Word embeddings are widely used in Natural Language Processing, mainly due to their success in capturing semantic information from massive corpora. However, their creation process does not allow the different meanings of a word to be automatically separated, as it conflates them into a single vector. We address this issue by proposing a new model which learns word and sense embeddings jointly. Our model exploits large corpora and knowledge from semantic networks in order to produce a unified vector space of word and sense embeddings. We evaluate the main features of our approach both qualitatively and quantitatively in a variety of tasks, highlighting the advantages of the proposed method in comparison to state-of-the-art word- and sense-based models.
Word embeddings are widely used in Nat-ural Language Processing, mainly due totheir success in capturing semantic infor-mation from massive corpora. However,their creation process does not allow thedifferent meanings of a word to be auto-matically separated, as it conflates theminto a single vector. We address this issueby proposing a new model which learnsword and sense embeddings jointly. Ourmodel exploits large corpora and knowl-edge from semantic networks in order toproduce a unified vector space of wordand sense embeddings. We evaluate themain features of our approach both qual-itatively and quantitatively in a variety oftasks, highlighting the advantages of theproposed method in comparison to state-of-the-art word- and sense-based models.
Embedding Words and Senses Together via Joint Knowledge-Enhanced Training / Mancini, Massimiliano; CAMACHO COLLADOS, Jose'; Iacobacci, IGNACIO JAVIER; Navigli, Roberto. - ELETTRONICO. - (2017), pp. 100-111. (Intervento presentato al convegno 21st Conference on Computational Natural Language Learning (CoNLL 2017) tenutosi a Vancouver; Canada nel 3-4 Agosto 2017) [10.18653/v1/K17-1012].
Embedding Words and Senses Together via Joint Knowledge-Enhanced Training
Mancini, Massimiliano;
2017-01-01
Abstract
Word embeddings are widely used in Natural Language Processing, mainly due to their success in capturing semantic information from massive corpora. However, their creation process does not allow the different meanings of a word to be automatically separated, as it conflates them into a single vector. We address this issue by proposing a new model which learns word and sense embeddings jointly. Our model exploits large corpora and knowledge from semantic networks in order to produce a unified vector space of word and sense embeddings. We evaluate the main features of our approach both qualitatively and quantitatively in a variety of tasks, highlighting the advantages of the proposed method in comparison to state-of-the-art word- and sense-based models.I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione
