Papers › Extractive Summarization with SWAP-NET: Sentences and Words from Alternating Pointer Networks

Extractive Summarization with SWAP-NET: Sentences and Words from Alternating Pointer Networks

1 Jul 2018ACL 2018 7archive 2025-07-28

Aishwarya Jadhav, Vaibhav Rajan

We present a new neural sequence-to-sequence model for extractive summarization called SWAP-NET (Sentences and Words from Alternating Pointer Networks). Extractive summaries comprising a salient subset of input sentences, often also contain important key words. Guided by this principle, we design SWAP-NET that models the interaction of key words and salient sentences using a new two-level pointer network based architecture. SWAP-NET identifies both salient sentences and key words in an input document, and then combines them to form the extractive summary. Experiments on large scale benchmark corpora demonstrate the efficacy of SWAP-NET that outperforms state-of-the-art extractive summarizers.

PaperPDFCode

Code

aishj10/swap-net mentioned in papertf 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

Not run by Syntology. Nothing on this page verifies that the listed code works.

Tasks

Abstractive Text SummarizationDocument SummarizationExtractive SummarizationMachine TranslationQuestion AnsweringText Summarization

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Text Summarization CNN / Daily Mail (Anonymized) SWAP-NET ROUGE-1 41.6 #2 of 13 Archive leaderboard report
Text Summarization CNN / Daily Mail (Anonymized) SWAP-NET ROUGE-2 18.3 #2 of 13 Archive leaderboard report
Text Summarization CNN / Daily Mail (Anonymized) SWAP-NET ROUGE-L 37.7 #2 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

LSTMPointer NetworkSigmoid ActivationSoftmaxTanh 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