Language-Independent Representations Improve Zero-Shot Summarization

Vladimir Solovyev, Danni Liu, Jan Niehues


Abstract
Finetuning pretrained models on downstream generation tasks often leads to catastrophic forgetting in zero-shot conditions. In this work, we focus on summarization and tackle the problem through the lens of language-independent representations. After training on monolingual summarization, we perform zero-shot transfer to new languages or language pairs. We first show naively finetuned models are highly language-specific in both output behavior and internal representations, resulting in poor zero-shot performance. Next, we propose query-key (QK) finetuning to decouple task-specific knowledge from the pretrained language generation abilities. Then, after showing downsides of the standard adversarial language classifier, we propose a balanced variant that more directly enforces language-agnostic representations. Moreover, our qualitative analyses show removing source language identity correlates to zero-shot summarization performance. Our code is openly available.
Anthology ID:
2024.naacl-short.68
Volume:
Proceedings of the 2024 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (Volume 2: Short Papers)
Month:
June
Year:
2024
Address:
Mexico City, Mexico
Editors:
Kevin Duh, Helena Gomez, Steven Bethard
Venue:
NAACL
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
772–782
Language:
URL:
https://aclanthology.org/2024.naacl-short.68
DOI:
10.18653/v1/2024.naacl-short.68
Bibkey:
Cite (ACL):
Vladimir Solovyev, Danni Liu, and Jan Niehues. 2024. Language-Independent Representations Improve Zero-Shot Summarization. In Proceedings of the 2024 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (Volume 2: Short Papers), pages 772–782, Mexico City, Mexico. Association for Computational Linguistics.
Cite (Informal):
Language-Independent Representations Improve Zero-Shot Summarization (Solovyev et al., NAACL 2024)
Copy Citation:
PDF:
https://aclanthology.org/2024.naacl-short.68.pdf