Overcoming Catastrophic Forgetting in Zero-Shot Cross-Lingual Generation

Tu Vu, Aditya Barua, Brian Lester, Daniel Cer, Mohit Iyyer, Noah Constant


Abstract
In this paper, we explore the challenging problem of performing a generative task in a target language when labeled data is only available in English, using summarization as a case study. We assume a strict setting with no access to parallel data or machine translation and find that common transfer learning approaches struggle in this setting, as a generative multilingual model fine-tuned purely on English catastrophically forgets how to generate non-English. Given the recent rise of parameter-efficient adaptation techniques, we conduct the first investigation into how one such method, prompt tuning (Lester et al., 2021), can overcome catastrophic forgetting to enable zero-shot cross-lingual generation. Our experiments show that parameter-efficient prompt tuning provides gains over standard fine-tuning when transferring between less-related languages, e.g., from English to Thai. However, a significant gap still remains between these methods and fully-supervised baselines. To improve cross-lingual transfer further, we explore several approaches, including: (1) mixing in unlabeled multilingual data, and (2) explicitly factoring prompts into recombinable language and task components. Our approaches can provide further quality gains, suggesting that robust zero-shot cross-lingual generation is within reach.
Anthology ID:
2022.emnlp-main.630
Volume:
Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing
Month:
December
Year:
2022
Address:
Abu Dhabi, United Arab Emirates
Venue:
EMNLP
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
9279–9300
Language:
URL:
https://aclanthology.org/2022.emnlp-main.630
DOI:
Bibkey:
Cite (ACL):
Tu Vu, Aditya Barua, Brian Lester, Daniel Cer, Mohit Iyyer, and Noah Constant. 2022. Overcoming Catastrophic Forgetting in Zero-Shot Cross-Lingual Generation. In Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing, pages 9279–9300, Abu Dhabi, United Arab Emirates. Association for Computational Linguistics.
Cite (Informal):
Overcoming Catastrophic Forgetting in Zero-Shot Cross-Lingual Generation (Vu et al., EMNLP 2022)
Copy Citation:
PDF:
https://preview.aclanthology.org/nodalida-main-page/2022.emnlp-main.630.pdf