2,311 Hits in 8.9 sec

Verb Sense Disambiguation Using Selectional Preferences Extracted with a State-of-the-art Semantic Role Labeler

Patrick Ye, Timothy Baldwin
2006 Australasian Language Technology Association Workshop  
preferences to be presented in this paper are extracted from the output of a state-of-the-art semantic role labeler and incorporate a much richer set of semantic roles.  ...  This paper investigates whether multisemantic-role (MSR) based selectional preferences can be used to improve the performance of supervised verb sense disambiguation.  ...  The research in this paper has been supported by the Australian Research Council through Discovery Project grant number DP0663879, and also NTT Communication Science Laboratories, Nippon Telegraph and  ... 
dblp:conf/acl-alta/YeB06 fatcat:zegavz26sjgerndpsxuuyv52fe

Selection Preference Basede Verb Sense Disambiguation Using WordNet

Patrick Ye
2004 Australasian Language Technology Association Workshop  
This study investigates whether better performance can be achieved using the current state-of-art semantic role labelling systems, and explores alternative ways of applying selectional preferences for  ...  Selectional preferences are a source of linguistic information commonly applied to the task of Word Sense Disambiguation (WSD).  ...  Adrian Pearce, for reviewing the paper. This research was sponsored by Australian Postgraduate Awards (APA) from the Australian Research Council (ARC).  ... 
dblp:conf/acl-alta/Ye04 fatcat:t2s5pzigdbcmzdfubjjovuswbi

Generating Training Data for Semantic Role Labeling based on Label Transfer from Linked Lexical Resources

Silvana Hartmann, Judith Eckle-Kohler, Iryna Gurevych
2016 Transactions of the Association for Computational Linguistics  
The automatically labeled training data ( knowledge-based-srl/) are evaluated on four corpora from different domains for the tasks of word sense disambiguation and semantic role  ...  ) by linking them on the sense or on the role level.  ...  We thank the action editors and anonymous reviewers for their thoughtful comments. Additional thanks go to Nancy Ide and Collin Baker for providing the MASC dataset.  ... 
doi:10.1162/tacl_a_00093 fatcat:cirmmv7qmrao7btya4lpcyokge

Automated Verb Sense Labelling Based on Linked Lexical Resources

Kostadin Cholakov, Judith Eckle-Kohler, Iryna Gurevych
2014 Proceedings of the 14th Conference of the European Chapter of the Association for Computational Linguistics  
We evaluate our labelling method intrinsically on SemCor and extrinsically by using automatically labelled corpus text to train a classifier for verb sense disambiguation.  ...  Testing this classifier on verbs from the English MASC corpus and on verbs from the Senseval-3 all-words disambiguation task shows that it matches the performance of a classifier which has been trained  ...  Acknowledgments This work has been supported by the Volkswagen Foundation as part of the Lichtenberg-Professorship Program under grant No.  ... 
doi:10.3115/v1/e14-1008 dblp:conf/eacl/CholakovEG14 fatcat:b262hpmdobhdnfz4qoxsbgncti

A Novel Approach to Word Sense Disambiguation Based on Topical and Semantic Association

Xin Wang, Wanli Zuo, Ying Wang
2013 The Scientific World Journal  
Word sense disambiguation (WSD) is a fundamental problem in nature language processing, the objective of which is to identify the most proper sense for an ambiguous word in a given context.  ...  We then exploit syntactic features, topic span features, and semantic features to disambiguate nouns and verbs in the context of ambiguous word.  ...  The sentence frames state that different senses of verbs may occur with an infinitive, with a transitive, and with an intransitive syntactic frame.  ... 
doi:10.1155/2013/586327 pmid:24294131 pmcid:PMC3833093 fatcat:ibbu2es2xzap3p77dpebtqjzsu

Werdy: Recognition and Disambiguation of Verbs and Verb Phrases with Syntactic and Semantic Pruning

Luciano Del Corro, Rainer Gemulla, Gerhard Weikum
2014 Proceedings of the 2014 Conference on Empirical Methods in Natural Language Processing (EMNLP)  
We then generate a list of candidate senses for each word or phrase, using novel syntactic and semantic pruning techniques.  ...  We present Werdy, a framework for WERD with particular focus on verbs and verbal phrases.  ...  In the final step, Werdy employs a state-of-the-art general WSD method to select the most suitable sense from the remaining candidates.  ... 
doi:10.3115/v1/d14-1042 dblp:conf/emnlp/CorroGW14 fatcat:yuq2xwpchrcyti56nhth3r5ube

Selectional Preferences for Semantic Role Classification

Beñat Zapirain, Eneko Agirre, Lluís Màrquez, Mihai Surdeanu
2013 Computational Linguistics  
Furthermore, we show that a state-of-the-art SRC system extended with features based on selectional preferences performs significantly better, both in domain (17% error reduction) and out of domain (13%  ...  We mitigate this problem using models that integrate automatically learned selectional preferences (SP). We explore a range of models based on WordNet and distributional-similarity SPs.  ...  Acknowledgments The authors would like to thank the three anonymous reviewers for their detailed and insightful comments on the submitted version of this manuscript, which helped us to improve it significantly  ... 
doi:10.1162/coli_a_00145 fatcat:wadqjxjw7bcvvaay4f6agredgi

Coupled intrinsic and extrinsic human language resource-based query expansion [article]

Bhawani Selvaretnam, Mohammed Belkhatir
2020 arXiv   pre-print
queries that are in line with the vocabulary of the documents deemed relevant to a specific search goal.  ...  Additionally, extrinsic language-based resources such as ontologies are needed to suggest expansion concepts semantically coherent with the query content.  ...  The approach of utilizing the "first sense heuristic" (i.e. choosing the first or predominant sense of a word) is reiterated by McCarthy et al. (2007) as a method that is used by most state-of-the-art  ... 
arXiv:2004.11083v1 fatcat:pxro5fus6zhrxiw32a2xbzsiue

Improving the Use of Pseudo-Words for Evaluating Selectional Preferences

Nathanael Chambers, Daniel Jurafsky
2010 Annual Meeting of the Association for Computational Linguistics  
A selectional preference model ranks a set of possible arguments for a verb by their semantic fit to the verb. Pseudo-words serve as a proxy evaluation for these decisions.  ...  While pseudowords originally evaluated word sense disambiguation, they are now commonly used to evaluate selectional preferences.  ...  Any opinions, ndings, and conclusion or recommendations expressed in this material are those of the authors and do not necessarily reect the view of the AFRL.  ... 
dblp:conf/acl/ChambersJ10 fatcat:7y3xmlyffvclbjxedwyyqojmom

A Knowledge-Intensive Model for Prepositional Phrase Attachment

Ndapandula Nakashole, Tom M. Mitchell
2015 Proceedings of the 53rd Annual Meeting of the Association for Computational Linguistics and the 7th International Joint Conference on Natural Language Processing (Volume 1: Long Papers)  
Experiments show that our method yields improvements over existing methods including a state of the art dependency parser. 1  ...  We present a method for resolving ambiguities arising from PPs, making extensive use of semantic knowledge from various resources.  ...  Acknowledgments We thank Shashank Srivastava and members of the NELL team at CMU for helpful comments. This research was supported by DARPA under contract number FA8750-13-2-0005.  ... 
doi:10.3115/v1/p15-1036 dblp:conf/acl/NakasholeM15 fatcat:vx3gei52xneidpwpl3rin57y7q

Can Selectional Preferences Help Automatic Semantic Role Labeling?

Shumin Wu, Martha Palmer
2015 Proceedings of the Fourth Joint Conference on Lexical and Computational Semantics  
Using the topic features generated by an LDA model on the extracted predicate-arguments over the Chinese Gigaword corpus, we show improvement to our state-of-the-art Chinese SRL system by 2.34 F1 points  ...  We describe a topic model based approach for selectional preference.  ...  The Janus supercomputer is a joint effort of the University of Colorado Boulder, the University of Colorado Denver and the National Center for Atmospheric Research.  ... 
doi:10.18653/v1/s15-1027 dblp:conf/starsem/WuP15 fatcat:36qgtlcpozahzbblij5cxmoj44

Semantically Enriched Models for Modal Sense Classification

Mengfei Zhou, Anette Frank, Annemarie Friedrich, Alexis Palmer
2015 Proceedings of the First Workshop on Linking Computational Models of Lexical, Sentential and Discourse-level Semantics  
Besides improved classification performance, especially for difficult sense distinctions, closer examination of interpretable feature sets allows us to obtain a better understanding of relevant semantic  ...  In this work we uncover the difficulty of particular modal sense distinctions by eliminating both distributional bias and sparsity of existing small-scale annotated corpora used in prior work.  ...  Related Work Most relevant to our work is the state of the art in modal sense classification in Ruppenhofer and Rehbein (2012) .  ... 
doi:10.18653/v1/w15-2705 dblp:conf/emnlp/ZhouFFP15 fatcat:xmgafed475dvjg3oqh5jexnyc4

Word sense and semantic relations in noun compounds

Su Nam Kim, Timothy Baldwin
2013 ACM Transactions on Speech and Language Processing  
Our primary goal is to disambiguate the word sense of component words in NCs, based on investigation of "semantic collocation" between them.  ...  Further, we develop a word sense-based approach to interpreting the semantic relations in NCs.  ...  Acknowledgements This research was supported in part by the Australian Research Council, under grants FT120100658 and DP110101934.  ... 
doi:10.1145/2483969.2483971 dblp:journals/tslp/KimB13 fatcat:c7oa75ehdjhktaz5fmhf5yonuy

K-SRL: Instance-based Learning for Semantic Role Labeling

Alan Akbik, Yunyao Li
2016 International Conference on Computational Linguistics  
Semantic role labeling (SRL) is the task of identifying and labeling predicate-argument structures in sentences with semantic frame and role labels.  ...  In a comparative evaluation we experimentally demonstrate that our instance-based learning approach significantly outperforms current state-of-the-art systems on both in-domain and out-of-domain data,  ...  Role labels roughly correspond to simple questions (who, when, how, why, with whom) with regards to the disambiguated predicate.  ... 
dblp:conf/coling/AkbikL16 fatcat:kf74ojisuncw3g5knngj33lbf4

Prepositions in Applications: A Survey and Introduction to the Special Issue

Timothy Baldwin, Valia Kordoni, Aline Villavicencio
2009 Computational Linguistics  
In addition to standalone word sense disambiguation tasks, however, there needs to be more research on the interaction of preposition semantics with other semantic tasks, such as semantic role labeling  ...  as semantic role labeling.  ... 
doi:10.1162/coli.2009.35.2.119 fatcat:kxejjmz42vasbmnlgksnbyc6iy
« Previous Showing results 1 — 15 out of 2,311 results