Constrained Regeneration for Cross-Lingual Query-Focused Extractive Summarization

Elsbeth Turcan, David Wan, Faisal Ladhak, Petra Galuscakova, Sukanta Sen, Svetlana Tchistiakova, Weijia Xu, Marine Carpuat, Kenneth Heafield, Douglas Oard, Kathleen McKeown


Abstract
Query-focused summaries of foreign-language, retrieved documents can help a user understand whether a document is actually relevant to the query term. A standard approach to this problem is to first translate the source documents and then perform extractive summarization to find relevant snippets. However, in a cross-lingual setting, the query term does not necessarily appear in the translations of relevant documents. In this work, we show that constrained machine translation and constrained post-editing can improve human relevance judgments by including a query term in a summary when its translation appears in the source document. We also present several strategies for selecting only certain documents for regeneration which yield further improvements
Anthology ID:
2022.coling-1.236
Volume:
Proceedings of the 29th International Conference on Computational Linguistics
Month:
October
Year:
2022
Address:
Gyeongju, Republic of Korea
Venue:
COLING
SIG:
Publisher:
International Committee on Computational Linguistics
Note:
Pages:
2668–2680
Language:
URL:
https://aclanthology.org/2022.coling-1.236
DOI:
Bibkey:
Cite (ACL):
Elsbeth Turcan, David Wan, Faisal Ladhak, Petra Galuscakova, Sukanta Sen, Svetlana Tchistiakova, Weijia Xu, Marine Carpuat, Kenneth Heafield, Douglas Oard, and Kathleen McKeown. 2022. Constrained Regeneration for Cross-Lingual Query-Focused Extractive Summarization. In Proceedings of the 29th International Conference on Computational Linguistics, pages 2668–2680, Gyeongju, Republic of Korea. International Committee on Computational Linguistics.
Cite (Informal):
Constrained Regeneration for Cross-Lingual Query-Focused Extractive Summarization (Turcan et al., COLING 2022)
Copy Citation:
PDF:
https://aclanthology.org/2022.coling-1.236.pdf