Integrating WordNet for Multiple Sense Embeddings in Vector Semantics

Popular distributional approaches to semantics allow for only a single embedding of any particular word. A single embedding per word conflates the distinct meanings of the word and their appropriate contexts, irrespective of whether those usages are related of completely disjoint. We compare models that use the graph structure of the knowledge base WordNet as a postprocessing step to improve vector-space models with multiple sense embeddings for each word, and explore the application to word sense disambiguation.

[1]  Raymond J. Mooney,et al.  Multi-Prototype Vector-Space Models of Word Meaning , 2010, NAACL.

[2]  Hans Uszkoreit,et al.  Multi-Objective Optimization for the Joint Disambiguation of Nouns and Named Entities , 2015, ACL.

[3]  Jeffrey Dean,et al.  Efficient Estimation of Word Representations in Vector Space , 2013, ICLR.

[4]  Patrick Pantel,et al.  From Frequency to Meaning: Vector Space Models of Semantics , 2010, J. Artif. Intell. Res..

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

[6]  Yulia Tsvetkov,et al.  Problems With Evaluation of Word Embeddings Using Word Similarity Tasks , 2016, RepEval@ACL.

[7]  George A. Miller,et al.  WordNet: A Lexical Database for English , 1995, HLT.

[8]  Andrew Y. Ng,et al.  Improving Word Representations via Global Context and Multiple Word Prototypes , 2012, ACL.

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

[10]  Hinrich Schütze,et al.  AutoExtend: Extending Word Embeddings to Embeddings for Synsets and Lexemes , 2015, ACL.

[11]  Andrew McCallum,et al.  Efficient Non-parametric Estimation of Multiple Embeddings per Word in Vector Space , 2014, EMNLP.

[12]  Jeffrey Dean,et al.  Distributed Representations of Words and Phrases and their Compositionality , 2013, NIPS.

[13]  Roberto Navigli,et al.  SemEval-2015 Task 13: Multilingual All-Words Sense Disambiguation and Entity Linking , 2015, *SEMEVAL.

[14]  R. Shaw.  Problems of evaluation , 1980 .

[15]  John B. Goodenough,et al.  Contextual correlates of synonymy , 1965, CACM.

[16]  Ted Pedersen,et al.  Using WordNet-based Context Vectors to Estimate the Semantic Relatedness of Concepts , 2006 .

[17]  Chris Dyer,et al.  Ontologically Grounded Multi-sense Representation Learning for Semantic Vector Space Models , 2015, NAACL.

[18]  Peter D. Turney.  Mining the Web for Synonyms: PMI-IR versus LSA on TOEFL , 2001, ECML.

[19]  Zhiyuan Liu,et al.  A Unified Model for Word Sense Representation and Disambiguation , 2014, EMNLP.

[20]  T. Landauer,et al.  A Solution to Plato's Problem: The Latent Semantic Analysis Theory of Acquisition, Induction, and Representation of Knowledge. , 1997 .