Papers › Mask Attention Networks: Rethinking and Strengthen Transformer

Mask Attention Networks: Rethinking and Strengthen Transformer

25 Mar 2021NAACL 2021 4arXiv:2103.13597archive 2025-07-28

Zhihao Fan, Yeyun Gong, Dayiheng Liu, Zhongyu Wei, Siyuan Wang, Jian Jiao, Nan Duan, Ruofei Zhang, Xuanjing Huang

Transformer is an attention-based neural network, which consists of two sublayers, namely, Self-Attention Network (SAN) and Feed-Forward Network (FFN). Existing research explores to enhance the two sublayers separately to improve the capability of Transformer for text representation. In this paper, we present a novel understanding of SAN and FFN as Mask Attention Networks (MANs) and show that they are two special cases of MANs with static mask matrices. However, their static mask matrices limit the capability for localness modeling in text representation learning. We therefore introduce a new layer named dynamic mask attention network (DMAN) with a learnable mask matrix which is able to model localness adaptively. To incorporate advantages of DMAN, SAN, and FFN, we propose a sequential layered structure to combine the three types of layers. Extensive experiments on various tasks, including neural machine translation and text summarization demonstrate that our model outperforms the original Transformer.

PaperPDFConference PDFCodeCode Syntology ran

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

For agents, Syntology's MCP tool lists every function and class Syntology harvested from this paper and whether it ran (how to connect): get_harvested_code_for_paper(arxiv_id="2103.13597")

Code

Syntology Ran 0 of 3 code samples harvested from 2 repositories linked to this paper; 3 have no recorded run.

By repository: community (archive-listed): 1 sample from 1 repository, 0 ran; found in paper text by Syntology: 2 samples from 1 repository, 0 ran. The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.

libertfan/man mentioned on GitHubpytorch 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

3 samples harvested; 0 ran; 0 honoured the contract we drafted; 3 have no recorded run. Read from Syntology's graph 2026-09-24; that is when this build read the record, not when the samples ran.

3unverified

Licence: 0 of the 3 samples are pointer only, meaning Syntology does not serve that copy's text. This page shows no code text for any sample; each one links to its file in the repository.

Harvested from 2 repositories linked to this paper, official or community; each sample names its own and says which. “Ran” means the sample executed on a synthesized input. It does not mean the output is correct, and nothing here reproduces the paper's results. “Honoured” and “violated” refer to a contract Syntology drafted from the code itself; “our draft was wrong” and “fixture could not drive it” are failures of Syntology's instrument, not of the code.

Each sample ends with its code_sha256, Syntology's identity for that exact code. An agent fetches the stored sample with Syntology's MCP tool get_code(code_sha256="…") (how to connect); click an identity to copy that call.

Repository labels, per sample. official repository: The archive marks this repository official for the paper. named in the paper: The archive records that the paper mentions this repository; it is not marked official. community (archive-listed): In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper. found in paper text by Syntology: Syntology found this repository in the paper's own text; whether it is the authors' implementation is not asserted. community: Not in the archive's code links for this paper; a community repository Syntology harvested. Samples from a repository marked official are listed first. Licence labels name the repository's licence as recorded at harvest. “Pointer only” means Syntology does not serve that copy's text, for one of four reasons: no licence file was found; the licence was not identified; the licence is recorded as permissive but that copy's record is not marked cleared; or the licence is outside the permissive list Syntology serves text under (MIT, Apache-2.0, BSD and similar). Some licences outside that list permit redistribution, such as WTFPL, and GPL-3.0 under its conditions; they are simply not on the list. Hover a licence label for the reason. File links open the file on GitHub at the default branch, which may have changed since the harvest.

MANEncoderLayer libertfan/man/summarization/model/man.py community (archive-listed) unverified MIT (permissive) · 150f87cfae2bfdf2 · report
line_count pltrdy/files2rouge/files2rouge/utils.py found in paper text by Syntology unverified MIT (permissive) · c5a79ceafeff9d5e · report
split_files pltrdy/files2rouge/files2rouge/utils.py found in paper text by Syntology unverified MIT (permissive) · 1d25cd789e57612f · report

Tasks

Abstractive Text SummarizationMachine TranslationRepresentation LearningText SummarizationTranslation

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Abstractive Text Summarization CNN / Daily Mail Mask Attention Network ROUGE-1 40.98 #36 of 53 Archive leaderboard report
Abstractive Text Summarization CNN / Daily Mail Mask Attention Network ROUGE-2 18.29 #36 of 53 Archive leaderboard report
Abstractive Text Summarization CNN / Daily Mail Mask Attention Network ROUGE-L 37.88 #36 of 53 Archive leaderboard report
Machine Translation IWSLT2014 German-English Mask Attention Network (small) BLEU score 36.3 #15 of 34 Archive leaderboard report
Machine Translation IWSLT2014 German-English Mask Attention Network (small) Number of Params 37M #15 of 34 Archive leaderboard report
Machine Translation WMT2014 English-German Mask Attention Network (big) BLEU score 30.4 #11 of 91 Archive leaderboard report
Machine Translation WMT2014 English-German Mask Attention Network (big) Number of Params 215M #11 of 91 Archive leaderboard report
Machine Translation WMT2014 English-German Mask Attention Network (base) BLEU score 29.1 #32 of 91 Archive leaderboard report
Machine Translation WMT2014 English-German Mask Attention Network (base) Number of Params 63M #32 of 91 Archive leaderboard report
Text Summarization GigaWord Mask Attention Network ROUGE-1 38.28 #21 of 41 Archive leaderboard report
Text Summarization GigaWord Mask Attention Network ROUGE-2 19.46 #21 of 41 Archive leaderboard report
Text Summarization GigaWord Mask Attention Network ROUGE-L 35.46 #21 of 41 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.

Methods

Absolute Position EncodingsAdamAttentionBPEDense ConnectionsDropoutLabel SmoothingLayer NormalizationLinear LayerMulti-Head AttentionPosition-Wise Feed-Forward LayerResidual ConnectionSoftmaxTransformer

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