Papers › Fast Abstractive Summarization with Reinforce-Selected Sentence Rewriting

Fast Abstractive Summarization with Reinforce-Selected Sentence Rewriting

28 May 2018ACL 2018 7arXiv:1805.11080archive 2025-07-28

Yen-Chun Chen, Mohit Bansal

Inspired by how humans summarize long documents, we propose an accurate and fast summarization model that first selects salient sentences and then rewrites them abstractively (i.e., compresses and paraphrases) to generate a concise overall summary. We use a novel sentence-level policy gradient method to bridge the non-differentiable computation between these two neural networks in a hierarchical way, while maintaining language fluency. Empirically, we achieve the new state-of-the-art on all metrics (including human evaluation) on the CNN/Daily Mail dataset, as well as significantly higher abstractiveness scores. Moreover, by first operating at the sentence-level and then the word-level, we enable parallel decoding of our neural generative model that results in substantially faster (10-20x) inference speed as well as 4x faster training convergence than previous long-paragraph encoder-decoder models. We also demonstrate the generalization of our model on the test-only DUC-2002 dataset, where we achieve higher scores than a state-of-the-art model.

PaperPDFConference PDFCodeCode Syntology ran

In Syntology View this paper on Syntology, its page in Syntology's graph. That page adds which of its functions are also present in other papers' code Syntology holds, with dates, and its dated run record as JSON and a README badge. It also 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

Syntology 3 code samples harvested from 2 repositories linked to this paper: 3 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 3 where Syntology's instrument failed) · 0 unverified. Where Syntology's instrument failed: 1 where our contract draft was wrong; 2 where the contract check could not run; failures of Syntology's instrument, not of the code. Every run on this page is a failure of Syntology's instrument, not of the code.

By repository: official repository: 1 sample from 1 repository, 1 ran (0 with no instrument failure; 1 where Syntology's instrument failed); community (archive-listed): 2 samples from 1 repository, 2 ran (0 with no instrument failure; 2 where Syntology's instrument failed). The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.

Levels written on 2026-09-22 (UTC): the dates Syntology's graph wrote each sample's verification level, not when the code executed.

ChenRocks/fast_abs_rl officialmentioned in papermentioned on GitHubpytorchSyntology: 1 sample, 1 ran (1 instrument-failed) · 0 unverified report
johnnyb1509/2020_VBDI_DL mentioned on GitHubtfSyntology: 2 samples, 2 ran (2 instrument-failed) · 0 unverified report
yunzhusong/AAAI20-PORLHG 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.

Code Syntology ran Syntology

3 samples harvested: 3 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 3 where Syntology's instrument failed) · 0 unverified. “Where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code. Every run on this page is a failure of Syntology's instrument, not of the code. Syntology's record for this page has not changed since , the first build that kept a record date for it; when this build read Syntology's graph is in the build record. That date is not when the samples ran.

1ran · our draft was wrong
2ran; the contract check could not run

Licence: 2 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; the list below is grouped by repository, each group headed by its name and what it is to the paper. “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. A line beginning “fixture:” under a sample that ran gives the arguments Syntology's fixture called the sample with, each as name:type/rank/element kind (? where none was recorded), and the type of what the fixture's run returned, exactly as the harness recorded them; the arguments and the returned type were recorded by two separate runs of the same fixture. No output value is shown, and a returned type says nothing about whether the output was right. “Level recorded” gives the UTC date when Syntology's graph wrote the sample's verification level, not when the code executed; where the level was written before Syntology's graph kept that date, the row says “level recorded, date not recorded”. “Honoured” and “violated” refer to a contract Syntology drafted from the code itself. “Our draft was wrong” and “the contract check could not run” are failures of Syntology's instrument, not of the code: the sample ran on Syntology's synthesized input, and then the drafted contract did not describe it, or the check itself raised an error (RAISES), lacked a dependency (DEP_MISSING) or ran out of time (TIMEOUT); hover the label for which. A metamorphic tier, where shown, is evidence of the output's shape, not that the sample implements the method.

Each sample ends with its code_sha256. A sample's code_sha256 is Syntology's identity for that exact code. It is printed in full (16 hexadecimal characters for every sample in this build), and get_code(code_sha256="…") takes it exactly as printed. An agent calls it on Syntology's MCP service (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 are grouped by repository: a repository marked official first, then by how directly the repository is tied to the paper, then in the archive's order; never by how many ran. 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 six 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; the licence is outside the permissive list Syntology serves text under (MIT, Apache-2.0, BSD and similar); this paper's copy was not located, so its licence is not recorded; or this paper's copy is cleared, but the stored copy of the same code that Syntology serves is not. 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.

ChenRocks/fast_abs_rl official repository 1 sample, 1 ran (1 instrument-failed) · 0 unverified
configure_training train_full_rl.py ran · our draft was wrong MIT (permissive) · 7189f6534350d1f5 · report fixture: signature opt:str/0/str, lr:float/0/float, clip_grad:float/0/float, lr_decay:float/0/float, batch_size:int/0/int, gamma:float/0/float, reward:float/0/float, stop_coeff:float/0/float, stop_reward:float/0/float · returned dict · level recorded 2026-09-22
johnnyb1509/2020_VBDI_DL community (archive-listed) 2 samples, 2 ran (2 instrument-failed) · 0 unverified
seq2summary src/inference_summary.py ran; the contract check could not run (RAISES) · metamorphic tier: deterministic no licence file found · pointer only · e84b1808b94a05a6 · report fixture: signature input_seq:ndarray/1/int, target_word_index:dict/0/?, reverse_target_word_index:dict/0/? · returned str · level recorded 2026-09-22
seq2text src/inference_summary.py ran; the contract check could not run (RAISES) · metamorphic tier: deterministic no licence file found · pointer only · eb5f5405d341bf97 · report fixture: signature input_seq:ndarray/1/int, reverse_source_word_index:dict/0/? · returned str · level recorded 2026-09-22

Tasks

Abstractive Text SummarizationDecoderSentenceSentence ReWritingText Summarization

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Abstractive Text Summarization CNN / Daily Mail rnn-ext + RL ROUGE-1 41.47 #33 of 53 Archive leaderboard report
Abstractive Text Summarization CNN / Daily Mail rnn-ext + RL ROUGE-2 18.72 #33 of 53 Archive leaderboard report
Abstractive Text Summarization CNN / Daily Mail rnn-ext + RL ROUGE-L 37.76 #33 of 53 Archive leaderboard report
Abstractive Text Summarization CNN / Daily Mail rnn-ext + abs + RL + rerank ROUGE-1 40.88 #38 of 53 Archive leaderboard report
Abstractive Text Summarization CNN / Daily Mail rnn-ext + abs + RL + rerank ROUGE-2 17.80 #38 of 53 Archive leaderboard report
Abstractive Text Summarization CNN / Daily Mail rnn-ext + abs + RL + rerank ROUGE-L 38.54 #38 of 53 Archive leaderboard report
Text Summarization CNN / Daily Mail (Anonymized) rnn-ext + abs + RL + rerank ROUGE-1 39.66 #7 of 13 Archive leaderboard report
Text Summarization CNN / Daily Mail (Anonymized) rnn-ext + abs + RL + rerank ROUGE-2 15.85 #7 of 13 Archive leaderboard report
Text Summarization CNN / Daily Mail (Anonymized) rnn-ext + abs + RL + rerank ROUGE-L 37.34 #7 of 13 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

SPEED

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