Papers › A Discourse-Aware Attention Model for Abstractive Summarization of Long Documents

A Discourse-Aware Attention Model for Abstractive Summarization of Long Documents

16 Apr 2018NAACL 2018 6arXiv:1804.05685archive 2025-07-28

Arman Cohan, Franck Dernoncourt, Doo Soon Kim, Trung Bui, Seokhwan Kim, Walter Chang, Nazli Goharian

Neural abstractive summarization models have led to promising results in summarizing relatively short documents. We propose the first model for abstractive summarization of single, longer-form documents (e.g., research papers). Our approach consists of a new hierarchical encoder that models the discourse structure of a document, and an attentive discourse-aware decoder to generate the summary. Empirical results on two large-scale datasets of scientific papers show that our model significantly outperforms state-of-the-art models.

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 14 code samples harvested from 2 repositories linked to this paper: 7 ran (of which 0 constructed an object rather than computing a result; 6 with no instrument failure: 0 honoured, 0 violated, 6 with no contract checked; 1 where Syntology's instrument failed) · 7 unverified. Where Syntology's instrument failed: 1 where our contract draft was wrong; failures of Syntology's instrument, not of the code.

By repository: official repository: 11 samples from 1 repository, 6 ran (5 with no instrument failure; 1 where Syntology's instrument failed); community (archive-listed): 3 samples from 1 repository, 1 ran (1 with no instrument failure; 0 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 between 2026-09-22 and 2026-09-26 (UTC): the dates Syntology's graph wrote each sample's verification level, not when the code executed.

acohan/long-summarization officialmentioned in papermentioned on GitHubtfApache-2.0Syntology: 11 samples, 6 ran (1 instrument-failed) · 5 unverified report
AlexGidiotis/DANCER-summ mentioned on GitHubpytorchMITSyntology: 3 samples, 1 ran (0 instrument-failed) · 2 unverified report
tongbao96/code-for-sfr-as 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

14 samples harvested: 7 ran (of which 0 constructed an object rather than computing a result; 6 with no instrument failure: 0 honoured, 0 violated, 6 with no contract checked; 1 where Syntology's instrument failed) · 7 unverified. “Where Syntology's instrument failed” counts failures 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
6ran
7unverified

Licence: 0 of the 14 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.

A function or class name links to its page when the name occurs in the harvested code of at least 5 papers; the name is a string, not an identity.

acohan/long-summarization official repository 11 samples, 6 ran (1 instrument-failed) · 5 unverified
abstract2ids data.py ran Apache-2.0 (permissive) · fe1c05743cd67af2 · report fixture: signature abstract_words:list/1/str, vocab:Vocabulary/0/?, article_oovs:list/1/str · returned list · level recorded 2026-09-25
article2ids data.py ran Apache-2.0 (permissive) · ecb10763ebbfe0bd · report fixture: signature article_words:list/1/str, vocab:Vocabulary/0/? · returned tuple · level recorded 2026-09-25
load_embeddings in 33 papers util.py ran Apache-2.0 (permissive) · ab9862cbeb4502b8 · report fixture: signature fpath:str/0/str, word_to_id:dict/0/?, emd_init_var:float/0/float · returned ndarray · level recorded 2026-09-25
make_html_safe in 5 papers decode.py ran · our draft was wrong fingerprinted Apache-2.0 (permissive) · 84fcb74e05d73aff · report fixture: signature s:str/0/str · returned str · level recorded 2026-09-22
outputids2words data.py ran Apache-2.0 (permissive) · eca0776bc82826da · report fixture: signature id_list:list/1/int, vocab:MockVocab/0/?, article_oovs:list/1/str · returned list · level recorded 2026-09-25
sort_hyps beam_search.py ran Apache-2.0 (permissive) · 8891bb52fbe37510 · report fixture: signature hyps:list/1/Hypothesis · returned list · level recorded 2026-09-25
attention_decoder attention_decoder_new.py unverified Apache-2.0 (permissive) · e099bb1c118a98d5 · report
calc_running_avg_loss run_summarization.py unverified Apache-2.0 (permissive) · dfba7977a83de9b4 · report
linear in 88 papers attention_decoder.py unverified Apache-2.0 (permissive) · 75bf8deb2b42c686 · report
linear_weight_sharing attention_decoder_new.py unverified Apache-2.0 (permissive) · fee6d1051182f149 · report
rouge_log decode.py unverified Apache-2.0 (permissive) · 47c13473d0a48d39 · report
AlexGidiotis/DANCER-summ community (archive-listed) 3 samples, 1 ran (0 instrument-failed) · 2 unverified
rouge_targets src/full_prep.py ran MIT (permissive) · 652b875f36ede145 · report fixture: signature abstract_sentences:list/1/str, section_sentences:list/1/str, rg_scorer:MockRougeScorer/0/? · returned list · level recorded 2026-09-26
init_loader src/loaders.py unverified MIT (permissive) · e9773eff8ddf3122 · report
load_model in 479 papers src/loaders.py unverified MIT (permissive) · 6a3b6c3e04b98ed4 · report

Tasks

Abstractive Text SummarizationDecoderText SummarizationUnsupervised Extractive Summarization

Datasets

Introduced by this paper, per the archive.

arXiv Summarization Dataset

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Text Summarization Arxiv HEP-TH citation graph Discourse ROUGE-1 35.80 #26 of 28 Archive leaderboard report
Text Summarization Pubmed Discourse ROUGE-1 38.93 #27 of 29 Archive leaderboard report
Unsupervised Extractive Summarization Pubmed LexRank ROUGE-1 39.19 #4 of 9 Archive leaderboard report
Unsupervised Extractive Summarization Pubmed LexRank ROUGE-2 13.89 #4 of 9 Archive leaderboard report
Unsupervised Extractive Summarization Pubmed LexRank ROUGE-L 34.59 #4 of 9 Archive leaderboard report
Unsupervised Extractive Summarization Pubmed SumBasic ROUGE-1 37.15 #7 of 9 Archive leaderboard report
Unsupervised Extractive Summarization Pubmed SumBasic ROUGE-2 11.36 #7 of 9 Archive leaderboard report
Unsupervised Extractive Summarization Pubmed SumBasic ROUGE-L 33.43 #7 of 9 Archive leaderboard report
Unsupervised Extractive Summarization Pubmed LSA ROUGE-1 33.89 #9 of 9 Archive leaderboard report
Unsupervised Extractive Summarization Pubmed LSA ROUGE-2 9.93 #9 of 9 Archive leaderboard report
Unsupervised Extractive Summarization Pubmed LSA ROUGE-L 29.70 #9 of 9 Archive leaderboard report
Unsupervised Extractive Summarization arXiv Summarization Dataset LexRank ROUGE-1 33.85 #5 of 10 Archive leaderboard report
Unsupervised Extractive Summarization arXiv Summarization Dataset LexRank ROUGE-2 10.73 #5 of 10 Archive leaderboard report
Unsupervised Extractive Summarization arXiv Summarization Dataset LexRank ROUGE-L 28.99 #5 of 10 Archive leaderboard report
Unsupervised Extractive Summarization arXiv Summarization Dataset LSA ROUGE-1 29.91 #7 of 10 Archive leaderboard report
Unsupervised Extractive Summarization arXiv Summarization Dataset LSA ROUGE-2 7.42 #7 of 10 Archive leaderboard report
Unsupervised Extractive Summarization arXiv Summarization Dataset LSA ROUGE-L 25.67 #7 of 10 Archive leaderboard report
Unsupervised Extractive Summarization arXiv Summarization Dataset SumBasic ROUGE-1 29.47 #9 of 10 Archive leaderboard report
Unsupervised Extractive Summarization arXiv Summarization Dataset SumBasic ROUGE-2 6.95 #9 of 10 Archive leaderboard report
Unsupervised Extractive Summarization arXiv Summarization Dataset SumBasic ROUGE-L 26.30 #9 of 10 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