A Robust Abstractive System for Cross-Lingual Summarization

Jessica Ouyang, Boya Song, Kathy McKeown


Abstract
We present a robust neural abstractive summarization system for cross-lingual summarization. We construct summarization corpora for documents automatically translated from three low-resource languages, Somali, Swahili, and Tagalog, using machine translation and the New York Times summarization corpus. We train three language-specific abstractive summarizers and evaluate on documents originally written in the source languages, as well as on a fourth, unseen language: Arabic. Our systems achieve significantly higher fluency than a standard copy-attention summarizer on automatically translated input documents, as well as comparable content selection.
Anthology ID:
N19-1204
Volume:
Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long and Short Papers)
Month:
June
Year:
2019
Address:
Minneapolis, Minnesota
Editors:
Jill Burstein, Christy Doran, Thamar Solorio
Venue:
NAACL
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
2025–2031
Language:
URL:
https://aclanthology.org/N19-1204
DOI:
10.18653/v1/N19-1204
Bibkey:
Cite (ACL):
Jessica Ouyang, Boya Song, and Kathy McKeown. 2019. A Robust Abstractive System for Cross-Lingual Summarization. In Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long and Short Papers), pages 2025–2031, Minneapolis, Minnesota. Association for Computational Linguistics.
Cite (Informal):
A Robust Abstractive System for Cross-Lingual Summarization (Ouyang et al., NAACL 2019)
Copy Citation:
PDF:
https://aclanthology.org/N19-1204.pdf
Video:
 https://vimeo.com/356048544
Data
New York Times Annotated Corpus