Embedding Words and Senses Together via Joint Knowledge-Enhanced Training
arXiv:1612.02703
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.
arXiv commentAccepted in CoNLL 2017. 12 pages
References in corpus (5)
- Efficient Estimation of Word Representations in Vector Space
- Using Information Content to Evaluate Semantic Similarity in a Taxonomy
- AutoExtend: Extending Word Embeddings to Embeddings for Synsets and Lexemes
- Question Answering with Subgraph Embeddings
- Structured Training for Neural Network Transition-Based Parsing