Regular polysemy: from sense vectors to sense patterns

Anastasiya Lopukhina, Konstantin Lopukhin


Abstract
Regular polysemy was extensively investigated in lexical semantics, but this phenomenon has been very little studied in distributional semantics. We propose a model for regular polysemy detection that is based on sense vectors and allows to work directly with senses in semantic vector space. Our method is able to detect polysemous words that have the same regular sense alternation as in a given example (a word with two automatically induced senses that represent one polysemy pattern, such as ANIMAL / FOOD). The method works equally well for nouns, verbs and adjectives and achieves average recall of 0.55 and average precision of 0.59 for ten different polysemy patterns.
Anthology ID:
W16-5303
Volume:
Proceedings of the 5th Workshop on Cognitive Aspects of the Lexicon (CogALex - V)
Month:
December
Year:
2016
Address:
Osaka, Japan
Venue:
CogALex
SIG:
Publisher:
The COLING 2016 Organizing Committee
Note:
Pages:
19–23
Language:
URL:
https://aclanthology.org/W16-5303
DOI:
Bibkey:
Cite (ACL):
Anastasiya Lopukhina and Konstantin Lopukhin. 2016. Regular polysemy: from sense vectors to sense patterns. In Proceedings of the 5th Workshop on Cognitive Aspects of the Lexicon (CogALex - V), pages 19–23, Osaka, Japan. The COLING 2016 Organizing Committee.
Cite (Informal):
Regular polysemy: from sense vectors to sense patterns (Lopukhina & Lopukhin, CogALex 2016)
Copy Citation:
PDF:
https://preview.aclanthology.org/auto-file-uploads/W16-5303.pdf