Abstract
In traditional Distributional Semantic Models (DSMs) the multiple senses of a polysemous word are conflated into a single vector space representation. In this work, we propose a DSM that learns multiple distributional representations of a word based on different topics. First, a separate DSM is trained for each topic and then each of the topic-based DSMs is aligned to a common vector space. Our unsupervised mapping approach is motivated by the hypothesis that words preserving their relative distances in different topic semantic sub-spaces constitute robust semantic anchors that define the mappings between them. Aligned cross-topic representations achieve state-of-the-art results for the task of contextual word similarity. Furthermore, evaluation on NLP downstream tasks shows that multiple topic-based embeddings outperform single-prototype models.- Anthology ID:
- N19-1110
- Volume:
- Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long and Short Papers)
- Month:
- June
- Year:
- 2019
- Address:
- Minneapolis, Minnesota
- Editors:
- Jill Burstein, Christy Doran, Thamar Solorio
- Venue:
- NAACL
- SIG:
- Publisher:
- Association for Computational Linguistics
- Note:
- Pages:
- 1052–1061
- Language:
- URL:
- https://aclanthology.org/N19-1110
- DOI:
- 10.18653/v1/N19-1110
- Cite (ACL):
- Eleftheria Briakou, Nikos Athanasiou, and Alexandros Potamianos. 2019. Cross-Topic Distributional Semantic Representations Via Unsupervised Mappings. In Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long and Short Papers), pages 1052–1061, Minneapolis, Minnesota. Association for Computational Linguistics.
- Cite (Informal):
- Cross-Topic Distributional Semantic Representations Via Unsupervised Mappings (Briakou et al., NAACL 2019)
- PDF:
- https://preview.aclanthology.org/landing_page/N19-1110.pdf