Abstract
In this paper, we propose a method of calibrating a word embedding, so that the semantic it conveys becomes more relevant to the context. Our method is novel because the output shows clearly which senses that were originally presented in a target word embedding become stronger or weaker. This is possible by utilizing the technique of using sparse coding to recover senses that comprises a word embedding.- Anthology ID:
- W18-5442
- Volume:
- Proceedings of the 2018 EMNLP Workshop BlackboxNLP: Analyzing and Interpreting Neural Networks for NLP
- Month:
- November
- Year:
- 2018
- Address:
- Brussels, Belgium
- Editors:
- Tal Linzen, Grzegorz Chrupała, Afra Alishahi
- Venue:
- EMNLP
- SIG:
- Publisher:
- Association for Computational Linguistics
- Note:
- Pages:
- 341–343
- Language:
- URL:
- https://aclanthology.org/W18-5442
- DOI:
- 10.18653/v1/W18-5442
- Cite (ACL):
- Kyoung-Rok Jang, Sung-Hyon Myaeng, and Sang-Bum Kim. 2018. Interpretable Word Embedding Contextualization. In Proceedings of the 2018 EMNLP Workshop BlackboxNLP: Analyzing and Interpreting Neural Networks for NLP, pages 341–343, Brussels, Belgium. Association for Computational Linguistics.
- Cite (Informal):
- Interpretable Word Embedding Contextualization (Jang et al., EMNLP 2018)
- PDF:
- https://preview.aclanthology.org/nschneid-patch-4/W18-5442.pdf