Lightweight Cross-Lingual Sentence Representation Learning
Zhuoyuan Mao, Prakhar Gupta, Chenhui Chu, Martin Jaggi, Sadao Kurohashi
Abstract
Large-scale models for learning fixed-dimensional cross-lingual sentence representations like LASER (Artetxe and Schwenk, 2019b) lead to significant improvement in performance on downstream tasks. However, further increases and modifications based on such large-scale models are usually impractical due to memory limitations. In this work, we introduce a lightweight dual-transformer architecture with just 2 layers for generating memory-efficient cross-lingual sentence representations. We explore different training tasks and observe that current cross-lingual training tasks leave a lot to be desired for this shallow architecture. To ameliorate this, we propose a novel cross-lingual language model, which combines the existing single-word masked language model with the newly proposed cross-lingual token-level reconstruction task. We further augment the training task by the introduction of two computationally-lite sentence-level contrastive learning tasks to enhance the alignment of cross-lingual sentence representation space, which compensates for the learning bottleneck of the lightweight transformer for generative tasks. Our comparisons with competing models on cross-lingual sentence retrieval and multilingual document classification confirm the effectiveness of the newly proposed training tasks for a shallow model.- Anthology ID:
- 2021.acl-long.226
- 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:
- 2902–2913
- Language:
- URL:
- https://aclanthology.org/2021.acl-long.226
- DOI:
- 10.18653/v1/2021.acl-long.226
- Cite (ACL):
- Zhuoyuan Mao, Prakhar Gupta, Chenhui Chu, Martin Jaggi, and Sadao Kurohashi. 2021. Lightweight Cross-Lingual Sentence Representation 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 2902–2913, Online. Association for Computational Linguistics.
- Cite (Informal):
- Lightweight Cross-Lingual Sentence Representation Learning (Mao et al., ACL-IJCNLP 2021)
- PDF:
- https://preview.aclanthology.org/ingest-acl-2023-videos/2021.acl-long.226.pdf
- Code
- Mao-KU/lightweight-crosslingual-sent2vec
- Data
- MLDoc, ParaCrawl