Abstract
Cross-lingual language tasks typically require a substantial amount of annotated data or parallel translation data. We explore whether language representations that capture relationships among languages can be learned and subsequently leveraged in cross-lingual tasks without the use of parallel data. We generate dense embeddings for 29 languages using a denoising autoencoder, and evaluate the embeddings using the World Atlas of Language Structures (WALS) and two extrinsic tasks in a zero-shot setting: cross-lingual dependency parsing and cross-lingual natural language inference.- Anthology ID:
- 2021.acl-long.560
- Volume:
- Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing (Volume 1: Long Papers)
- Month:
- August
- Year:
- 2021
- Address:
- Online
- Editors:
- Chengqing Zong, Fei Xia, Wenjie Li, Roberto Navigli
- Venues:
- ACL | IJCNLP
- SIG:
- Publisher:
- Association for Computational Linguistics
- Note:
- Pages:
- 7210–7225
- Language:
- URL:
- https://aclanthology.org/2021.acl-long.560
- DOI:
- 10.18653/v1/2021.acl-long.560
- Cite (ACL):
- Dian Yu, Taiqi He, and Kenji Sagae. 2021. Language Embeddings for Typology and Cross-lingual Transfer Learning. In Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing (Volume 1: Long Papers), pages 7210–7225, Online. Association for Computational Linguistics.
- Cite (Informal):
- Language Embeddings for Typology and Cross-lingual Transfer Learning (Yu et al., ACL-IJCNLP 2021)
- PDF:
- https://preview.aclanthology.org/nschneid-patch-2/2021.acl-long.560.pdf
- Code
- DianDYu/language_embeddings
- Data
- XNLI