UAlberta at SemEval-2020 Task 2: Using Translations to Predict Cross-Lingual Entailment
Bradley Hauer, Amir Ahmad Habibi, Yixing Luan, Arnob Mallik, Grzegorz Kondrak
Abstract
We investigate the hypothesis that translations can be used to identify cross-lingual lexical entailment. We propose novel methods that leverage parallel corpora, word embeddings, and multilingual lexical resources. Our results demonstrate that the implementation of these ideas leads to improvements in predicting entailment.- Anthology ID:
- 2020.semeval-1.32
- Volume:
- Proceedings of the Fourteenth Workshop on Semantic Evaluation
- Month:
- December
- Year:
- 2020
- Address:
- Barcelona (online)
- Venue:
- SemEval
- SIG:
- SIGLEX
- Publisher:
- International Committee for Computational Linguistics
- Note:
- Pages:
- 263–269
- Language:
- URL:
- https://aclanthology.org/2020.semeval-1.32
- DOI:
- 10.18653/v1/2020.semeval-1.32
- Cite (ACL):
- Bradley Hauer, Amir Ahmad Habibi, Yixing Luan, Arnob Mallik, and Grzegorz Kondrak. 2020. UAlberta at SemEval-2020 Task 2: Using Translations to Predict Cross-Lingual Entailment. In Proceedings of the Fourteenth Workshop on Semantic Evaluation, pages 263–269, Barcelona (online). International Committee for Computational Linguistics.
- Cite (Informal):
- UAlberta at SemEval-2020 Task 2: Using Translations to Predict Cross-Lingual Entailment (Hauer et al., SemEval 2020)
- PDF:
- https://preview.aclanthology.org/starsem-semeval-split/2020.semeval-1.32.pdf
- Data
- OpenSubtitles