Szczegóły publikacji
Opis bibliograficzny
Disambiguated skip-gram model / Karol GRZEGORZCZYK, Marcin KURDZIEL // W: EMNLP 2018 [Dokument elektroniczny] : [proceedings of the 2018 conference on Empirical Methods in Natural Language Processing] : Brussels, Belgium, Oct. 31 – Nov. 4. — Wersja do Windows. — Dane tekstowe. — Stroudsburg : Association for Computational Linguistic (ACL), cop. 2018. — e-ISBN: 978-1-948087-84-1. — S. 1445–1454. — Wymagania systemowe: Adobe Reader. — Bibliogr. s. 1453–1454, Abstr. — K. Grzegorczyk – dod. afiliacja: Allegro, Poznań
Autorzy (2)
Dane bibliometryczne
| ID BaDAP | 118050 |
|---|---|
| Data dodania do BaDAP | 2018-11-20 |
| Tekst źródłowy | URL |
| Rok publikacji | 2018 |
| Typ publikacji | materiały konferencyjne (aut.) |
| Otwarty dostęp |  |
| Konferencja | 2018 conference on Empirical Methods in Natural Language Processing |
Abstract
We present disambiguated skip-gram: a neural-probabilistic model for learning multi-sense distributed representations of words. Disambiguated skip-gram jointly estimates a skip-gram-like context word prediction model and a word sense disambiguation model. Unlike previous probabilistic models for learning multi-sense word embeddings, disambiguated skip-gram is end-to-end differentiable and can be interpreted as a simple feed-forward neural network. We also introduce an effective pruning strategy for the embeddings learned by disambiguated skip-gram. This allows us to control the granularity of representations learned by our model. In experimental evaluation disambiguated skip-gram improves state-of-the are results in several word sense induction benchmarks. © 2018 Association for Computational Linguistics