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 |
Year | Venue | DocType |
---|---|---|
2022 | International Conference on Computational Linguistics | Conference |
Volume | Citations | PageRank |
Proceedings of the 29th International Conference on Computational Linguistics | 0 | 0.34 |
References | Authors | |
0 | 11 |
Name | Order | Citations | PageRank |
---|---|---|---|
Elsbeth Turcan | 1 | 0 | 0.34 |
David Wan | 2 | 0 | 1.35 |
Faisal Ladhak | 3 | 5 | 2.76 |
Petra Galuscakova | 4 | 0 | 0.34 |
Sukanta Sen | 5 | 0 | 0.68 |
Svetlana Tchistiakova | 6 | 0 | 1.35 |
Weijia Xu | 7 | 0 | 5.75 |
Marine Carpuat | 8 | 13 | 3.31 |
Kenneth Heafield | 9 | 579 | 39.46 |
Douglas W. Oard | 10 | 2484 | 246.11 |
Kathleen R. McKeown | 11 | 4990 | 741.29 |