Abstract
Learning word embeddings on large unlabeled corpus has been shown to be successful in improving many natural language tasks. The most efficient and popular approaches learn or retrofit such representations using additional external data. Resulting embeddings are generally better than their corpus-only counterparts, although such resources cover a fraction of words in the vocabulary. In this paper, we propose a new approach, Dict2vec, based on one of the largest yet refined datasource for describing words – natural language dictionaries. Dict2vec builds new word pairs from dictionary entries so that semantically-related words are moved closer, and negative sampling filters out pairs whose words are unrelated in dictionaries. We evaluate the word representations obtained using Dict2vec on eleven datasets for the word similarity task and on four datasets for a text classification task.- Anthology ID:
- D17-1024
- Volume:
- Proceedings of the 2017 Conference on Empirical Methods in Natural Language Processing
- Month:
- September
- Year:
- 2017
- Address:
- Copenhagen, Denmark
- Venue:
- EMNLP
- SIG:
- SIGDAT
- Publisher:
- Association for Computational Linguistics
- Note:
- Pages:
- 254–263
- Language:
- URL:
- https://aclanthology.org/D17-1024
- DOI:
- 10.18653/v1/D17-1024
- Cite (ACL):
- Julien Tissier, Christophe Gravier, and Amaury Habrard. 2017. Dict2vec : Learning Word Embeddings using Lexical Dictionaries. In Proceedings of the 2017 Conference on Empirical Methods in Natural Language Processing, pages 254–263, Copenhagen, Denmark. Association for Computational Linguistics.
- Cite (Informal):
- Dict2vec : Learning Word Embeddings using Lexical Dictionaries (Tissier et al., EMNLP 2017)
- PDF:
- https://preview.aclanthology.org/starsem-semeval-split/D17-1024.pdf
- Code
- tca19/dict2vec
- Data
- DBpedia