Leveraging Lexical Substitutes for Unsupervised Word Sense Induction (CROSBI ID 658223)
Prilog sa skupa u zborniku | izvorni znanstveni rad | međunarodna recenzija
Podaci o odgovornosti
Alagić, Domagoj ; Šnajder, Jan ; Padó, Sebastian
engleski
Leveraging Lexical Substitutes for Unsupervised Word Sense Induction
Word sense induction is the most prominent unsupervised approach to lexical disambiguation. It clusters word instances, typically represented by their bag-of-words contexts. Therefore, uninformative and ambiguous contexts present a major challenge. In this paper, we investigate the use of an alternative instance representation based on lexical substitutes, i.e., contextually suitable, meaning-preserving replacements. Using lexical substitutes predicted by a state- of-the-art automatic system and a simple clustering algorithm, we out-perform bag-of- words instance representations and compete with much more complex structured probabilistic models. Furthermore, we show that an oracle based on manually-labeled lexical substitutes yields yet substantially higher performance. Taken together, this provides evidence for a complementarity between word sense induction and lexical substitution that has not been given much consideration before.
Lexical semantics ; Natural language processing ; Lexical substitution ; Polysemy ; Word sense induction
nije evidentirano
nije evidentirano
nije evidentirano
nije evidentirano
nije evidentirano
nije evidentirano
Podaci o prilogu
5004-5011.
2018.
objavljeno
Podaci o matičnoj publikaciji
Proceedings of the Thirty-Second AAAI Conference on Artificial Intelligence (AAAI-18)
Podaci o skupu
32nd AAAI Conference on Artificial Intelligence (AAAI-18)
predavanje
02.02.2018-07.02.2018
New Orleans (LA), Sjedinjene Američke Države