ACROSS: An Alignment-based Framework for Low-Resource Many-to-One Cross-Lingual Summarization

Peiyao Li, Zhengkun Zhang, Jun Wang, Liang Li, Adam Jatowt, Zhenglu Yang

Abstract
This research addresses the challenges of Cross-Lingual Summarization (CLS) in low-resource scenarios and over imbalanced multilingual data. Existing CLS studies mostly resort to pipeline frameworks or multi-task methods in bilingual settings. However, they ignore the data imbalance in multilingual scenarios and do not utilize the high-resource monolingual summarization data. In this paper, we propose the Aligned CROSs-lingual Summarization (ACROSS) model to tackle these issues. Our framework aligns low-resource cross-lingual data with high-resource monolingual data via contrastive and consistency loss, which help enrich low-resource information for high-quality summaries. In addition, we introduce a data augmentation method that can select informative monolingual sentences, which facilitates a deep exploration of high-resource information and introduce new information for low-resource languages. Experiments on the CrossSum dataset show that ACROSS outperforms baseline models and obtains consistently dominant performance on 45 language pairs.
Anthology ID:
2023.findings-acl.154
Volume:
Findings of the Association for Computational Linguistics: ACL 2023
Month:
July
Year:
2023
Address:
Toronto, Canada
Editors:
Anna Rogers, Jordan Boyd-Graber, Naoaki Okazaki
Venue:
Findings
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
2458–2472
Language:
URL:
https://aclanthology.org/2023.findings-acl.154
DOI:
10.18653/v1/2023.findings-acl.154
Bibkey:
Cite (ACL):
Peiyao Li, Zhengkun Zhang, Jun Wang, Liang Li, Adam Jatowt, and Zhenglu Yang. 2023. ACROSS: An Alignment-based Framework for Low-Resource Many-to-One Cross-Lingual Summarization. In Findings of the Association for Computational Linguistics: ACL 2023, pages 2458–2472, Toronto, Canada. Association for Computational Linguistics.
Cite (Informal):
ACROSS: An Alignment-based Framework for Low-Resource Many-to-One Cross-Lingual Summarization (Li et al., Findings 2023)
Copy Citation:
PDF:
https://preview.aclanthology.org/nschneid-patch-3/2023.findings-acl.154.pdf
PDF Search