Papers › Bottom-Up Abstractive Summarization

Bottom-Up Abstractive Summarization

31 Aug 2018EMNLP 2018 10arXiv:1808.10792archive 2025-07-28

Sebastian Gehrmann, Yuntian Deng, Alexander M. Rush

Neural network-based methods for abstractive summarization produce outputs that are more fluent than other techniques, but which can be poor at content selection. This work proposes a simple technique for addressing this issue: use a data-efficient content selector to over-determine phrases in a source document that should be part of the summary. We use this selector as a bottom-up attention step to constrain the model to likely phrases. We show that this approach improves the ability to compress text, while still generating fluent summaries. This two-step process is both simpler and higher performing than other end-to-end content selection models, leading to significant improvements on ROUGE for both the CNN-DM and NYT corpus. Furthermore, the content selector can be trained with as little as 1,000 sentences, making it easy to transfer a trained summarizer to a new domain.

PaperPDFConference PDFCodeCode Syntology ran

In Syntology View this paper on Syntology: its repositories, every harvested function with whether it ran, its licence and the call to fetch it.

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="1808.10792")

Code

Syntology Ran 5 of 6 code samples harvested from 1 repository linked to this paper; 1 has no recorded run. Of those that ran: 3 ran · our draft was wrong; 2 ran · fixture could not drive it.

By repository: official repository: 6 samples from 1 repository, 5 ran. The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.

sebastianGehrmann/bottom-up-summary officialmentioned in papermentioned on GitHub report
W4ngatang/qags mentioned on GitHubpytorch report
j40903272/bottom-up-summary mentioned on GitHubpytorch report
prashanth41/text-summarization mentioned on GitHubtfNOASSERTION 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

6 samples harvested; 5 ran; 0 honoured the contract we drafted; 1 has no recorded run. Read from Syntology's graph 2026-09-25; that is when this build read the record, not when the samples ran.

3ran · our draft was wrong
2ran · fixture could not drive it
1unverified

Licence: 0 of the 6 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 sebastianGehrmann/bottom-up-summary. “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.

compile_substring sebastianGehrmann/bottom-up-summary/preprocess_copy.py official repository ran · our draft was wrong fingerprinted BSD-3-Clause (permissive) · 17692adbeaedd54d · report
format_json sebastianGehrmann/bottom-up-summary/preprocess_copy.py official repository ran · our draft was wrong fingerprinted BSD-3-Clause (permissive) · 1489df8b19518049 · report
get_sents sebastianGehrmann/bottom-up-summary/prediction_to_text.py official repository ran · fixture could not drive it fingerprinted BSD-3-Clause (permissive) · 6b890c90cd5ecfa6 · report
get_three sebastianGehrmann/bottom-up-summary/prediction_to_text.py official repository ran · fixture could not drive it BSD-3-Clause (permissive) · 20cb63f02f26da92 · report
splits sebastianGehrmann/bottom-up-summary/preprocess_copy.py official repository ran · our draft was wrong fingerprinted BSD-3-Clause (permissive) · 12d9e8622f8706e2 · report
get_phrases sebastianGehrmann/bottom-up-summary/prediction_to_text.py official repository unverified BSD-3-Clause (permissive) · e378ee2b26dd8ebc · report

Tasks

Abstractive Text SummarizationDocument SummarizationMulti-Document Summarization

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Abstractive Text Summarization CNN / Daily Mail Bottom-Up Summarization ROUGE-1 41.22 #35 of 53 Archive leaderboard report
Abstractive Text Summarization CNN / Daily Mail Bottom-Up Summarization ROUGE-2 18.68 #35 of 53 Archive leaderboard report
Abstractive Text Summarization CNN / Daily Mail Bottom-Up Summarization ROUGE-L 38.34 #35 of 53 Archive leaderboard report
Document Summarization CNN / Daily Mail Bottom-Up Sum PPL 32.75 #16 of 26 Archive leaderboard report
Document Summarization CNN / Daily Mail Bottom-Up Sum ROUGE-1 41.22 #16 of 26 Archive leaderboard report
Document Summarization CNN / Daily Mail Bottom-Up Sum ROUGE-2 18.68 #16 of 26 Archive leaderboard report
Document Summarization CNN / Daily Mail Bottom-Up Sum ROUGE-L 38.34 #16 of 26 Archive leaderboard report
Multi-Document Summarization Multi-News CopyTransformer ROUGE-1 43.57 #4 of 6 Archive leaderboard report
Multi-Document Summarization Multi-News CopyTransformer ROUGE-2 14.03 #4 of 6 Archive leaderboard report
Multi-Document Summarization Multi-News CopyTransformer ROUGE-SU4 17.37 #4 of 6 Archive leaderboard report
Multi-Document Summarization Multi-News PG-BRNN ROUGE-1 42.80 #6 of 6 Archive leaderboard report
Multi-Document Summarization Multi-News PG-BRNN ROUGE-2 14.19 #6 of 6 Archive leaderboard report
Multi-Document Summarization Multi-News PG-BRNN ROUGE-SU4 16.75 #6 of 6 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