Papers › A Divide-and-Conquer Approach to the Summarization of Long Documents

A Divide-and-Conquer Approach to the Summarization of Long Documents

13 Apr 2020arXiv:2004.06190archive 2025-07-28

Alexios Gidiotis, Grigorios Tsoumakas

We present a novel divide-and-conquer method for the neural summarization of long documents. Our method exploits the discourse structure of the document and uses sentence similarity to split the problem into an ensemble of smaller summarization problems. In particular, we break a long document and its summary into multiple source-target pairs, which are used for training a model that learns to summarize each part of the document separately. These partial summaries are then combined in order to produce a final complete summary. With this approach we can decompose the problem of long document summarization into smaller and simpler problems, reducing computational complexity and creating more training examples, which at the same time contain less noise in the target summaries compared to the standard approach. We demonstrate that this approach paired with different summarization models, including sequence-to-sequence RNNs and Transformers, can lead to improved summarization performance. Our best models achieve results that are on par with the state-of-the-art in two two publicly available datasets of academic articles.

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

AlexGidiotis/DANCER-summ officialmentioned on GitHubpytorchMITSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to A Discourse-Aware Attention Model for Abstractive Summarization of Long Documents (arXiv:1804.05685; that paper's own run record: 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); 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

ArticlesDocument SummarizationSentenceSentence SimilarityText Summarization

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Text Summarization Arxiv HEP-TH citation graph DANCER PEGASUS ROUGE-1 45.01 #15 of 28 Archive leaderboard report
Text Summarization Arxiv HEP-TH citation graph DANCER PEGASUS ROUGE-2 17.6 #15 of 28 Archive leaderboard report
Text Summarization Arxiv HEP-TH citation graph DANCER PEGASUS ROUGE-L 40.56 #15 of 28 Archive leaderboard report
Text Summarization Arxiv HEP-TH citation graph DANCER RUM ROUGE-1 42.7 #21 of 28 Archive leaderboard report
Text Summarization Arxiv HEP-TH citation graph DANCER RUM ROUGE-2 16.54 #21 of 28 Archive leaderboard report
Text Summarization Arxiv HEP-TH citation graph DANCER RUM ROUGE-L 38.44 #21 of 28 Archive leaderboard report
Text Summarization Arxiv HEP-TH citation graph DANCER LSTM ROUGE-1 41.87 #24 of 28 Archive leaderboard report
Text Summarization Arxiv HEP-TH citation graph DANCER LSTM ROUGE-2 15.92 #24 of 28 Archive leaderboard report
Text Summarization Arxiv HEP-TH citation graph DANCER LSTM ROUGE-L 37.61 #24 of 28 Archive leaderboard report
Text Summarization Pubmed DANCER PEGASUS ROUGE-1 46.34 #14 of 29 Archive leaderboard report
Text Summarization Pubmed DANCER PEGASUS ROUGE-2 19.97 #14 of 29 Archive leaderboard report
Text Summarization Pubmed DANCER PEGASUS ROUGE-L 42.42 #14 of 29 Archive leaderboard report
Text Summarization Pubmed DANCER LSTM ROUGE-1 44.09 #21 of 29 Archive leaderboard report
Text Summarization Pubmed DANCER LSTM ROUGE-2 17.69 #21 of 29 Archive leaderboard report
Text Summarization Pubmed DANCER LSTM ROUGE-L 40.27 #21 of 29 Archive leaderboard report
Text Summarization Pubmed DANCER RUM ROUGE-1 43.98 #22 of 29 Archive leaderboard report
Text Summarization Pubmed DANCER RUM ROUGE-2 17.65 #22 of 29 Archive leaderboard report
Text Summarization Pubmed DANCER RUM ROUGE-L 40.25 #22 of 29 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

LSTMSigmoid ActivationTanh Activation

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