Papers › Dynamic Coattention Networks For Question Answering

Dynamic Coattention Networks For Question Answering

5 Nov 2016arXiv:1611.01604archive 2025-07-28

Caiming Xiong, Victor Zhong, Richard Socher

Several deep learning models have been proposed for question answering. However, due to their single-pass nature, they have no way to recover from local maxima corresponding to incorrect answers. To address this problem, we introduce the Dynamic Coattention Network (DCN) for question answering. The DCN first fuses co-dependent representations of the question and the document in order to focus on relevant parts of both. Then a dynamic pointing decoder iterates over potential answer spans. This iterative procedure enables the model to recover from initial local maxima corresponding to incorrect answers. On the Stanford question answering dataset, a single DCN model improves the previous state of the art from 71.0% F1 to 75.9%, while a DCN ensemble obtains 80.4% F1.

PaperPDFCode

In Syntology View this paper on Syntology, its page in Syntology's graph. That page lists the repositories linked to the paper, the abstract and the calls for agents.

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

For agents, on Syntology's MCP service (how to connect):

Code

BAJUKA/SQuAD-NLP mentioned on GitHubtfSyntology: not harvested report
Lou1sM/AML-Project mentioned on GitHubtfSyntology: not harvested report
Lou1sM/AdvancedML-Project-Dynamic-Coattention-Networks mentioned on GitHubtfSyntology: not harvested report
andreiilie1/dynamic_coattention_networks mentioned on GitHubtfSyntology: not harvested report
lmn-extracts/dcn_plus mentioned on GitHubtfSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Bidirectional Attention Flow for Machine Comprehension (arXiv:1611.01603; that paper's own run record: 9 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 1 honoured, 2 violated, 1 with no contract checked; 5 where Syntology's instrument failed) · 2 unverified); nothing checks that they implement this paper's method. report
wasimusu/MachineRC mentioned on GitHubpytorchSyntology: not harvested 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.

A paper named beside a repository with no sample linked to this paper is shown with that paper's own run record, not this paper's: “ran” means executed on a synthesized input, not that the code is correct, and “where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code. Papers are listed in arXiv-id order, at most three per repository.

Code Syntology ran Syntology

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

Tasks

DecoderQuestion Answering

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Open-Domain Question Answering SQuAD1.1 DCN EM 66.2 #2 of 3 Archive leaderboard report
Question Answering SQuAD1.1 Dynamic Coattention Networks (ensemble) EM 71.625 #148 of 213 Archive leaderboard report
Question Answering SQuAD1.1 Dynamic Coattention Networks (ensemble) F1 80.383 #148 of 213 Archive leaderboard report
Question Answering SQuAD1.1 Dynamic Coattention Networks (single model) EM 66.233 #178 of 213 Archive leaderboard report
Question Answering SQuAD1.1 Dynamic Coattention Networks (single model) F1 75.896 #178 of 213 Archive leaderboard report
Question Answering SQuAD1.1 dev DCN EM 65.4 #45 of 55 Archive leaderboard report
Question Answering SQuAD1.1 dev DCN F1 75.6 #45 of 55 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