Explicit retrofitting of distributional word vectors
View / Open Files
Authors
Glavaš, G
Vulić, I
Publication Date
2018Journal Title
ACL 2018 - 56th Annual Meeting of the Association for Computational Linguistics, Proceedings of the Conference (Long Papers)
Conference Name
Proceedings of the 56th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)
ISBN
9781948087322
Publisher
Association for Computational Linguistics
Volume
1
Pages
34-45
Type
Conference Object
Metadata
Show full item recordCitation
Glavaš, G., & Vulić, I. (2018). Explicit retrofitting of distributional word vectors. ACL 2018 - 56th Annual Meeting of the Association for Computational Linguistics, Proceedings of the Conference (Long Papers), 1 34-45. https://doi.org/10.18653/v1/p18-1004
Abstract
Semantic specialization of distributional word vectors, referred to as retrofitting, is a process of fine-tuning word vectors using external lexical knowledge in order to better embed some semantic relation. Existing retrofitting models integrate linguistic constraints directly into learning objectives and, consequently, specialize only the vectors of words from the constraints. In this work, in contrast, we transform external lexico-semantic relations into training examples which we use to learn an explicit retrofitting model (ER). The ER model allows us to learn a global specialization function and specialize the vectors of words unobserved in the training data as well. We report large gains over original distributional vector spaces in (1) intrinsic word similarity evaluation and on (2) two downstream tasks -- lexical simplification and dialog state tracking. Finally, we also successfully specialize vector spaces of new languages (i.e., unseen in the training data) by coupling ER with shared multilingual distributional vector spaces.
Sponsorship
European Research Council (648909)
Identifiers
External DOI: https://doi.org/10.18653/v1/p18-1004
This record's URL: https://www.repository.cam.ac.uk/handle/1810/285039
Rights
Licence:
http://www.rioxx.net/licenses/all-rights-reserved
Statistics
Total file downloads (since January 2020). For more information on metrics see the
IRUS guide.