Embedding Words and Senses Together via Joint Knowledge-Enhanced Training
| Autor: | Roberto Navigli, Jose Camacho-Collados, Ignacio Iacobacci, Massimiliano Mancini |
|---|---|
| Rok vydání: | 2016 |
| Předmět: |
FOS: Computer and information sciences
Exploit Process (engineering) Computer science 02 engineering and technology computer.software_genre Semantic network Related work 020204 information systems 0202 electrical engineering electronic engineering information engineering Nat-ural Language Processing Computer Science - Computation and Language business.industry 4. Education capturing semantic infor-mation Computer Science::Computation and Language (Computational Linguistics and Natural Language and Speech Processing) Variety (linguistics) SemEval Embedding 020201 artificial intelligence & image processing Artificial intelligence business computer Computation and Language (cs.CL) Natural language processing Word (computer architecture) Vector space |
| Zdroj: | Proceedings of the 21st Conference on Computational Natural Language Learning (CoNLL 2017) CoNLL |
| DOI: | 10.48550/arxiv.1612.02703 |
| Popis: | 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. Comment: Accepted in CoNLL 2017. 12 pages |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|