Papers › MASS: Masked Sequence to Sequence Pre-training for Language Generation

MASS: Masked Sequence to Sequence Pre-training for Language Generation

7 May 2019arXiv:1905.02450archive 2025-07-28

Kaitao Song, Xu Tan, Tao Qin, Jianfeng Lu, Tie-Yan Liu

Pre-training and fine-tuning, e.g., BERT, have achieved great success in language understanding by transferring knowledge from rich-resource pre-training task to the low/zero-resource downstream tasks. Inspired by the success of BERT, we propose MAsked Sequence to Sequence pre-training (MASS) for the encoder-decoder based language generation tasks. MASS adopts the encoder-decoder framework to reconstruct a sentence fragment given the remaining part of the sentence: its encoder takes a sentence with randomly masked fragment (several consecutive tokens) as input, and its decoder tries to predict this masked fragment. In this way, MASS can jointly train the encoder and decoder to develop the capability of representation extraction and language modeling. By further fine-tuning on a variety of zero/low-resource language generation tasks, including neural machine translation, text summarization and conversational response generation (3 tasks and totally 8 datasets), MASS achieves significant improvements over the baselines without pre-training or with other pre-training methods. Specially, we achieve the state-of-the-art accuracy (37.5 in terms of BLEU score) on the unsupervised English-French translation, even beating the early attention-based supervised model.

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

microsoft/MASS officialmentioned in papermentioned on GitHubpytorchNOASSERTIONSyntology: not harvested report
jiaruncao/BioCopyMechanism mentioned on GitHubSyntology: not harvested report
michael-wzhu/mpnet_zh mentioned on GitHubpytorchMITSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to MPNet: Masked and Permuted Pre-training for Language Understanding (arXiv:2004.09297; that paper's own run record: 8 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 1 honoured, 0 violated, 4 with no contract checked; 3 where Syntology's instrument failed) · 0 unverified); nothing checks that they implement this paper's method. report
microsoft/MPNet mentioned on GitHubpytorchSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to MPNet: Masked and Permuted Pre-training for Language Understanding (arXiv:2004.09297; that paper's own run record: 8 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 1 honoured, 0 violated, 4 with no contract checked; 3 where Syntology's instrument failed) · 0 unverified); nothing checks that they implement this paper's method. report
MindSpore-paper-code-3/code9 mindsporeSyntology: not harvested report
cui0523/Code6 mindsporeSyntology: not harvested report
mindspore-ai/models mindsporeSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to AdaBin: Improving Binary Neural Networks with Adaptive Binary Sets (arXiv:2208.08084; that paper's own run record: 4 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 0 violated, 4 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified); nothing checks that they implement this paper's method. 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

Conversational Response GenerationDecoderLanguage ModelingMachine TranslationResponse GenerationSentenceText GenerationText SummarizationTranslationUnsupervised Machine Translation

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Text Summarization GigaWord MASS ROUGE-1 38.73 #20 of 41 Archive leaderboard report
Text Summarization GigaWord MASS ROUGE-2 19.71 #20 of 41 Archive leaderboard report
Text Summarization GigaWord MASS ROUGE-L 35.96 #20 of 41 Archive leaderboard report
Unsupervised Machine Translation WMT2014 English-French MASS (6-layer Transformer) BLEU 37.5 #2 of 7 Archive leaderboard report
Unsupervised Machine Translation WMT2014 French-English MASS (6-layer Transformer) BLEU 34.9 #2 of 7 Archive leaderboard report
Unsupervised Machine Translation WMT2016 English-German MASS (6-layer Transformer) BLEU 28.3 #2 of 7 Archive leaderboard report
Unsupervised Machine Translation WMT2016 English-Romanian MASS (6-layer Transformer) BLEU 35.2 #3 of 3 Archive leaderboard report
Unsupervised Machine Translation WMT2016 German-English MASS (6-layer Transformer) BLEU 35.2 #2 of 7 Archive leaderboard report
Unsupervised Machine Translation WMT2016 Romanian-English MASS (6-layer Transformer) BLEU 33.1 #2 of 3 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

AdamAttentionAttention DropoutBERTDense ConnectionsDropoutLayer NormalizationLinear LayerLinear Warmup With Linear DecayMulti-Head AttentionResidual ConnectionSoftmaxWeight DecayWordPiece

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