Exploring Vector Spaces for Semantic Relations
| Autor: | Isabelle Tellier, Kata Gábor, Thierry Charnois, Davide Buscaldi, Haïfa Zargayouna |
|---|---|
| Rok vydání: | 2017 |
| Předmět: |
Computer science
business.industry Cosine similarity Computer Science::Computation and Language (Computational Linguistics and Natural Language and Speech Processing) 02 engineering and technology Variety (linguistics) computer.software_genre Measure (mathematics) SemEval Relation classification 020204 information systems 0202 electrical engineering electronic engineering information engineering 020201 artificial intelligence & image processing Word2vec Artificial intelligence business computer Word (computer architecture) Natural language processing Vector space |
| Zdroj: | EMNLP |
| DOI: | 10.18653/v1/d17-1193 |
| Popis: | Word embeddings are used with success for a variety of tasks involving lexical semantic similarities between individual words. Using unsupervised methods and just cosine similarity, encouraging results were obtained for analogical similarities. In this paper, we explore the potential of pre-trained word embeddings to identify generic types of semantic relations in an unsupervised experiment. We propose a new relational similarity measure based on the combination of word2vec’s CBOW input and output vectors which outperforms concurrent vector representations, when used for unsupervised clustering on SemEval 2010 Relation Classification data. |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|