Papers › Answering while Summarizing: Multi-task Learning for Multi-hop QA with Evidence Extraction

Answering while Summarizing: Multi-task Learning for Multi-hop QA with Evidence Extraction

21 May 2019ACL 2019 7arXiv:1905.08511archive 2025-07-28

Kosuke Nishida, Kyosuke Nishida, Masaaki Nagata, Atsushi Otsuka, Itsumi Saito, Hisako Asano, Junji Tomita

Question answering (QA) using textual sources for purposes such as reading comprehension (RC) has attracted much attention. This study focuses on the task of explainable multi-hop QA, which requires the system to return the answer with evidence sentences by reasoning and gathering disjoint pieces of the reference texts. It proposes the Query Focused Extractor (QFE) model for evidence extraction and uses multi-task learning with the QA model. QFE is inspired by extractive summarization models; compared with the existing method, which extracts each evidence sentence independently, it sequentially extracts evidence sentences by using an RNN with an attention mechanism on the question sentence. It enables QFE to consider the dependency among the evidence sentences and cover important information in the question sentence. Experimental results show that QFE with a simple RC baseline model achieves a state-of-the-art evidence extraction score on HotpotQA. Although designed for RC, it also achieves a state-of-the-art evidence extraction score on FEVER, which is a recognizing textual entailment task on a large textual database.

PaperPDFConference PDF

In Syntology Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.

Code

No code repository is listed for this paper in the archive or in Syntology's graph.

Code Syntology ran Syntology

Not run by Syntology. Nothing on this page verifies that the listed code works.

Tasks

Answer SelectionExtractive SummarizationMulti-Task LearningNatural Language InferenceQuestion AnsweringReading ComprehensionSentence

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Question Answering HotpotQA QFE ANS-EM 0.287 #61 of 72 Archive leaderboard report
Question Answering HotpotQA QFE ANS-F1 0.381 #61 of 72 Archive leaderboard report
Question Answering HotpotQA QFE JOINT-EM 0.087 #61 of 72 Archive leaderboard report
Question Answering HotpotQA QFE JOINT-F1 0.231 #61 of 72 Archive leaderboard report
Question Answering HotpotQA QFE SUP-EM 0.142 #61 of 72 Archive leaderboard report
Question Answering HotpotQA QFE SUP-F1 0.444 #61 of 72 Archive leaderboard report

Ranks are positions in the archive's leaderboards as they stood at the 2025-07-28 snapshot. Results published since then are not among these rows, so a rank here is not a current standing.

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections