossary is not a speedy operation. [sent-20, score-0.699]
16 Collaborative efforts are currently producing large-scale encyclopedias, such as Wikipedia, which are proving very useful in NLP (Hovy et al. [sent-21, score-0.039]
17 However, such glossaries still suffer from the same above-mentioned problems, i. [sent-24, score-0.552]
18 , being incomplete or over-specific,1 and hard to customize according to a user’s needs. [sent-26, score-0.07]
19 To automatically obtain large domain glossaries, over recent years computational approaches have been developed which extract textual definitions from corpora (Navigli and Velardi, 2010; Reiplinger et al. [sent-27, score-0.289]
20 The former methods start from a given set of terms (possibly automatically extracted from a domain corpus) and then harvest textual definitions for these terms from the input corpus using a supervised system. [sent-29, score-0.483]
21 Web- based methods, instead, extract text snippets from Web pages which match pre-defined lexical patterns, such as “X is a Y”, along the lines of Hearst (1992). [sent-30, score-0.063]
22 These approaches typically perform with high precision and low recall, because they fall short of detecting the high variability of the syntactic structure of textual definitions. [sent-31, score-0.091]
23 To address the low-recall issue, recurring cue terms occurring within dictionary and encyclopedic resources can be automatically extracted and incorporated into lexical patterns (Saggion, 2004). [sent-32, score-0.165]
24 However, this approach is term-specific and does not scale to arbitrary terminologies and domains. [sent-33, score-0.081]
25 In this paper we propose GlossBoot, a novel approach which reduces human intervention to a bare minimum and exploits the Web to learn a 1http://en. [sent-34, score-0.079]
26 Given a domain and a language of interest, we bootstrap the glossary learning process with just a few hypernymy relations (such as computer is-a device), with the only condition that the (term, hypernym) pairs must be specific enough to implicitly identify the domain in the target language. [sent-40, score-1.051]
27 Hence we drop the requirement of a large domain corpus, and also avoid the use of training data or a manually defined set of lexical patterns. [sent-41, score-0.13]
28 To the best of our knowledge, this is the first approach which jointly acquires large amounts of terms and glosses from the Web with minimal supervision for any target domain and language. [sent-42, score-0.26]
29 2 GlossBoot Our objective is to harvest a domain glossary G containing pairs of terms/glosses in a given language. [sent-43, score-0.787]
30 To this end, we automatically populate a set of HTML patterns P which we use to extract definitions from Web glossaries. [sent-44, score-0.213]
31 We incrementally populate tPhe : t=wo ∅ s aentsd by means Wofe an cirneitmiaeln stealeldy s peolepuctliaotne step and four iterative steps (cf. [sent-46, score-0.109]
32 Initial seed selection: first, we manually select a set of K hypernymy relation seeds S = {(t1, h1) , . [sent-48, score-0.351]
33 , (tK, hK)}, where the pair (ti, hSi) = c {o(nttains a term ti and }its, generalization hti (e. [sent-51, score-0.181]
34 This is the only human input to the entire glossary learning process. [sent-54, score-0.541]
35 The selection of the input seeds plays a key role in the bootstrapping process, in that the pattern and gloss extraction process will be driven by these seeds. [sent-55, score-0.31]
36 The chosen hypernymy relations thus have to be as topical and representative as possible for the domain of interest (e. [sent-56, score-0.309]
37 , (compiler, computer program) is an appropriate pair for computer science, while (byte, unit of measurement) is not, as it might cause the extraction of several glossaries of units and measures). [sent-58, score-0.581]
38 We now set the iteration counter k to 1and start the first iteration ofthe glossary bootstrapping process (steps 2-5). [sent-59, score-0.872]
39 After each iteration k, we keep track of the set of glosses Gk, acquired during iteration k. [sent-60, score-0.271]
40 Seed queries: for each seed pair (ti, hi), we submit the following query to a Web search engine: “ti” “hi” glos saryKeyword2 (where glos saryKeyword is the term in the target language referring to glossary (i. [sent-62, score-0.904]
41 3 Each resulting page is a candidate glossary for the domain implicitly identified by our relation seeds S. [sent-66, score-0.881]
42 Pattern and glossary extraction: we initialize the glossary for iteration k as follows: Gk := ∅. [sent-68, score-1.188]
43 e N teexxtt, snippets s starting wgi ptha ti ,a wnde e hnadr-ing with hi (e. [sent-70, score-0.321]
wordName wordTfidf (topN-words)
[('glossaries', 0.552), ('glossary', 0.541), ('glossboot', 0.226), ('hypernymy', 0.14), ('domain', 0.13), ('navigli', 0.118), ('harvest', 0.116), ('seeds', 0.114), ('glos', 0.098), ('firewall', 0.098), ('definitions', 0.095), ('flavio', 0.09), ('ti', 0.086), ('web', 0.085), ('faralli', 0.085), ('bootstrapping', 0.083), ('velardi', 0.081), ('terminologies', 0.081), ('populate', 0.081), ('iteration', 0.08), ('roma', 0.077), ('gk', 0.077), ('hi', 0.074), ('seed', 0.072), ('glosses', 0.066), ('textual', 0.064), ('snippets', 0.063), ('compiled', 0.058), ('di', 0.054), ('term', 0.05), ('faral', 0.049), ('byte', 0.049), ('compiler', 0.049), ('cused', 0.049), ('encyclopedias', 0.049), ('wgi', 0.049), ('wnde', 0.049), ('interestingly', 0.047), ('acquired', 0.045), ('benedictis', 0.045), ('dipartimento', 0.045), ('navigl', 0.045), ('fujii', 0.045), ('ishikawa', 0.045), ('wofe', 0.045), ('customize', 0.045), ('hti', 0.045), ('submit', 0.045), ('bootstrap', 0.043), ('domainspecific', 0.042), ('sapienza', 0.042), ('wikipedias', 0.042), ('implicitly', 0.041), ('informatica', 0.04), ('stefano', 0.04), ('bare', 0.04), ('recurring', 0.04), ('tphe', 0.04), ('humans', 0.039), ('interest', 0.039), ('acquires', 0.039), ('intervention', 0.039), ('proving', 0.039), ('security', 0.037), ('hsi', 0.037), ('patterns', 0.037), ('saggion', 0.036), ('yates', 0.035), ('hk', 0.034), ('counter', 0.034), ('hearst', 0.033), ('repositories', 0.033), ('encyclopedic', 0.033), ('device', 0.032), ('cui', 0.031), ('duan', 0.03), ('retrieving', 0.03), ('page', 0.03), ('cue', 0.03), ('gloss', 0.03), ('extraction', 0.029), ('hypernym', 0.029), ('today', 0.029), ('wo', 0.029), ('tk', 0.029), ('gathering', 0.028), ('driven', 0.028), ('start', 0.028), ('universit', 0.028), ('incrementally', 0.028), ('variability', 0.027), ('infrequent', 0.027), ('acquiring', 0.026), ('initialize', 0.026), ('services', 0.026), ('process', 0.026), ('ontology', 0.025), ('incomplete', 0.025), ('terms', 0.025), ('relation', 0.025)]
simIndex simValue paperId paperTitle
same-paper 1 0.99999964 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.
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.
3 0.14786683 6 acl-2013-A Java Framework for Multilingual Definition and Hypernym Extraction
Author: Stefano Faralli ; Roberto Navigli
Abstract: In this paper we present a demonstration of a multilingual generalization of Word-Class Lattices (WCLs), a supervised lattice-based model used to identify textual definitions and extract hypernyms from them. Lattices are learned from a dataset of automatically-annotated definitions from Wikipedia. We release a Java API for the programmatic use of multilingual WCLs in three languages (English, French and Italian), as well as a Web application for definition and hypernym extraction from user-provided sentences.
4 0.10836863 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.
5 0.062165935 154 acl-2013-Extracting bilingual terminologies from comparable corpora
Author: Ahmet Aker ; Monica Paramita ; Rob Gaizauskas
Abstract: In this paper we present a method for extracting bilingual terminologies from comparable corpora. In our approach we treat bilingual term extraction as a classification problem. For classification we use an SVM binary classifier and training data taken from the EUROVOC thesaurus. We test our approach on a held-out test set from EUROVOC and perform precision, recall and f-measure evaluations for 20 European language pairs. The performance of our classifier reaches the 100% precision level for many language pairs. We also perform manual evaluation on bilingual terms extracted from English-German term-tagged comparable corpora. The results of this manual evaluation showed 60-83% of the term pairs generated are exact translations and over 90% exact or partial translations.
6 0.050234865 43 acl-2013-Align, Disambiguate and Walk: A Unified Approach for Measuring Semantic Similarity
7 0.048302662 93 acl-2013-Context Vector Disambiguation for Bilingual Lexicon Extraction from Comparable Corpora
8 0.046849426 62 acl-2013-Automatic Term Ambiguity Detection
9 0.046695657 316 acl-2013-SenseSpotting: Never let your parallel data tie you to an old domain
10 0.041238673 188 acl-2013-Identifying Sentiment Words Using an Optimization-based Model without Seed Words
11 0.038371254 111 acl-2013-Density Maximization in Context-Sense Metric Space for All-words WSD
12 0.038232055 134 acl-2013-Embedding Semantic Similarity in Tree Kernels for Domain Adaptation of Relation Extraction
13 0.037964921 112 acl-2013-Dependency Parser Adaptation with Subtrees from Auto-Parsed Target Domain Data
14 0.037685711 281 acl-2013-Post-Retrieval Clustering Using Third-Order Similarity Measures
15 0.037061129 181 acl-2013-Hierarchical Phrase Table Combination for Machine Translation
16 0.035581287 228 acl-2013-Leveraging Domain-Independent Information in Semantic Parsing
17 0.034923524 148 acl-2013-Exploring Sentiment in Social Media: Bootstrapping Subjectivity Clues from Multilingual Twitter Streams
18 0.033797659 272 acl-2013-Paraphrase-Driven Learning for Open Question Answering
19 0.033710588 116 acl-2013-Detecting Metaphor by Contextual Analogy
20 0.033578452 160 acl-2013-Fine-grained Semantic Typing of Emerging Entities
topicId topicWeight
[(0, 0.093), (1, 0.034), (2, 0.011), (3, -0.049), (4, -0.008), (5, -0.019), (6, -0.065), (7, -0.008), (8, 0.031), (9, -0.019), (10, 0.01), (11, 0.026), (12, -0.048), (13, 0.018), (14, 0.049), (15, -0.026), (16, 0.02), (17, -0.0), (18, -0.023), (19, -0.003), (20, -0.005), (21, 0.016), (22, -0.029), (23, 0.07), (24, 0.113), (25, 0.018), (26, -0.024), (27, -0.035), (28, 0.006), (29, 0.131), (30, -0.077), (31, 0.173), (32, 0.056), (33, 0.005), (34, 0.191), (35, 0.077), (36, 0.023), (37, 0.048), (38, -0.047), (39, -0.031), (40, 0.034), (41, 0.015), (42, 0.007), (43, -0.028), (44, 0.011), (45, 0.015), (46, -0.025), (47, 0.077), (48, 0.007), (49, 0.031)]
simIndex simValue paperId paperTitle
same-paper 1 0.93383384 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 0.87902582 6 acl-2013-A Java Framework for Multilingual Definition and Hypernym Extraction
Author: Stefano Faralli ; Roberto Navigli
Abstract: In this paper we present a demonstration of a multilingual generalization of Word-Class Lattices (WCLs), a supervised lattice-based model used to identify textual definitions and extract hypernyms from them. Lattices are learned from a dataset of automatically-annotated definitions from Wikipedia. We release a Java API for the programmatic use of multilingual WCLs in three languages (English, French and Italian), as well as a Web application for definition and hypernym extraction from user-provided sentences.
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 0.49994585 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.
5 0.46092466 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.
6 0.42945355 62 acl-2013-Automatic Term Ambiguity Detection
7 0.42589638 154 acl-2013-Extracting bilingual terminologies from comparable corpora
8 0.4089343 242 acl-2013-Mining Equivalent Relations from Linked Data
9 0.40474135 356 acl-2013-Transfer Learning Based Cross-lingual Knowledge Extraction for Wikipedia
10 0.39883944 65 acl-2013-BRAINSUP: Brainstorming Support for Creative Sentence Generation
11 0.36400574 198 acl-2013-IndoNet: A Multilingual Lexical Knowledge Network for Indian Languages
12 0.35949391 365 acl-2013-Understanding Tables in Context Using Standard NLP Toolkits
13 0.345954 215 acl-2013-Large-scale Semantic Parsing via Schema Matching and Lexicon Extension
14 0.34536555 373 acl-2013-Using Conceptual Class Attributes to Characterize Social Media Users
15 0.34432808 268 acl-2013-PATHS: A System for Accessing Cultural Heritage Collections
16 0.32624531 228 acl-2013-Leveraging Domain-Independent Information in Semantic Parsing
17 0.32327953 269 acl-2013-PLIS: a Probabilistic Lexical Inference System
18 0.32284594 159 acl-2013-Filling Knowledge Base Gaps for Distant Supervision of Relation Extraction
19 0.3176963 238 acl-2013-Measuring semantic content in distributional vectors
20 0.31561741 100 acl-2013-Crowdsourcing Interaction Logs to Understand Text Reuse from the Web
topicId topicWeight
[(0, 0.025), (6, 0.011), (11, 0.59), (24, 0.031), (26, 0.022), (35, 0.057), (42, 0.028), (48, 0.034), (64, 0.017), (70, 0.024), (88, 0.014), (95, 0.053)]
simIndex simValue paperId paperTitle
1 0.97136867 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.
same-paper 2 0.96884149 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.
3 0.93979788 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.
4 0.93842614 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
6 0.92914468 376 acl-2013-Using Lexical Expansion to Learn Inference Rules from Sparse Data
7 0.90249121 71 acl-2013-Bootstrapping Entity Translation on Weakly Comparable Corpora
8 0.86034346 61 acl-2013-Automatic Interpretation of the English Possessive
9 0.79312503 245 acl-2013-Modeling Human Inference Process for Textual Entailment Recognition
10 0.69729167 156 acl-2013-Fast and Adaptive Online Training of Feature-Rich Translation Models
11 0.67529655 358 acl-2013-Transition-based Dependency Parsing with Selectional Branching
12 0.67470574 242 acl-2013-Mining Equivalent Relations from Linked Data
13 0.65262693 27 acl-2013-A Two Level Model for Context Sensitive Inference Rules
14 0.62133861 154 acl-2013-Extracting bilingual terminologies from comparable corpora
15 0.60620064 208 acl-2013-Joint Inference for Heterogeneous Dependency Parsing
16 0.59046179 169 acl-2013-Generating Synthetic Comparable Questions for News Articles
17 0.58858943 202 acl-2013-Is a 204 cm Man Tall or Small ? Acquisition of Numerical Common Sense from the Web
18 0.58603621 387 acl-2013-Why-Question Answering using Intra- and Inter-Sentential Causal Relations
19 0.57300133 132 acl-2013-Easy-First POS Tagging and Dependency Parsing with Beam Search
20 0.57191992 148 acl-2013-Exploring Sentiment in Social Media: Bootstrapping Subjectivity Clues from Multilingual Twitter Streams