acl acl2010 acl2010-106 knowledge-graph by maker-knowledge-mining
Source: pdf
Author: Tingxu Yan ; Tamsin Maxwell ; Dawei Song ; Yuexian Hou ; Peng Zhang
Abstract: p . zhang1 @ rgu .ac .uk Bag-of-words approaches to information retrieval (IR) are effective but assume independence between words. The Hyperspace Analogue to Language (HAL) is a cognitively motivated and validated semantic space model that captures statistical dependencies between words by considering their co-occurrences in a surrounding window of text. HAL has been successfully applied to query expansion in IR, but has several limitations, including high processing cost and use of distributional statistics that do not exploit syntax. In this paper, we pursue two methods for incorporating syntactic-semantic information from textual ‘events’ into HAL. We build the HAL space directly from events to investigate whether processing costs can be reduced through more careful definition of word co-occurrence, and improve the quality of the pseudo-relevance feedback by applying event information as a constraint during HAL construction. Both methods significantly improve performance results in comparison with original HAL, and interpolation of HAL and relevance model expansion outperforms either method alone.
Reference: text
sentIndex sentText sentNum sentScore
1 uk Bag-of-words approaches to information retrieval (IR) are effective but assume independence between words. [sent-14, score-0.073]
2 The Hyperspace Analogue to Language (HAL) is a cognitively motivated and validated semantic space model that captures statistical dependencies between words by considering their co-occurrences in a surrounding window of text. [sent-15, score-0.283]
3 HAL has been successfully applied to query expansion in IR, but has several limitations, including high processing cost and use of distributional statistics that do not exploit syntax. [sent-16, score-0.349]
4 We build the HAL space directly from events to investigate whether processing costs can be reduced through more careful definition of word co-occurrence, and improve the quality of the pseudo-relevance feedback by applying event information as a constraint during HAL construction. [sent-18, score-0.611]
5 Both methods significantly improve performance results in comparison with original HAL, and interpolation of HAL and relevance model expansion outperforms either method alone. [sent-19, score-0.423]
6 1 Introduction Despite its intuitive appeal, the incorporation of linguistic and semantic word dependencies in IR has not been shown to significantly improve over a bigram language modeling approach (Song and Croft, 1999) that encodes word dependencies assumed from mere syntactic adjacency. [sent-20, score-0.169]
7 Improving retrieval performance through application of semantic and syntactic information beyond proximity and co-occurrence features is a difficult task but remains a tantalising prospect. [sent-23, score-0.116]
8 Compared to the MRF model, our approach is unsupervised where MRFs require the training of parameters using relevance judgments that are often unavailable in practical conditions. [sent-26, score-0.072]
9 Independent from IR, Pado and Lapata (2007) proposed a general framework for the construction of a semantic space endowed with syntactic 120 UppsalaP,r Sowce ed ein ,g 1s1 o-f16 th Jeu AlyC 2L0 210 1. [sent-28, score-0.141]
10 This was represented by an undirected graph, where nodes stood for words, dependency edges stood for syntactical relations, and sequences of dependency edges formed paths that were weighted for each target word. [sent-31, score-0.31]
11 Our work is in line with Pado and Lapata (2007) in constructing a semantic space with syntactic information, but builds our space from events, states and attributions as defined linguistically by Bach (1986). [sent-32, score-0.123]
12 We call these simply events, and extract them automatically from predicate-argument structures and a dependency parse. [sent-33, score-0.044]
13 We will use this space to perform query expansion in IR, a task that aims to find additional words related to original query terms, such that an expanded query including these words better expresses the information need. [sent-34, score-0.758]
14 To our knowledge, the notion of events has not been applied to query expansion before. [sent-35, score-0.537]
15 This paper will outline the original HAL algorithm which serves as our baseline, and the event extraction process. [sent-36, score-0.316]
16 We then propose two methods to arm HAL with event information: direct construction of HAL from events (eHAL-1), and treating events as constraints on HAL construction from the corpus (eHAL-2). [sent-37, score-0.755]
17 Evaluation will compare results using original HAL, eHAL1 and eHAL-2 with a widely used unigram language model (LM) for IR and a state of the art query expansion method, namely the Relevance Model (RM) (Lavrenko and Croft, 2001). [sent-38, score-0.451]
18 We also explore whether a complementary effect can be achieved by combining HAL-based dependency modelling with the unigram-based RM. [sent-39, score-0.044]
19 2 HAL Construction Semantic space models aim to capture the mean- ings of words using co-occurrence information in a text corpus. [sent-40, score-0.08]
20 In these semantic spaces, vector-based representations facilitate measurement of similarities between words. [sent-42, score-0.043]
21 Semantic space models have been validated through various studies and demonstrate compatibility with human information processing. [sent-43, score-0.04]
22 Recently, they have also been applied in IR, such as LSA for latent semantic indexing, and HAL for query expansion. [sent-44, score-0.24]
23 For the purpose of this paper, we focus on HAL, which encodes word co-occurrence information explicitly and thus can be applied to query expansion in a straightforward way. [sent-45, score-0.349]
24 HAL is premised on context surrounding a word providing important information about its meaning (Harris, 1968). [sent-46, score-0.035]
25 To be specific, an L-size sliding window moves across a large text corpus word-by-word. [sent-47, score-0.243]
26 Any two words in the same window are treated as co-occurring with each other with a weight that is inversely proportional to their separation distance in the text. [sent-48, score-0.102]
27 w w513462w3451w3452w453w45 w6 Table 1: A HAL space for the text “w1 w2 w3 w4 w5 w6” using a 5-word sliding window (L = 5). [sent-53, score-0.283]
28 HAL has been successfully applied to query expansion and can be incorporated into this task directly (Bai et al. [sent-54, score-0.349]
29 The event extraction algorithm then instantiates the template REL [modREL] Arg0 [modArg0] . [sent-59, score-0.263]
30 ArgN [modArgN], where REL is the predicate relation (or root verb if no predicates are identified), and Arg0. [sent-62, score-0.084]
31 Modifiers (mod) are identified by tracing from predicate and argument heads along the dependency tree. [sent-66, score-0.257]
32 All predicates are associated with at least one event unless both Arg0 and Arg1 are not identified, or the only argument is not a noun. [sent-67, score-0.347]
33 The algorithm checks for modifiers based on POS tag1, tracing up and down the dependency tree, skipping over prepositions, coordinating conjunctions and words indicating apportionment, such as ‘sample (of) ’. [sent-68, score-0.235]
34 For example, given the phrase ‘apples from the store nearby ’ and an argument head apples, the first dependent, store, will be extracted but not nearby, which is the dependent of store. [sent-70, score-0.035]
35 Available paths up and down the dependency tree are followed until all branches are exhausted, given the rules outlined above. [sent-73, score-0.044]
36 Tracing can result in multiple extracted events for one predicate and predicates may also appear as arguments in a different event, or be part of argument phrases. [sent-74, score-0.307]
37 For this reason, events are constrained to cover only detail appearing above subsequent predicates in the tree, which simplifies the event structure. [sent-75, score-0.5]
38 be built in a similar manner to the original HAL. [sent-79, score-0.053]
39 We ignore the parameter of window length (L) and treat every event as a single window of length equal to the number of words in the event. [sent-80, score-0.467]
40 Every pair of words in an event is considered to be cooccurrent with each other. [sent-81, score-0.263]
41 With this scheme, all the events are traversed and the event-based HAL is constructed. [sent-83, score-0.188]
42 The advantage of this method is that it substantially reduces the processing time during HAL construction because only events are involved and there is no need to calculate weights per occurrence. [sent-84, score-0.246]
43 Additional processing time is incurred in semantic role labelling (SRL) during event identification. [sent-85, score-0.306]
44 However, the naive approach to extraction might be simulated with a combination of less costly chunking and dependency parsing, given that the word ordering information available with SRL is not utilised. [sent-86, score-0.044]
45 eHAL-1 combines syntactical and statistical information, but has a potential drawback in that only events are used during construction so some information existing in the co-occurrence patterns of the original text may be lost. [sent-87, score-0.453]
46 The key idea is to decide whether a text segment in a corpus should be used for the HAL construction, based on how much event information it covers. [sent-91, score-0.409]
47 Given a corpus of text and the events extracted from it, the eHAL-2 method runs as follows: 1. [sent-92, score-0.228]
48 Select the events of length M or more and discard the others for efficiency; 2. [sent-93, score-0.188]
49 Set an “inclusion criterion”, which decides if a text segment, defined as a word sequence within an L-size sliding window, contains an event. [sent-94, score-0.141]
50 For example, if 80% of the words in an event are contained in a text segment, it could be considered to “include” the event; 3. [sent-95, score-0.303]
51 Move across the whole corpus word-by-word with an L-size sliding window. [sent-96, score-0.101]
52 For the current L-size text segment, check whether it includes an event according to the “inclusion criterion” (Step 2); 122 5. [sent-98, score-0.303]
53 If an event is included in the current text segment, check the following segments for a consecutive sequence of segments that also include this event. [sent-99, score-0.488]
54 If the current segment includes more than one event, find the longest sequence of related text segments. [sent-100, score-0.146]
55 An illustration is given in Figure 1 in which dark nodes stand for the words in a specific event and an 80% inclusion criterion is used. [sent-101, score-0.353]
56 Text Segment K Segment K+1 Segment K+2 Segment K+3 Figure 1: Consecutive segments for an event 6. [sent-102, score-0.336]
57 Extract the full span of consecutive segments just identified and go to the next available text segment. [sent-103, score-0.189]
58 When the scanning is done, construct HAL using the original HAL method over all extracted sequences. [sent-105, score-0.053]
59 With the guidance ofevent information, the procedure above keeps only those segments of text that include at least one event and discards the rest. [sent-106, score-0.376]
60 It also alleviates the identified drawback of eHAL-1 by using the full text surrounding events. [sent-108, score-0.112]
61 A tradeoff is that not all the events are included by the selected text segments, and thus some syntactical information may be lost. [sent-109, score-0.342]
62 5 Evaluation We empirically test whether our event-based HALs perform better than the original HAL, and standard LM and RM, using three TREC2 collections: AP89 with Topics 1-50 (title field), AP8889 with Topics 101-150 (title field) and WSJ9092 with Topics 201-250 (description field). [sent-111, score-0.053]
63 All the collections are stemmed, and stop words are removed, prior to retrieval using the Lemur Toolkit Version 4. [sent-112, score-0.073]
64 Initial retrieval is identical for all models evaluated: KL-divergence µ 2TREC stands for the Text REtrieval Conference series run by NIST. [sent-114, score-0.073]
65 org/ based LM smoothed using Dirichlet prior with set to 1000 as appropriate for TREC style title queries (Lavrenko, 2004). [sent-120, score-0.035]
66 The top 50 returned documents form the basis for all pseudo-relevance feedback, with other parameters tuned separately for the RM and HAL methods. [sent-121, score-0.035]
67 For each dataset, the number of feedback terms for each method is selected optimally among 20, 40, 60, 804 and the interpolation and smoothing coefficient is set to be optimal in [0,1] with interval 0. [sent-122, score-0.229]
68 For RM, we choose the first relevance model in Lavrenko and Croft (2001) with the document model smoothing parameter optimally set at 0. [sent-124, score-0.108]
69 The number of feedback terms is fixed at 60 (for AP89 and WSJ9092) and 80 (for AP8889), and interpolation between the query and relevance models is set at 0. [sent-126, score-0.423]
70 The HAL-based query expansion methods add the top 80 expansion terms to the query with interpolation coefficient 0. [sent-129, score-0.805]
71 The other HAL-based parameters are set as follows: shortest event length M = 5, for eHAL-2 the “inclusion criterion” is 75% of words in an event, and for HAL and eHAL-2, window size L = 8. [sent-131, score-0.365]
72 Top expansion terms are selected according to the formula: PHAL(tj| ⊕ t) =PtiHHAAL(Lt(jt|i ⊕| ⊕ q) q) where HAL(tj | ⊕q) is the weight of tj in the combined HAL vec|t⊕oqr ⊕q (Bruza ta ondf Song, 2002) obifn original query terms. [sent-132, score-0.448]
73 It can be observed that all the three HAL-based query expansion methods improve performance over the LM and both eHALs achieve better performance than original HAL, indicating that the incorporation of event information is beneficial. [sent-136, score-0.665]
74 The results are still short of those achieved 4For RM, feedback terms were also tested on larger numbers up to 1000 but only comparable result was observed. [sent-138, score-0.086]
75 5In Table 2, brackets show percent improvement of eHALs / RM over HAL / eHAL-2 respectively and * and # indicate the corresponding statistical significance. [sent-139, score-0.032]
76 123 MethodAP89AP8889WSJ9092 expansion using different HALs with RM, but the gap is significantly reduced by incorporating event information here, suggesting this is a promising line of work. [sent-140, score-0.488]
77 , 2005), the Information Flow method built upon the original HAL largely outperformed RM. [sent-142, score-0.053]
78 As is known, RM is a pure unigram model while HAL methods are dependency-based. [sent-144, score-0.049]
79 Apply RM to the feedback documents (original RM), the events extracted from these documents (eRM-1), and the text segments around each event (eRM-2), where the three sources are the same as used to produce HAL, eHAL-1 and eHAL-2 respectively; 2. [sent-147, score-0.72]
80 Interpolate the expanded query model by RM with the ones generated by each HAL, represented by HAL+RM, eHAL-1+RM and eHAL-2+RM. [sent-148, score-0.158]
81 The interpolation coefficient is again selected to achieve the optimal MAP. [sent-149, score-0.107]
82 The MAP comparison between the original RM and these new models are demonstrated in Table 36. [sent-150, score-0.053]
83 From the first three lines (Scheme 1), we can observe that in most cases the performance generally deteriorates when RM is directly run over the events and the text segments. [sent-151, score-0.228]
84 The event information is more effective to express the information about the term dependencies while the unigram RM ignores this information and only takes 6For rows in Table 3, brackets show percent difference from original RM. [sent-152, score-0.46]
85 MethodAP89AP8889WSJ9092 expansion using the combination of RM and term dependencies the occurrence frequencies of individual words into account, which is not well-captured by the events. [sent-153, score-0.254]
86 The three methods outperform the original RM in most cases, but the improvement is not significant and it is also observed that there is little difference shown between RM with HAL and eHALs. [sent-155, score-0.053]
87 The phenomenon implies more effective methods may be invented to complement the unigram models with the syntactical and statistical dependency information. [sent-156, score-0.207]
88 6 Conclusions The application of original HAL to query expansion attempted to incorporate statistical word association information, but did not take into account the syntactical dependencies and had a high processing cost. [sent-157, score-0.579]
89 In addition, interpolation of HAL and RM expansion improved results over those achieved by either method alone. [sent-160, score-0.298]
wordName wordTfidf (topN-words)
[('hal', 0.557), ('rm', 0.325), ('event', 0.263), ('expansion', 0.191), ('events', 0.188), ('query', 0.158), ('syntactical', 0.114), ('bruza', 0.107), ('tianjin', 0.107), ('interpolation', 0.107), ('segment', 0.106), ('song', 0.104), ('croft', 0.104), ('window', 0.102), ('sliding', 0.101), ('ir', 0.091), ('lavrenko', 0.087), ('feedback', 0.086), ('bai', 0.086), ('sigir', 0.074), ('retrieval', 0.073), ('segments', 0.073), ('relevance', 0.072), ('weapons', 0.07), ('tracing', 0.07), ('metzler', 0.067), ('modifiers', 0.067), ('dependencies', 0.063), ('hyperspace', 0.06), ('landauer', 0.059), ('construction', 0.058), ('pado', 0.055), ('baghdad', 0.054), ('ehal', 0.054), ('ehals', 0.054), ('hals', 0.054), ('kelledy', 0.054), ('rgu', 0.054), ('skipping', 0.054), ('smeaton', 0.054), ('stood', 0.054), ('syntacticsemantic', 0.054), ('original', 0.053), ('analogue', 0.052), ('lm', 0.051), ('lapata', 0.049), ('predicates', 0.049), ('unigram', 0.049), ('ny', 0.049), ('biological', 0.047), ('donnell', 0.047), ('harshman', 0.047), ('laham', 0.047), ('mrf', 0.047), ('tj', 0.046), ('acm', 0.046), ('criterion', 0.045), ('inclusion', 0.045), ('dependency', 0.044), ('massive', 0.043), ('sleator', 0.043), ('temperley', 0.043), ('apples', 0.043), ('foltz', 0.043), ('semantic', 0.043), ('flow', 0.04), ('nugues', 0.04), ('deerwester', 0.04), ('furnas', 0.04), ('bach', 0.04), ('text', 0.04), ('space', 0.04), ('gao', 0.04), ('consecutive', 0.039), ('latent', 0.039), ('facilities', 0.038), ('burgess', 0.038), ('lund', 0.038), ('united', 0.037), ('indexing', 0.037), ('identified', 0.037), ('optimally', 0.036), ('gordon', 0.036), ('cao', 0.036), ('nie', 0.036), ('york', 0.036), ('heads', 0.036), ('argument', 0.035), ('documents', 0.035), ('predicate', 0.035), ('harris', 0.035), ('field', 0.035), ('title', 0.035), ('surrounding', 0.035), ('reduced', 0.034), ('producing', 0.034), ('johansson', 0.034), ('aberdeen', 0.034), ('continue', 0.033), ('percent', 0.032)]
simIndex simValue paperId paperTitle
same-paper 1 1.0000005 106 acl-2010-Event-Based Hyperspace Analogue to Language for Query Expansion
Author: Tingxu Yan ; Tamsin Maxwell ; Dawei Song ; Yuexian Hou ; Peng Zhang
Abstract: p . zhang1 @ rgu .ac .uk Bag-of-words approaches to information retrieval (IR) are effective but assume independence between words. The Hyperspace Analogue to Language (HAL) is a cognitively motivated and validated semantic space model that captures statistical dependencies between words by considering their co-occurrences in a surrounding window of text. HAL has been successfully applied to query expansion in IR, but has several limitations, including high processing cost and use of distributional statistics that do not exploit syntax. In this paper, we pursue two methods for incorporating syntactic-semantic information from textual ‘events’ into HAL. We build the HAL space directly from events to investigate whether processing costs can be reduced through more careful definition of word co-occurrence, and improve the quality of the pseudo-relevance feedback by applying event information as a constraint during HAL construction. Both methods significantly improve performance results in comparison with original HAL, and interpolation of HAL and relevance model expansion outperforms either method alone.
2 0.19984902 247 acl-2010-Unsupervised Event Coreference Resolution with Rich Linguistic Features
Author: Cosmin Bejan ; Sanda Harabagiu
Abstract: This paper examines how a new class of nonparametric Bayesian models can be effectively applied to an open-domain event coreference task. Designed with the purpose of clustering complex linguistic objects, these models consider a potentially infinite number of features and categorical outcomes. The evaluation performed for solving both within- and cross-document event coreference shows significant improvements of the models when compared against two baselines for this task.
3 0.12667088 165 acl-2010-Learning Script Knowledge with Web Experiments
Author: Michaela Regneri ; Alexander Koller ; Manfred Pinkal
Abstract: We describe a novel approach to unsupervised learning of the events that make up a script, along with constraints on their temporal ordering. We collect naturallanguage descriptions of script-specific event sequences from volunteers over the Internet. Then we compute a graph representation of the script’s temporal structure using a multiple sequence alignment algorithm. The evaluation of our system shows that we outperform two informed baselines.
4 0.12563699 245 acl-2010-Understanding the Semantic Structure of Noun Phrase Queries
Author: Xiao Li
Abstract: Determining the semantic intent of web queries not only involves identifying their semantic class, which is a primary focus of previous works, but also understanding their semantic structure. In this work, we formally define the semantic structure of noun phrase queries as comprised of intent heads and intent modifiers. We present methods that automatically identify these constituents as well as their semantic roles based on Markov and semi-Markov conditional random fields. We show that the use of semantic features and syntactic features significantly contribute to improving the understanding performance.
5 0.1103209 177 acl-2010-Multilingual Pseudo-Relevance Feedback: Performance Study of Assisting Languages
Author: Manoj Kumar Chinnakotla ; Karthik Raman ; Pushpak Bhattacharyya
Abstract: In a previous work of ours Chinnakotla et al. (2010) we introduced a novel framework for Pseudo-Relevance Feedback (PRF) called MultiPRF. Given a query in one language called Source, we used English as the Assisting Language to improve the performance of PRF for the source language. MulitiPRF showed remarkable improvement over plain Model Based Feedback (MBF) uniformly for 4 languages, viz., French, German, Hungarian and Finnish with English as the assisting language. This fact inspired us to study the effect of any source-assistant pair on MultiPRF performance from out of a set of languages with widely different characteristics, viz., Dutch, English, Finnish, French, German and Spanish. Carrying this further, we looked into the effect of using two assisting languages together on PRF. The present paper is a report of these investigations, their results and conclusions drawn therefrom. While performance improvement on MultiPRF is observed whatever the assisting language and whatever the source, observations are mixed when two assisting languages are used simultaneously. Interestingly, the performance improvement is more pronounced when the source and assisting languages are closely related, e.g., French and Spanish.
6 0.098000154 232 acl-2010-The S-Space Package: An Open Source Package for Word Space Models
7 0.089939684 246 acl-2010-Unsupervised Discourse Segmentation of Documents with Inherently Parallel Structure
8 0.084054694 94 acl-2010-Edit Tree Distance Alignments for Semantic Role Labelling
9 0.081379652 153 acl-2010-Joint Syntactic and Semantic Parsing of Chinese
10 0.080851607 123 acl-2010-Generating Focused Topic-Specific Sentiment Lexicons
11 0.080063105 122 acl-2010-Generating Fine-Grained Reviews of Songs from Album Reviews
12 0.078600638 164 acl-2010-Learning Phrase-Based Spelling Error Models from Clickthrough Data
13 0.07595177 238 acl-2010-Towards Open-Domain Semantic Role Labeling
14 0.075057238 49 acl-2010-Beyond NomBank: A Study of Implicit Arguments for Nominal Predicates
15 0.072477728 184 acl-2010-Open-Domain Semantic Role Labeling by Modeling Word Spans
16 0.070600457 17 acl-2010-A Structured Model for Joint Learning of Argument Roles and Predicate Senses
17 0.067089126 22 acl-2010-A Unified Graph Model for Sentence-Based Opinion Retrieval
18 0.06475386 190 acl-2010-P10-5005 k2opt.pdf
19 0.06412942 27 acl-2010-An Active Learning Approach to Finding Related Terms
20 0.061845832 155 acl-2010-Kernel Based Discourse Relation Recognition with Temporal Ordering Information
topicId topicWeight
[(0, -0.189), (1, 0.084), (2, 0.02), (3, 0.033), (4, 0.01), (5, 0.011), (6, -0.031), (7, -0.034), (8, 0.023), (9, -0.036), (10, -0.056), (11, 0.002), (12, 0.016), (13, -0.069), (14, 0.038), (15, 0.079), (16, -0.069), (17, 0.025), (18, -0.017), (19, -0.074), (20, 0.124), (21, -0.179), (22, 0.042), (23, 0.029), (24, 0.203), (25, -0.01), (26, 0.118), (27, -0.02), (28, 0.088), (29, -0.149), (30, 0.182), (31, 0.067), (32, -0.073), (33, -0.115), (34, 0.077), (35, 0.037), (36, 0.068), (37, -0.045), (38, -0.001), (39, -0.021), (40, 0.039), (41, 0.022), (42, 0.035), (43, -0.124), (44, 0.089), (45, 0.088), (46, 0.039), (47, -0.092), (48, 0.03), (49, 0.115)]
simIndex simValue paperId paperTitle
same-paper 1 0.9594897 106 acl-2010-Event-Based Hyperspace Analogue to Language for Query Expansion
Author: Tingxu Yan ; Tamsin Maxwell ; Dawei Song ; Yuexian Hou ; Peng Zhang
Abstract: p . zhang1 @ rgu .ac .uk Bag-of-words approaches to information retrieval (IR) are effective but assume independence between words. The Hyperspace Analogue to Language (HAL) is a cognitively motivated and validated semantic space model that captures statistical dependencies between words by considering their co-occurrences in a surrounding window of text. HAL has been successfully applied to query expansion in IR, but has several limitations, including high processing cost and use of distributional statistics that do not exploit syntax. In this paper, we pursue two methods for incorporating syntactic-semantic information from textual ‘events’ into HAL. We build the HAL space directly from events to investigate whether processing costs can be reduced through more careful definition of word co-occurrence, and improve the quality of the pseudo-relevance feedback by applying event information as a constraint during HAL construction. Both methods significantly improve performance results in comparison with original HAL, and interpolation of HAL and relevance model expansion outperforms either method alone.
2 0.63974875 165 acl-2010-Learning Script Knowledge with Web Experiments
Author: Michaela Regneri ; Alexander Koller ; Manfred Pinkal
Abstract: We describe a novel approach to unsupervised learning of the events that make up a script, along with constraints on their temporal ordering. We collect naturallanguage descriptions of script-specific event sequences from volunteers over the Internet. Then we compute a graph representation of the script’s temporal structure using a multiple sequence alignment algorithm. The evaluation of our system shows that we outperform two informed baselines.
3 0.62504733 177 acl-2010-Multilingual Pseudo-Relevance Feedback: Performance Study of Assisting Languages
Author: Manoj Kumar Chinnakotla ; Karthik Raman ; Pushpak Bhattacharyya
Abstract: In a previous work of ours Chinnakotla et al. (2010) we introduced a novel framework for Pseudo-Relevance Feedback (PRF) called MultiPRF. Given a query in one language called Source, we used English as the Assisting Language to improve the performance of PRF for the source language. MulitiPRF showed remarkable improvement over plain Model Based Feedback (MBF) uniformly for 4 languages, viz., French, German, Hungarian and Finnish with English as the assisting language. This fact inspired us to study the effect of any source-assistant pair on MultiPRF performance from out of a set of languages with widely different characteristics, viz., Dutch, English, Finnish, French, German and Spanish. Carrying this further, we looked into the effect of using two assisting languages together on PRF. The present paper is a report of these investigations, their results and conclusions drawn therefrom. While performance improvement on MultiPRF is observed whatever the assisting language and whatever the source, observations are mixed when two assisting languages are used simultaneously. Interestingly, the performance improvement is more pronounced when the source and assisting languages are closely related, e.g., French and Spanish.
4 0.61604804 247 acl-2010-Unsupervised Event Coreference Resolution with Rich Linguistic Features
Author: Cosmin Bejan ; Sanda Harabagiu
Abstract: This paper examines how a new class of nonparametric Bayesian models can be effectively applied to an open-domain event coreference task. Designed with the purpose of clustering complex linguistic objects, these models consider a potentially infinite number of features and categorical outcomes. The evaluation performed for solving both within- and cross-document event coreference shows significant improvements of the models when compared against two baselines for this task.
5 0.5959574 245 acl-2010-Understanding the Semantic Structure of Noun Phrase Queries
Author: Xiao Li
Abstract: Determining the semantic intent of web queries not only involves identifying their semantic class, which is a primary focus of previous works, but also understanding their semantic structure. In this work, we formally define the semantic structure of noun phrase queries as comprised of intent heads and intent modifiers. We present methods that automatically identify these constituents as well as their semantic roles based on Markov and semi-Markov conditional random fields. We show that the use of semantic features and syntactic features significantly contribute to improving the understanding performance.
6 0.58212239 164 acl-2010-Learning Phrase-Based Spelling Error Models from Clickthrough Data
7 0.52697492 225 acl-2010-Temporal Information Processing of a New Language: Fast Porting with Minimal Resources
8 0.44535586 196 acl-2010-Plot Induction and Evolutionary Search for Story Generation
9 0.38452566 28 acl-2010-An Entity-Level Approach to Information Extraction
10 0.38005239 215 acl-2010-Speech-Driven Access to the Deep Web on Mobile Devices
11 0.37324834 55 acl-2010-Bootstrapping Semantic Analyzers from Non-Contradictory Texts
12 0.36977404 101 acl-2010-Entity-Based Local Coherence Modelling Using Topological Fields
13 0.36838302 232 acl-2010-The S-Space Package: An Open Source Package for Word Space Models
14 0.36494577 246 acl-2010-Unsupervised Discourse Segmentation of Documents with Inherently Parallel Structure
15 0.36148909 238 acl-2010-Towards Open-Domain Semantic Role Labeling
16 0.35946181 94 acl-2010-Edit Tree Distance Alignments for Semantic Role Labelling
17 0.35333681 49 acl-2010-Beyond NomBank: A Study of Implicit Arguments for Nominal Predicates
18 0.35296389 198 acl-2010-Predicate Argument Structure Analysis Using Transformation Based Learning
20 0.3428708 17 acl-2010-A Structured Model for Joint Learning of Argument Roles and Predicate Senses
topicId topicWeight
[(25, 0.065), (42, 0.017), (59, 0.109), (71, 0.011), (72, 0.017), (73, 0.046), (78, 0.039), (80, 0.015), (83, 0.081), (84, 0.045), (98, 0.17), (99, 0.279)]
simIndex simValue paperId paperTitle
same-paper 1 0.80579954 106 acl-2010-Event-Based Hyperspace Analogue to Language for Query Expansion
Author: Tingxu Yan ; Tamsin Maxwell ; Dawei Song ; Yuexian Hou ; Peng Zhang
Abstract: p . zhang1 @ rgu .ac .uk Bag-of-words approaches to information retrieval (IR) are effective but assume independence between words. The Hyperspace Analogue to Language (HAL) is a cognitively motivated and validated semantic space model that captures statistical dependencies between words by considering their co-occurrences in a surrounding window of text. HAL has been successfully applied to query expansion in IR, but has several limitations, including high processing cost and use of distributional statistics that do not exploit syntax. In this paper, we pursue two methods for incorporating syntactic-semantic information from textual ‘events’ into HAL. We build the HAL space directly from events to investigate whether processing costs can be reduced through more careful definition of word co-occurrence, and improve the quality of the pseudo-relevance feedback by applying event information as a constraint during HAL construction. Both methods significantly improve performance results in comparison with original HAL, and interpolation of HAL and relevance model expansion outperforms either method alone.
Author: Decong Li ; Sujian Li ; Wenjie Li ; Wei Wang ; Weiguang Qu
Abstract: It is a fundamental and important task to extract key phrases from documents. Generally, phrases in a document are not independent in delivering the content of the document. In order to capture and make better use of their relationships in key phrase extraction, we suggest exploring the Wikipedia knowledge to model a document as a semantic network, where both n-ary and binary relationships among phrases are formulated. Based on a commonly accepted assumption that the title of a document is always elaborated to reflect the content of a document and consequently key phrases tend to have close semantics to the title, we propose a novel semi-supervised key phrase extraction approach in this paper by computing the phrase importance in the semantic network, through which the influence of title phrases is propagated to the other phrases iteratively. Experimental results demonstrate the remarkable performance of this approach. 1
3 0.74416935 83 acl-2010-Dependency Parsing and Projection Based on Word-Pair Classification
Author: Wenbin Jiang ; Qun Liu
Abstract: In this paper we describe an intuitionistic method for dependency parsing, where a classifier is used to determine whether a pair of words forms a dependency edge. And we also propose an effective strategy for dependency projection, where the dependency relationships of the word pairs in the source language are projected to the word pairs of the target language, leading to a set of classification instances rather than a complete tree. Experiments show that, the classifier trained on the projected classification instances significantly outperforms previous projected dependency parsers. More importantly, when this clas- , sifier is integrated into a maximum spanning tree (MST) dependency parser, obvious improvement is obtained over the MST baseline.
4 0.6318261 261 acl-2010-Wikipedia as Sense Inventory to Improve Diversity in Web Search Results
Author: Celina Santamaria ; Julio Gonzalo ; Javier Artiles
Abstract: Is it possible to use sense inventories to improve Web search results diversity for one word queries? To answer this question, we focus on two broad-coverage lexical resources of a different nature: WordNet, as a de-facto standard used in Word Sense Disambiguation experiments; and Wikipedia, as a large coverage, updated encyclopaedic resource which may have a better coverage of relevant senses in Web pages. Our results indicate that (i) Wikipedia has a much better coverage of search results, (ii) the distribution of senses in search results can be estimated using the internal graph structure of the Wikipedia and the relative number of visits received by each sense in Wikipedia, and (iii) associating Web pages to Wikipedia senses with simple and efficient algorithms, we can produce modified rankings that cover 70% more Wikipedia senses than the original search engine rankings. 1 Motivation The application of Word Sense Disambiguation (WSD) to Information Retrieval (IR) has been subject of a significant research effort in the recent past. The essential idea is that, by indexing and matching word senses (or even meanings) , the retrieval process could better handle polysemy and synonymy problems (Sanderson, 2000). In practice, however, there are two main difficulties: (i) for long queries, IR models implicitly perform disambiguation, and thus there is little room for improvement. This is the case with most standard IR benchmarks, such as TREC (trec.nist.gov) or CLEF (www.clef-campaign.org) ad-hoc collections; (ii) for very short queries, disambiguation j ul io @ l i uned . e s j avart s . @bec . uned . e s may not be possible or even desirable. This is often the case with one word and even two word queries in Web search engines. In Web search, there are at least three ways of coping with ambiguity: • • • Promoting diversity in the search results (Clarke negt al., 2008): given th seea query s”uolatssis”, the search engine may try to include representatives for different senses of the word (such as the Oasis band, the Organization for the Advancement of Structured Information Standards, the online fashion store, etc.) among the top results. Search engines are supposed to handle diversity as one of the multiple factors that influence the ranking. Presenting the results as a set of (labelled) cPlruessteenrtsi nragth tehre eth reansu as a a rsan ake sde lti ostf (Carpineto et al., 2009). Complementing search results with search suggestions (e.g. e”oaracshis band”, ”woitahsis s fashion store”) that serve to refine the query in the intended way (Anick, 2003). All of them rely on the ability of the search engine to cluster search results, detecting topic similarities. In all of them, disambiguation is implicit, a side effect of the process but not its explicit target. Clustering may detect that documents about the Oasis band and the Oasis fashion store deal with unrelated topics, but it may as well detect a group of documents discussing why one of the Oasis band members is leaving the band, and another group of documents about Oasis band lyrics; both are different aspects of the broad topic Oasis band. A perfect hierarchical clustering should distinguish between the different Oasis senses at a first level, and then discover different topics within each of the senses. Is it possible to use sense inventories to improve search results for one word queries? To answer 1357 Proce dingUsp opfs thaela 4, 8Stwhe Adnen u,a 1l1- M16e Jtiunlgy o 2f0 t1h0e. A ?c s 2o0c1ia0ti Aosnso focria Ctio nm fpourta Ctoiomnpault Laitniognuaislt Licisn,g puaigsetisc 1s357–136 , this question, we will focus on two broad-coverage lexical resources of a different nature: WordNet (Miller et al., 1990), as a de-facto standard used in Word Sense Disambiguation experiments and many other Natural Language Processing research fields; and Wikipedia (www.wikipedia.org), as a large coverage and updated encyclopedic resource which may have a better coverage of relevant senses in Web pages. Our hypothesis is that, under appropriate conditions, any of the above mechanisms (clustering, search suggestions, diversity) might benefit from an explicit disambiguation (classification of pages in the top search results) using a wide-coverage sense inventory. Our research is focused on four relevant aspects of the problem: 1. Coverage: Are Wikipedia/Wordnet senses representative of search results? Otherwise, trying to make a disambiguation in terms of a fixed sense inventory would be meaningless. 2. If the answer to (1) is positive, the reverse question is also interesting: can we estimate search results diversity using our sense inven- tories? 3. Sense frequencies: knowing sense frequencies in (search results) Web pages is crucial to have a usable sense inventory. Is it possible to estimate Web sense frequencies from currently available information? 4. Classification: The association of Web pages to word senses must be done with some unsupervised algorithm, because it is not possible to hand-tag training material for every possible query word. Can this classification be done accurately? Can it be effective to promote diversity in search results? In order to provide an initial answer to these questions, we have built a corpus consisting of 40 nouns and 100 Google search results per noun, manually annotated with the most appropriate Wordnet and Wikipedia senses. Section 2 describes how this corpus has been created, and in Section 3 we discuss WordNet and Wikipedia coverage of search results according to our testbed. As this initial results clearly discard Wordnet as a sense inventory for the task, the rest of the paper mainly focuses on Wikipedia. In Section 4 we estimate search results diversity from our testbed, finding that the use of Wikipedia could substantially improve diversity in the top results. In Section 5 we use the Wikipedia internal link structure and the number of visits per page to estimate relative frequencies for Wikipedia senses, obtaining an estimation which is highly correlated with actual data in our testbed. Finally, in Section 6 we discuss a few strategies to classify Web pages into word senses, and apply the best classifier to enhance diversity in search results. The paper concludes with a discussion of related work (Section 7) and an overall discussion of our results in Section 8. 2 Test Set 2.1 Set of Words The most crucial step in building our test set is choosing the set of words to be considered. We are looking for words which are susceptible to form a one-word query for a Web search engine, and therefore we should focus on nouns which are used to denote one or more named entities. At the same time we want to have some degree of comparability with previous research on Word Sense Disambiguation, which points to noun sets used in Senseval/SemEval evaluation campaigns1 . Our budget for corpus annotation was enough for two persons-month, which limited us to handle 40 nouns (usually enough to establish statistically significant differences between WSD algorithms, although obviously limited to reach solid figures about the general behaviour of words in the Web). With these arguments in mind, we decided to choose: (i) 15 nouns from the Senseval-3 lexical sample dataset, which have been previously employed by (Mihalcea, 2007) in a related experiment (see Section 7); (ii) 25 additional words which satisfy two conditions: they are all ambiguous, and they are all names for music bands in one of their senses (not necessarily the most salient). The Senseval set is: {argument, arm, atmosphere, bank, degree, difference, disc, irmm-, age, paper, party, performance, plan, shelter, sort, source}. The bands set is {amazon, apple, camel, cell, columbia, cream, foreigner, fox, genesis, jaguar, oasis, pioneer, police, puma, rainbow, shell, skin, sun, tesla, thunder, total, traffic, trapeze, triumph, yes}. Fpoerz e,a trchiu noun, we looked up all its possible senses in WordNet 3.0 and in Wikipedia (using 1http://senseval.org 1358 Table 1: Coverage of Search Results: Wikipedia vs. WordNet Wikiped#ia documents # senses WordNe#t documents Senseval setava2il4a2b/1le0/u0sedassign8e7d7 to (5 s9o%me) senseavai9la2b/5le2/usedassigne6d96 to (4 s6o%m)e sense # senses BaTnodtsa lset868420//21774421323558 ((5546%%))17780/3/9911529995 (2 (342%%)) Wikipedia disambiguation pages). Wikipedia has an average of 22 senses per noun (25.2 in the Bands set and 16. 1in the Senseval set), and Wordnet a much smaller figure, 4.5 (3. 12 for the Bands set and 6.13 for the Senseval set). For a conventional dictionary, a higher ambiguity might indicate an excess of granularity; for an encyclopaedic resource such as Wikipedia, however, it is just an indication of larger coverage. Wikipedia en- tries for camel which are not in WordNet, for instance, include the Apache Camel routing and mediation engine, the British rock band, the brand of cigarettes, the river in Cornwall, and the World World War I fighter biplane. 2.2 Set of Documents We retrieved the 150 first ranked documents for each noun, by submitting the nouns as queries to a Web search engine (Google). Then, for each document, we stored both the snippet (small description of the contents of retrieved document) and the whole HTML document. This collection of documents contain an implicit new inventory of senses, based on Web search, as documents retrieved by a noun query are associated with some sense of the noun. Given that every document in the top Web search results is supposed to be highly relevant for the query word, we assume a ”one sense per document” scenario, although we allow annotators to assign more than one sense per document. In general this assumption turned out to be correct except in a few exceptional cases (such as Wikipedia disambiguation pages): only nine docu- ments received more than one WordNet sense, and 44 (1. 1% of all annotated pages) received more than one Wikipedia sense. 2.3 Manual Annotation We implemented an annotation interface which stored all documents and a short description for every Wordnet and Wikipedia sense. The annotators had to decide, for every document, whether there was one or more appropriate senses in each of the dictionaries. They were instructed to provide annotations for 100 documents per name; if an URL in the list was corrupt or not available, it had to be discarded. We provided 150 documents per name to ensure that the figure of 100 usable documents per name could be reached without problems. Each judge provided annotations for the 4,000 documents in the final data set. In a second round, they met and discussed their independent annotations together, reaching a consensus judgement for every document. 3 Coverage of Web Search Results: Wikipedia vs Wordnet Table 1 shows how Wikipedia and Wordnet cover the senses in search results. We report each noun subset separately (Senseval and bands subsets) as well as aggregated figures. The most relevant fact is that, unsurprisingly, Wikipedia senses cover much more search results (56%) than Wordnet (32%). If we focus on the top ten results, in the bands subset (which should be more representative of plausible web queries) Wikipedia covers 68% of the top ten documents. This is an indication that it can indeed be useful for promoting diversity or help clustering search results: even if 32% of the top ten documents are not covered by Wikipedia, it is still a representative source of senses in the top search results. We have manually examined all documents in the top ten results that are not covered by Wikipedia: a majority of the missing senses consists of names of (generally not well-known) companies (45%) and products or services (26%); the other frequent type (12%) of non annotated doc- ument is disambiguation pages (from Wikipedia and also from other dictionaries). It is also interesting to examine the degree of overlap between Wikipedia and Wordnet senses. Being two different types of lexical resource, they might have some degree of complementarity. Table 2 shows, however, that this is not the case: most of the (annotated) documents either fit Wikipedia senses (26%) or both Wikipedia and Wordnet (29%), and just 3% fit Wordnet only. 1359 Table 2: Overlap between Wikipedia and Wordnet in Search Results # documents annotated with Senseval setWikipe60di7a ( &40 W%o)rdnetWi2k7ip0e (d1i8a% on)lyWo8r9d (n6e%t o)nly534no (3n6e%) BaTnodtsa slet1517729 ( (2239%%))1708566 (3 (216%%))12176 ( (13%%))11614195 ( (4415%%)) Therefore, Wikipedia seems to extend the coverage of Wordnet rather than providing complementary sense information. If we wanted to extend the coverage of Wikipedia, the best strategy seems to be to consider lists ofcompanies, products and services, rather than complementing Wikipedia with additional sense inventories. 4 Diversity in Google Search Results Once we know that Wikipedia senses are a representative subset of actual Web senses (covering more than half of the documents retrieved by the search engine), we can test how well search results respect diversity in terms of this subset of senses. Table 3 displays the number of different senses found at different depths in the search results rank, and the average proportion of total senses that they represent. These results suggest that diversity is not a major priority for ranking results: the top ten results only cover, in average, 3 Wikipedia senses (while the average number of senses listed in Wikipedia is 22). When considering the first 100 documents, this number grows up to 6.85 senses per noun. Another relevant figure is the frequency of the most frequent sense for each word: in average, 63% of the pages in search results belong to the most frequent sense of the query word. This is roughly comparable with most frequent sense figures in standard annotated corpora such as Semcor (Miller et al., 1993) and the Senseval/Semeval data sets, which suggests that diversity may not play a major role in the current Google ranking algorithm. Of course this result must be taken with care, because variability between words is high and unpredictable, and we are using only 40 nouns for our experiment. But what we have is a positive indication that Wikipedia could be used to improve diversity or cluster search results: potentially the first top ten results could cover 6.15 different senses in average (see Section 6.5), which would be a substantial growth. 5 Sense Frequency Estimators for Wikipedia Wikipedia disambiguation pages contain no systematic information about the relative importance of senses for a given word. Such information, however, is crucial in a lexicon, because sense distributions tend to be skewed, and knowing them can help disambiguation algorithms. We have attempted to use two estimators of expected sense distribution: • • Internal relevance of a word sense, measured as incoming alinnckes o ffo ar wthoer U seRnLs o, fm a given sense in Wikipedia. External relevance of a word sense, measured as ttheren naulm rebleevr aonfc vei osifts a f woro trhde s eUnRsLe, mofe a given sense (as reported in http://stats.grok.se). The number of internal incoming links is expected to be relatively stable for Wikipedia articles. As for the number of visits, we performed a comparison of the number of visits received by the bands noun subset in May, June and July 2009, finding a stable-enough scenario with one notorious exception: the number of visits to the noun Tesla raised dramatically in July, because July 10 was the anniversary of the birth of Nicola Tesla, and a special Google logo directed users to the Wikipedia page for the scientist. We have measured correlation between the relative frequencies derived from these two indicators and the actual relative frequencies in our testbed. Therefore, for each noun w and for each sense wi, we consider three values: (i) proportion of documents retrieved for w which are manually assigned to each sense wi; (ii) inlinks(wi) : relative amount of incoming links to each sense wi; and (iii) visits(wi) : relative number of visits to the URL for each sense wi. We have measured the correlation between these three values using a linear regression correlation coefficient, which gives a correlation value of .54 for the number of visits and of .71 for the number of incoming links. Both estimators seem 1360 Table 3: Diversity in Search Results according to Wikipedia F ir s t 12570 docsBave6n425.rd9854a6 s8get#snSe 65sien43. v68a3s27elarcthesTu6543l.o t5083as5lBvaen.r3d2a73s81gectovrSaegnso. 4f32v615aWlsiketpdaTs.3oe249tn01asle to be positively correlated with real relative frequencies in our testbed, with a strong preference for the number of links. We have experimented with weighted combinations of both indicators, using weights of the form (k, 1 k) , k ∈ {0, 0.1, 0.2 . . . 1}, reaching a maxi(mk,a1l c−okrre),lkati ∈on { 0of, .07.13, f0o.r2 t.h.e. following weights: − freq(wi) = 0.9∗inlinks(wi) +0. 1∗visits(wi) (1) This weighted estimator provides a slight advantage over the use of incoming links only (.73 vs .71). Overall, we have an estimator which has a strong correlation with the distribution of senses in our testbed. In the next section we will test its utility for disambiguation purposes. 6 Association of Wikipedia Senses to Web Pages We want to test whether the information provided by Wikipedia can be used to classify search results accurately. Note that we do not want to consider approaches that involve a manual creation of training material, because they can’t be used in practice. Given a Web page p returned by the search engine for the query w, and the set of senses w1 . . . wn listed in Wikipedia, the task is to assign the best candidate sense to p. We consider two different techniques: • A basic Information Retrieval approach, wAhe breas tche I dfoocrmumateionnts Ranetdr tvhael Wikipedia pages are represented using a Vector Space Model (VSM) and compared with a standard cosine measure. This is a basic approach which, if successful, can be used efficiently to classify search results. An approach based on a state-of-the-art supervised oWacShD b system, extracting training examples automatically from Wikipedia content. We also compute two baselines: • • • A random assignment of senses (precision is computed as itghnem ienvnter osfe oenfs tehse ( pnruemcibsieorn o isf senses, for every test case). A most frequent sense heuristic which uses our eosstitm fraetiqoune otf s sense frequencies acnhd u assigns the same sense (the most frequent) to all documents. Both are naive baselines, but it must be noted that the most frequent sense heuristic is usually hard to beat for unsupervised WSD algorithms in most standard data sets. We now describe each of the two main approaches in detail. 6.1 VSM Approach For each word sense, we represent its Wikipedia page in a (unigram) vector space model, assigning standard tf*idf weights to the words in the document. idf weights are computed in two different ways: 1. Experiment VSM computes inverse document frequencies in the collection of retrieved documents (for the word being considered). 2. Experiment VSM-GT uses the statistics provided by the Google Terabyte collection (Brants and Franz, 2006), i.e. it replaces the collection of documents with statistics from a representative snapshot of the Web. 3. Experiment VSM-mixed combines statistics from the collection and from the Google Terabyte collection, following (Chen et al., 2009). The document p is represented in the same vector space as the Wikipedia senses, and it is compared with each of the candidate senses wi via the cosine similarity metric (we have experimented 1361 with other similarity metrics such as χ2, but differences are irrelevant). The sense with the highest similarity to p is assigned to the document. In case of ties (which are rare), we pick the first sense in the Wikipedia disambiguation page (which in practice is like a random decision, because senses in disambiguation pages do not seem to be ordered according to any clear criteria). We have also tested a variant of this approach which uses the estimation of sense frequencies presented above: once the similarities are computed, we consider those cases where two or more senses have a similar score (in particular, all senses with a score greater or equal than 80% of the highest score). In that cases, instead of using the small similarity differences to select a sense, we pick up the one which has the largest frequency according to our estimator. We have applied this strategy to the best performing system, VSM-GT, resulting in experiment VSM-GT+freq. 6.2 WSD Approach We have used TiMBL (Daelemans et al., 2001), a state-of-the-art supervised WSD system which uses Memory-Based Learning. The key, in this case, is how to extract learning examples from the Wikipedia automatically. For each word sense, we basically have three sources of examples: (i) occurrences of the word in the Wikipedia page for the word sense; (ii) occurrences of the word in Wikipedia pages pointing to the page for the word sense; (iii) occurrences of the word in external pages linked in the Wikipedia page for the word sense. After an initial manual inspection, we decided to discard external pages for being too noisy, and we focused on the first two options. We tried three alternatives: • • • TiMBL-core uses only the examples found Tini MtheB page rfoer u tshees sense being atrmaipneleds. TiMBL-inlinks uses the examples found in Wikipedia pages pointing etxoa mthep sense being trained. TiMBL-all uses both sources of examples. In order to classify a page p with respect to the senses for a word w, we first disambiguate all occurrences of w in the page p. Then we choose the sense which appears most frequently in the page according to TiMBL results. In case of ties we pick up the first sense listed in the Wikipedia disambiguation page. We have also experimented with a variant of the approach that uses our estimation of sense frequencies, similarly to what we did with the VSM approach. In this case, (i) when there is a tie between two or more senses (which is much more likely than in the VSM approach), we pick up the sense with the highest frequency according to our estimator; and (ii) when no sense reaches 30% of the cases in the page to be disambiguated, we also resort to the most frequent sense heuristic (among the candidates for the page). This experiment is called TiMBL-core+freq (we discarded ”inlinks” and ”all” versions because they were clearly worse than ”core”). 6.3 Classification Results Table 4 shows classification results. The accuracy of systems is reported as precision, i.e. the number of pages correctly classified divided by the total number of predictions. This is approximately the same as recall (correctly classified pages divided by total number of pages) for our systems, because the algorithms provide an answer for every page containing text (actual coverage is 94% because some pages only contain text as part of an image file such as photographs and logotypes). Table 4: Classification Results Experiment Precision random most frequent sense (estimation) .19 .46 TiMBL-core TiMBL-inlinks TiMBL-all TiMBL-core+freq .60 .50 .58 .67 VSM VSM-GT VSM-mixed VSM-GT+freq .67 .68 .67 .69 All systems are significantly better than the random and most frequent sense baselines (using p < 0.05 for a standard t-test). Overall, both approaches (using TiMBL WSD machinery and using VSM) lead to similar results (.67 vs. .69), which would make VSM preferable because it is a simpler and more efficient approach. Taking a 1362 Figure 1: Precision/Coverage curves for VSM-GT+freq classification algorithm closer look at the results with TiMBL, there are a couple of interesting facts: • There is a substantial difference between using only examples itaalke dnif fferroemnc tehe b Wikipedia Web page for the sense being trained (TiMBL-core, .60) and using examples from the Wikipedia pages pointing to that page (TiMBL-inlinks, .50). Examples taken from related pages (even if the relationship is close as in this case) seem to be too noisy for the task. This result is compatible with findings in (Santamar ı´a et al., 2003) using the Open Directory Project to extract examples automatically. • Our estimation of sense frequencies turns oOuutr rto e tbiem very helpful sfeor f cases wcihesere t our TiMBL-based algorithm cannot provide an answer: precision rises from .60 (TiMBLcore) to .67 (TiMBL-core+freq). The difference is statistically significant (p < 0.05) according to the t-test. As for the experiments with VSM, the variations tested do not provide substantial improvements to the baseline (which is .67). Using idf frequencies obtained from the Google Terabyte corpus (instead of frequencies obtained from the set of retrieved documents) provides only a small improvement (VSM-GT, .68), and adding the estimation of sense frequencies gives another small improvement (.69). Comparing the baseline VSM with the optimal setting (VSM-GT+freq), the difference is small (.67 vs .69) but relatively robust (p = 0.066 according to the t-test). Remarkably, the use of frequency estimations is very helpful for the WSD approach but not for the SVM one, and they both end up with similar performance figures; this might indicate that using frequency estimations is only helpful up to certain precision ceiling. 6.4 Precision/Coverage Trade-off All the above experiments are done at maximal coverage, i.e., all systems assign a sense for every document in the test collection (at least for every document with textual content). But it is possible to enhance search results diversity without annotating every document (in fact, not every document can be assigned to a Wikipedia sense, as we have discussed in Section 3). Thus, it is useful to investigate which is the precision/coverage trade-off in our dataset. We have experimented with the best performing system (VSM-GT+freq), introducing a similarity threshold: assignment of a document to a sense is only done if the similarity of the document to the Wikipedia page for the sense exceeds the similarity threshold. We have computed precision and coverage for every threshold in the range [0.00 −0.90] (beyond 0e.v9e0ry coverage was null) anngde represented 0th] e(b breeysuolntds in Figure 1 (solid line). The graph shows that we 1363 can classify around 20% of the documents with a precision above .90, and around 60% of the documents with a precision of .80. Note that we are reporting disambiguation results using a conventional WSD test set, i.e., one in which every test case (every document) has been manually assigned to some Wikipedia sense. But in our Web Search scenario, 44% of the documents were not assigned to any Wikipedia sense: in practice, our classification algorithm would have to cope with all this noise as well. Figure 1 (dotted line) shows how the precision/coverage curve is affected when the algorithm attempts to disambiguate all documents retrieved by Google, whether they can in fact be assigned to a Wikipedia sense or not. At a coverage of 20%, precision drops approximately from .90 to .70, and at a coverage of 60% it drops from .80 to .50. We now address the question of whether this performance is good enough to improve search re- sults diversity in practice. 6.5 Using Classification to Promote Diversity We now want to estimate how the reported classification accuracy may perform in practice to enhance diversity in search results. In order to provide an initial answer to this question, we have re-ranked the documents for the 40 nouns in our testbed, using our best classifier (VSM-GT+freq) and making a list of the top-ten documents with the primary criterion of maximising the number of senses represented in the set, and the secondary criterion of maximising the similarity scores of the documents to their assigned senses. The algorithm proceeds as follows: we fill each position in the rank (starting at rank 1), with the document which has the highest similarity to some of the senses which are not yet represented in the rank; once all senses are represented, we start choosing a second representative for each sense, following the same criterion. The process goes on until the first ten documents are selected. We have also produced a number of alternative rankings for comparison purposes: clustering (centroids): this method applies eHriiengrarc (hciecnatlr Agglomerative Clustering which proved to be the most competitive clustering algorithm in a similar task (Artiles et al., 2009) to the set of search results, forcing the algorithm to create ten clusters. The centroid of each cluster is then selected Table 5: Enhancement of Search Results Diversity • – – rank@10 # senses coverage Original rank2.8049% Wikipedia 4.75 77% clustering (centroids) 2.50 42% clustering (top ranked) 2.80 46% random 2.45 43% upper bound6.1597% as one of the top ten documents in the new rank. • clustering (top ranked): Applies the same clustering algorithm, db u)t: tAhpisp lti emse t tehe s top ranked document (in the original Google rank) of each cluster is selected. • • random: Randomly selects ten documents frraonmd otmhe: :se Rt aofn dreomtrielyve sde lreecstuslts te. upper bound: This is the maximal diversity tuhpapt can o beu nodb:tai Tnheids iins our mteasxtbiemda. lN doivteer tshitayt coverage is not 100%, because some words have more than ten meanings in Wikipedia and we are only considering the top ten documents. All experiments have been applied on the full set of documents in the testbed, including those which could not be annotated with any Wikipedia sense. Coverage is computed as the ratio of senses that appear in the top ten results compared to the number of senses that appear in all search results. Results are presented in Table 5. Note that diversity in the top ten documents increases from an average of 2.80 Wikipedia senses represented in the original search engine rank, to 4.75 in the modified rank (being 6.15 the upper bound), with the coverage of senses going from 49% to 77%. With a simple VSM algorithm, the coverage of Wikipedia senses in the top ten results is 70% larger than in the original ranking. Using Wikipedia to enhance diversity seems to work much better than clustering: both strategies to select a representative from each cluster are unable to improve the diversity of the original ranking. Note, however, that our evaluation has a bias towards using Wikipedia, because only Wikipedia senses are considered to estimate diversity. Of course our results do not imply that the Wikipedia modified rank is better than the original 1364 Google rank: there are many other factors that influence the final ranking provided by a search engine. What our results indicate is that, with simple and efficient algorithms, Wikipedia can be used as a reference to improve search results diversity for one-word queries. 7 Related Work Web search results clustering and diversity in search results are topics that receive an increasing attention from the research community. Diversity is used both to represent sub-themes in a broad topic, or to consider alternative interpretations for ambiguous queries (Agrawal et al., 2009), which is our interest here. Standard IR test collections do not usually consider ambiguous queries, and are thus inappropriate to test systems that promote diversity (Sanderson, 2008); it is only recently that appropriate test collections are being built, such as (Paramita et al., 2009) for image search and (Artiles et al., 2009) for person name search. We see our testbed as complementary to these ones, and expect that it can contribute to foster research on search results diversity. To our knowledge, Wikipedia has not explicitly been used before to promote diversity in search results; but in (Gollapudi and Sharma, 2009), it is used as a gold standard to evaluate diversification algorithms: given a query with a Wikipedia disambiguation page, an algorithm is evaluated as promoting diversity when different documents in the search results are semantically similar to different Wikipedia pages (describing the alternative senses of the query). Although semantic similarity is measured automatically in this work, our results confirm that this evaluation strategy is sound, because Wikipedia senses are indeed representative of search results. (Clough et al., 2009) analyses query diversity in a Microsoft Live Search, using click entropy and query reformulation as diversity indicators. It was found that at least 9.5% - 16.2% of queries could benefit from diversification, although no correlation was found between the number of senses of a word in Wikipedia and the indicators used to discover diverse queries. This result does not discard, however, that queries where applying diversity is useful cannot benefit from Wikipedia as a sense inventory. In the context of clustering, (Carmel et al., 2009) successfully employ Wikipedia to enhance automatic cluster labeling, finding that Wikipedia labels agree with manual labels associated by humans to a cluster, much more than with signif- icant terms that are extracted directly from the text. In a similar line, both (Gabrilovich and Markovitch, 2007) and (Syed et al., 2008) provide evidence suggesting that categories of Wikipedia articles can successfully describe common concepts in documents. In the field of Natural Language Processing, there has been successful attempts to connect Wikipedia entries to Wordnet senses: (RuizCasado et al., 2005) reports an algorithm that provides an accuracy of 84%. (Mihalcea, 2007) uses internal Wikipedia hyperlinks to derive sensetagged examples. But instead of using Wikipedia directly as sense inventory, Mihalcea then manually maps Wikipedia senses into Wordnet senses (claiming that, at the time of writing the paper, Wikipedia did not consistently report ambiguity in disambiguation pages) and shows that a WSD system based on acquired sense-tagged examples reaches an accuracy well beyond an (informed) most frequent sense heuristic. 8 Conclusions We have investigated whether generic lexical resources can be used to promote diversity in Web search results for one-word, ambiguous queries. We have compared WordNet and Wikipedia and arrived to a number of conclusions: (i) unsurprisingly, Wikipedia has a much better coverage of senses in search results, and is therefore more appropriate for the task; (ii) the distribution of senses in search results can be estimated using the internal graph structure of the Wikipedia and the relative number of visits received by each sense in Wikipedia, and (iii) associating Web pages to Wikipedia senses with simple and efficient algorithms, we can produce modified rankings that cover 70% more Wikipedia senses than the original search engine rankings. We expect that the testbed created for this research will complement the - currently short - set of benchmarking test sets to explore search results diversity and query ambiguity. Our testbed is publicly available for research purposes at http://nlp.uned.es. Our results endorse further investigation on the use of Wikipedia to organize search results. Some limitations of our research, however, must be 1365 noted: (i) the nature of our testbed (with every search result manually annotated in terms of two sense inventories) makes it too small to extract solid conclusions on Web searches (ii) our work does not involve any study of diversity from the point of view of Web users (i.e. when a Web query addresses many different use needs in practice); research in (Clough et al., 2009) suggests that word ambiguity in Wikipedia might not be related with diversity of search needs; (iii) we have tested our classifiers with a simple re-ordering of search results to test how much diversity can be improved, but a search results ranking depends on many other factors, some of them more crucial than diversity; it remains to be tested how can we use document/Wikipedia associations to improve search results clustering (for instance, providing seeds for the clustering process) and to provide search suggestions. Acknowledgments This work has been partially funded by the Spanish Government (project INES/Text-Mess) and the Xunta de Galicia. References R. Agrawal, S. Gollapudi, A. Halverson, and S. Leong. 2009. Diversifying Search Results. In Proc. of WSDM’09. ACM. P. Anick. 2003. Using Terminological Feedback for Web Search Refinement : a Log-based Study. In Proc. ACM SIGIR 2003, pages 88–95. ACM New York, NY, USA. J. Artiles, J. Gonzalo, and S. Sekine. 2009. WePS 2 Evaluation Campaign: overview of the Web People Search Clustering Task. In 2nd Web People Search Evaluation Workshop (WePS 2009), 18th WWW Conference. 2009. T. Brants and A. Franz. 2006. Web 1T 5-gram, version 1. Philadelphia: Linguistic Data Consortium. D. Carmel, H. Roitman, and N. Zwerdling. 2009. Enhancing Cluster Labeling using Wikipedia. In Pro- ceedings of the 32nd international ACM SIGIR conference on Research and development in information retrieval, pages 139–146. ACM. C. Carpineto, S. Osinski, G. Romano, and Dawid Weiss. 2009. A Survey of Web Clustering Engines. ACM Computing Surveys, 41(3). Y. Chen, S. Yat Mei Lee, and C. Huang. 2009. PolyUHK: A Robust Information Extraction System for Web Personal Names. In Proc. WWW’09 (WePS2 Workshop). ACM. C. Clarke, M. Kolla, G. Cormack, O. Vechtomova, A. Ashkan, S. B ¨uttcher, and I. MacKinnon. 2008. Novelty and Diversity in Information Retrieval Evaluation. In Proc. SIGIR ’08, pages 659–666. ACM. P. Clough, M. Sanderson, M. Abouammoh, S. Navarro, and M. Paramita. 2009. Multiple Approaches to Analysing Query Diversity. In Proc. of SIGIR 2009. ACM. W. Daelemans, J. Zavrel, K. van der Sloot, and A. van den Bosch. 2001 . TiMBL: Tilburg Memory Based Learner, version 4.0, Reference Guide. Technical report, University of Antwerp. E. Gabrilovich and S. Markovitch. 2007. Computing Semantic Relatedness using Wikipedia-based Explicit Semantic Analysis. In Proceedings of The 20th International Joint Conference on Artificial Intelligence (IJCAI), Hyderabad, India. S. Gollapudi and A. Sharma. 2009. An Axiomatic Approach for Result Diversification. In Proc. WWW 2009, pages 381–390. ACM New York, NY, USA. R. Mihalcea. 2007. Using Wikipedia for Automatic Word Sense Disambiguation. In Proceedings of NAACL HLT, volume 2007. G. Miller, C. R. Beckwith, D. Fellbaum, Gross, and K. Miller. 1990. Wordnet: An on-line lexical database. International Journal of Lexicograph, 3(4). G.A Miller, C. Leacock, R. Tengi, and Bunker R. T. 1993. A Semantic Concordance. In Proceedings of the ARPA WorkShop on Human Language Technology. San Francisco, Morgan Kaufman. M. Paramita, M. Sanderson, and P. Clough. 2009. Diversity in Photo Retrieval: Overview of the ImageCLEFPhoto task 2009. CLEF working notes, 2009. M. Ruiz-Casado, E. Alfonseca, and P. Castells. 2005. Automatic Assignment of Wikipedia Encyclopaedic Entries to Wordnet Synsets. Advances in Web Intelligence, 3528:380–386. M. Sanderson. 2000. Retrieving with Good Sense. Information Retrieval, 2(1):49–69. M. Sanderson. 2008. Ambiguous Queries: Test Collections Need More Sense. In Proceedings of the 31st annual international ACM SIGIR conference on Research and development in information retrieval, pages 499–506. ACM New York, NY, USA. C. Santamar ı´a, J. Gonzalo, and F. Verdejo. 2003. Automatic Association of Web Directories to Word Senses. Computational Linguistics, 29(3):485–502. Z. S. Syed, T. Finin, and Joshi. A. 2008. Wikipedia as an Ontology for Describing Documents. In Proc. ICWSM’08. 1366
5 0.63144851 184 acl-2010-Open-Domain Semantic Role Labeling by Modeling Word Spans
Author: Fei Huang ; Alexander Yates
Abstract: Most supervised language processing systems show a significant drop-off in performance when they are tested on text that comes from a domain significantly different from the domain of the training data. Semantic role labeling techniques are typically trained on newswire text, and in tests their performance on fiction is as much as 19% worse than their performance on newswire text. We investigate techniques for building open-domain semantic role labeling systems that approach the ideal of a train-once, use-anywhere system. We leverage recently-developed techniques for learning representations of text using latent-variable language models, and extend these techniques to ones that provide the kinds of features that are useful for semantic role labeling. In experiments, our novel system reduces error by 16% relative to the previous state of the art on out-of-domain text.
6 0.63139415 87 acl-2010-Discriminative Modeling of Extraction Sets for Machine Translation
7 0.63121772 136 acl-2010-How Many Words Is a Picture Worth? Automatic Caption Generation for News Images
8 0.63092953 79 acl-2010-Cross-Lingual Latent Topic Extraction
9 0.63020933 218 acl-2010-Structural Semantic Relatedness: A Knowledge-Based Method to Named Entity Disambiguation
10 0.63020527 113 acl-2010-Extraction and Approximation of Numerical Attributes from the Web
11 0.6297121 109 acl-2010-Experiments in Graph-Based Semi-Supervised Learning Methods for Class-Instance Acquisition
12 0.62950909 169 acl-2010-Learning to Translate with Source and Target Syntax
13 0.62892938 48 acl-2010-Better Filtration and Augmentation for Hierarchical Phrase-Based Translation Rules
14 0.62875664 133 acl-2010-Hierarchical Search for Word Alignment
15 0.62836838 51 acl-2010-Bilingual Sense Similarity for Statistical Machine Translation
16 0.62770414 55 acl-2010-Bootstrapping Semantic Analyzers from Non-Contradictory Texts
17 0.62763953 172 acl-2010-Minimized Models and Grammar-Informed Initialization for Supertagging with Highly Ambiguous Lexicons
18 0.62644875 146 acl-2010-Improving Chinese Semantic Role Labeling with Rich Syntactic Features
19 0.62538254 245 acl-2010-Understanding the Semantic Structure of Noun Phrase Queries
20 0.62499774 52 acl-2010-Bitext Dependency Parsing with Bilingual Subtree Constraints