Abstract
In this paper, we introduce a method of identifying the components (i.e. dimensions) of word embeddings that strongly signifies properties of a word. By elucidating such properties hidden in word embeddings, we could make word embeddings more interpretable, and also could perform property-based meaning comparison. With the capability, we can answer questions like “To what degree a given word has the property cuteness?” or “In what perspective two words are similar?”. We verify our method by examining how the strength of property-signifying components correlates with the degree of prototypicality of a target word.- Anthology ID:
- W17-1911
- Volume:
- Proceedings of the 1st Workshop on Sense, Concept and Entity Representations and their Applications
- Month:
- April
- Year:
- 2017
- Address:
- Valencia, Spain
- Editors:
- Jose Camacho-Collados, Mohammad Taher Pilehvar
- Venue:
- SENSE
- SIG:
- Publisher:
- Association for Computational Linguistics
- Note:
- Pages:
- 91–95
- Language:
- URL:
- https://aclanthology.org/W17-1911
- DOI:
- 10.18653/v1/W17-1911
- Cite (ACL):
- Kyoung-Rok Jang and Sung-Hyon Myaeng. 2017. Elucidating Conceptual Properties from Word Embeddings. In Proceedings of the 1st Workshop on Sense, Concept and Entity Representations and their Applications, pages 91–95, Valencia, Spain. Association for Computational Linguistics.
- Cite (Informal):
- Elucidating Conceptual Properties from Word Embeddings (Jang & Myaeng, SENSE 2017)
- PDF:
- https://preview.aclanthology.org/improve-issue-templates/W17-1911.pdf
- Data
- HyperLex