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

Word-sense recognition and disambiguation (WERD) is the task of identifying word phrases and their senses in natural language text. Though it is well understood how to disambiguate noun phrases, this task is much less studied for verbs and verbal phrases. We present Werdy, a framework for WERD with particular focus on verbs and verbal phrases. Our framework first identifies multi-word expressions based on the syntactic structure of the sentence; this allows us to recognize both contiguous and non-contiguous phrases. We then generate a list of candidate senses for each word or phrase, using novel syntactic and semantic pruning techniques. We also construct and leverage a new resource of pairs of senses for verbs and their object arguments. Finally, we feed the so-obtained candidate senses into standard word-sense disambiguation (WSD) methods, and boost their precision and recall. Our experiments indicate that Werdy significantly increases the performance of existing WSD methods.

[1]  Simone Paolo Ponzetto,et al.  Knowledge-Rich Word Sense Disambiguation Rivaling Supervised Systems , 2010, ACL.

[2]  Gerhard Weikum,et al.  PATTY: A Taxonomy of Relational Patterns with Semantic Types , 2012, EMNLP.

[3]  Neville Ryant,et al.  A Large-scale Classication of English Verbs , 2006 .

[4]  Dan Klein,et al.  Accurate Unlexicalized Parsing , 2003, ACL.

[5]  Daniel Gildea,et al.  The Proposition Bank: An Annotated Corpus of Semantic Roles , 2005, CL.

[6]  Martha Palmer,et al.  Improving Verb Sense Disambiguation with Automatically Retrieved Semantic Knowledge , 2008, 2008 IEEE International Conference on Semantic Computing.

[7]  B. T. S. Atkins,et al.  The Oxford Guide to Practical Lexicography , 2008 .

[8]  Mark A. Finlayson.  Java Libraries for Accessing the Princeton Wordnet: Comparison and Evaluation , 2014, GWC.

[9]  Rada Mihalcea,et al.  Coarse to Fine Grained Sense Disambiguation in Wikipedia , 2013, *SEM@NAACL-HLT.

[10]  Neville Ryant,et al.  A large-scale classification of English verbs , 2008, Lang. Resour. Evaluation.

[11]  Roberto Navigli.  A Quick Tour of Word Sense Disambiguation, Induction and Related Approaches , 2012, SOFSEM.

[12]  Iryna Gurevych,et al.  Using Distributional Similarity for Lexical Expansion in Knowledge-based Word Sense Disambiguation , 2012, COLING.

[13]  Tiziano Flati,et al.  SPred: Large-scale Harvesting of Semantic Predicates , 2013, ACL.

[14]  Michael E. Lesk,et al.  Automatic sense disambiguation using machine readable dictionaries: how to tell a pine cone from an ice cream cone , 1986, SIGDOC '86.

[15]  Eneko Agirre,et al.  Random Walks for Knowledge-Based Word Sense Disambiguation , 2014, CL.

[16]  Christiane Fellbaum,et al.  Book Reviews: WordNet: An Electronic Lexical Database , 1999, CL.

[17]  Ted Pedersen,et al.  Extended Gloss Overlaps as a Measure of Semantic Relatedness , 2003, IJCAI.

[18]  Roberto Navigli,et al.  SemEval-2007 Task 07: Coarse-Grained English All-Words Task , 2007, Fourth International Workshop on Semantic Evaluations (SemEval-2007).

[19]  John B. Lowe,et al.  The Berkeley FrameNet Project , 1998, ACL.

[20]  Christiane Fellbaum,et al.  Building Semantic Concordances , 1998 .

[21]  Roberto Navigli,et al.  Word sense disambiguation: A survey , 2009, CSUR.

[22]  Jan Svartvik,et al.  A __ comprehensive grammar of the English language , 1988 .

[23]  Iryna Gurevych,et al.  Automated Verb Sense Labelling Based on Linked Lexical Resources , 2014, EACL.

[24]  Adam Kilgarriff,et al.  Framework and Results for English SENSEVAL , 2000, Comput. Humanit..

[25]  Patrick Hanks,et al.  Contextual dependency and lexical sets , 1996 .

[26]  Hwee Tou Ng,et al.  NUS-PT: Exploiting Parallel Texts for Word Sense Disambiguation in the English All-Words Tasks , 2007, Fourth International Workshop on Semantic Evaluations (SemEval-2007).

[27]  Ted Pedersen,et al.  WordNet::Similarity - Measuring the Relatedness of Concepts , 2004, NAACL.

[28]  Martha Palmer,et al.  The Role of Semantic Roles in Disambiguating Verb Senses , 2005, ACL.

[29]  Iryna Gurevych,et al.  UBY - A Large-Scale Unified Lexical-Semantic Resource Based on LMF , 2012, EACL.

[30]  Hwee Tou Ng,et al.  It Makes Sense: A Wide-Coverage Word Sense Disambiguation System for Free Text , 2010, ACL.

[31]  Mark A. Finlayson,et al.  Detecting Multi-Word Expressions Improves Word Sense Disambiguation , 2011, MWE@ACL.

[32]  Iryna Gurevych,et al.  DKPro WSD: A Generalized UIMA-based Framework for Word Sense Disambiguation , 2013, ACL.

[33]  Beth Levin,et al.  English Verb Classes and Alternations: A Preliminary Investigation , 1993 .

[34]  Timothy Baldwin,et al.  Multiword Expressions: A Pain in the Neck for NLP , 2002, CICLing.

[35]  Martha Palmer,et al.  Improving English verb sense disambiguation performance with linguistically motivated features and clear sense distinction boundaries , 2009, Lang. Resour. Evaluation.

[36]  Victoria Arranz,et al.  Multiwords and Word Sense Disambiguation , 2005, CICLing.

[37]  Eneko Agirre,et al.  Personalizing PageRank for Word Sense Disambiguation , 2009, EACL.

[38]  Luciano Del Corro,et al.  ClausIE: clause-based open information extraction , 2013, WWW.

[39]  Simone Paolo Ponzetto,et al.  BabelNet: The automatic construction, evaluation and application of a wide-coverage multilingual semantic network , 2012, Artif. Intell..

[40]  Mirella Lapata,et al.  An Experimental Study of Graph Connectivity for Unsupervised Word Sense Disambiguation , 2010, IEEE Transactions on Pattern Analysis and Machine Intelligence.