Papers › A Question-Focused Multi-Factor Attention Network for Question Answering

A Question-Focused Multi-Factor Attention Network for Question Answering

25 Jan 2018arXiv:1801.08290archive 2025-07-28

Souvik Kundu, Hwee Tou Ng

Neural network models recently proposed for question answering (QA) primarily focus on capturing the passage-question relation. However, they have minimal capability to link relevant facts distributed across multiple sentences which is crucial in achieving deeper understanding, such as performing multi-sentence reasoning, co-reference resolution, etc. They also do not explicitly focus on the question and answer type which often plays a critical role in QA. In this paper, we propose a novel end-to-end question-focused multi-factor attention network for answer extraction. Multi-factor attentive encoding using tensor-based transformation aggregates meaningful facts even when they are located in multiple sentences. To implicitly infer the answer type, we also propose a max-attentional question aggregation mechanism to encode a question vector based on the important words in a question. During prediction, we incorporate sequence-level encoding of the first wh-word and its immediately following word as an additional source of question type information. Our proposed model achieves significant improvements over the best prior state-of-the-art results on three large-scale challenging QA datasets, namely NewsQA, TriviaQA, and SearchQA.

PaperPDFCode

Code

nusnlp/amanda officialmentioned on GitHub report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

Code Syntology ran Syntology

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

Tasks

Open-Domain Question AnsweringQuestion AnsweringReading ComprehensionSentenceTriviaQA

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Open-Domain Question Answering SearchQA AMANDA EM - #11 of 14 Archive leaderboard report
Open-Domain Question Answering SearchQA AMANDA F1 - #11 of 14 Archive leaderboard report
Open-Domain Question Answering SearchQA AMANDA N-gram F1 56.6 #11 of 14 Archive leaderboard report
Open-Domain Question Answering SearchQA AMANDA Unigram Acc 46.8 #11 of 14 Archive leaderboard report
Question Answering NewsQA AMANDA EM 48.4 #14 of 18 Archive leaderboard report
Question Answering NewsQA AMANDA F1 63.7 #14 of 18 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