Abstract
We present the Supervised Directional Similarity Network, a novel neural architecture for learning task-specific transformation functions on top of general-purpose word embeddings. Relying on only a limited amount of supervision from task-specific scores on a subset of the vocabulary, our architecture is able to generalise and transform a general-purpose distributional vector space to model the relation of lexical entailment. Experiments show excellent performance on scoring graded lexical entailment, raising the state-of-the-art on the HyperLex dataset by approximately 25%.- Anthology ID:
- P18-2101
- Volume:
- Proceedings of the 56th Annual Meeting of the Association for Computational Linguistics (Volume 2: Short Papers)
- Month:
- July
- Year:
- 2018
- Address:
- Melbourne, Australia
- Venue:
- ACL
- SIG:
- Publisher:
- Association for Computational Linguistics
- Note:
- Pages:
- 638–643
- Language:
- URL:
- https://aclanthology.org/P18-2101
- DOI:
- 10.18653/v1/P18-2101
- Cite (ACL):
- Marek Rei, Daniela Gerz, and Ivan Vulić. 2018. Scoring Lexical Entailment with a Supervised Directional Similarity Network. In Proceedings of the 56th Annual Meeting of the Association for Computational Linguistics (Volume 2: Short Papers), pages 638–643, Melbourne, Australia. Association for Computational Linguistics.
- Cite (Informal):
- Scoring Lexical Entailment with a Supervised Directional Similarity Network (Rei et al., ACL 2018)
- PDF:
- https://preview.aclanthology.org/nodalida-main-page/P18-2101.pdf
- Data
- HyperLex