Naslov
Leveraging Lexical Substitutes for Unsupervised Word Sense Induction

Autori
Alagić, Domagoj ; Šnajder, Jan ; Padó, Sebastian

Vrsta, podvrsta i kategorija rada
Radovi u zbornicima skupova, cjeloviti rad (in extenso), znanstveni

Izvornik
Proceedings of the Thirty-Second AAAI Conference on Artificial Intelligence (AAAI-18) / - , 2018, 5004-5011

Skup
32nd AAAI Conference on Artificial Intelligence (AAAI-18)

Mjesto i datum
New Orleans (LA), Sjedinjene Američke Države, 02.02.2018. - 07.02.2018

Vrsta sudjelovanja
Predavanje

Vrsta recenzije
Međunarodna recenzija

Ključne riječi
Lexical semantics ; Natural language processing ; Lexical substitution ; Polysemy ; Word sense induction

Sažetak
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.

Izvorni jezik
Engleski

Znanstvena područja
Računarstvo, Informacijske i komunikacijske znanosti

POVEZANOST RADA