Homonymy and Polysemy Detection with Multilingual Information

Deciding whether a semantically ambiguous word is homonymous or polysemous is equivalent to establishing whether it has any pair of senses that are semantically unrelated. We present novel methods for this task that leverage information from multilingual lexical resources. We formally prove the theoretical properties that provide the foundation for our methods. In particular, we show how the One Homonym Per Translation hypothesis of Hauer and Kondrak (2020a) follows from the synset properties formulated by Hauer and Kondrak (2020b). Experimental evaluation shows that our approach sets a new state of the art for homonymy detection.

[1]  Anu Koskela,et al.  Key Terms in Semantics , 2010 .

[2]  Grzegorz Kondrak,et al.  One Homonym per Translation , 2020, AAAI.

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

[4]  Ted Pedersen,et al.  Maximizing Semantic Relatedness to Perform Word Sense Disambiguation , 2005 .

[5]  Jörg Tiedemann,et al.  Finding Synonyms Using Automatic Word Alignment and Measures of Distributional Similarity , 2006, ACL.

[6]  Roberto Navigli,et al.  Meaningful Clustering of Senses Helps Boost Word Sense Disambiguation Performance , 2006, ACL.

[7]  Suzanne Stevenson,et al.  A comparison of homonym meaning frequency estimates derived from movie and television subtitles, free association, and explicit ratings , 2018, Behavior Research Methods.

[8]  Helge Dyvik,et al.  Translations as semantic mirrors: from parallel corpus to wordnet , 2004 .

[9]  Sebastian Padó,et al.  Ontology-based Distinction between Polysemy and Homonymy , 2011, IWCS.

[10]  Suzanne Stevenson,et al.  What Company Do Semantically Ambiguous Words Keep? Insights from Distributional Word Vectors , 2018, CogSci.

[11]  James H. Martin,et al.  Speech and language processing: an introduction to natural language processing, computational linguistics, and speech recognition, 2nd Edition , 2000, Prentice Hall series in artificial intelligence.

[12]  Mitchell P. Marcus,et al.  OntoNotes: The 90% Solution , 2006, NAACL.

[13]  Lora Aroyo,et al.  Homonym Detection For Humor Recognition In Short Text , 2018, WASSA@EMNLP.

[14]  Vladimir Pericliev.  On Colexification among Basic Vocabulary , 2015 .

[15]  Frederick Liu,et al.  Handling Homographs in Neural Machine Translation , 2017, NAACL.

[16]  ResnikPhilip,et al.  Distinguishing systems and distinguishing senses: new evaluation methods for Word Sense Disambiguation , 1999 .

[17]  Susan Windisch Brown,et al.  Choosing Sense Distinctions for WSD: Psycholinguistic Evidence , 2008, ACL.

[18]  Grzegorz Kondrak,et al.  Synonymy = Translational Equivalence , 2020, ArXiv.

[19]  P.J.T.M. Vossen,et al.  Right or wrong: combing lexical resources in the EuroWordNet project , 1996 .