</> Code with Papers by Syntology

Papers › Mixture Content Selection for Diverse Sequence Generation

Mixture Content Selection for Diverse Sequence Generation

4 Sep 2019IJCNLP 2019 11arXiv:1909.01953archive 2025-07-28

Jaemin Cho, Minjoon Seo, Hannaneh Hajishirzi

Generating diverse sequences is important in many NLP applications such as question generation or summarization that exhibit semantically one-to-many relationships between source and the target sequences. We present a method to explicitly separate diversification from generation using a general plug-and-play module (called SELECTOR) that wraps around and guides an existing encoder-decoder model. The diversification stage uses a mixture of experts to sample different binary masks on the source sequence for diverse content selection. The generation stage uses a standard encoder-decoder model given each selected content from the source sequence. Due to the non-differentiable nature of discrete sampling and the lack of ground truth labels for binary mask, we leverage a proxy for ground truth mask and adopt stochastic hard-EM for training. In question generation (SQuAD) and abstractive summarization (CNN-DM), our method demonstrates significant improvements in accuracy, diversity and training efficiency, including state-of-the-art top-1 accuracy in both datasets, 6% gain in top-5 accuracy, and 3.7 times faster training over a state of the art model. Our code is publicly available at https://github.com/clovaai/FocusSeq2Seq.

PaperPDFConference PDFCode

In Syntology Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.

Code

clovaai/FocusSeq2Seq officialmentioned in papermentioned on GitHubpytorch 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 SummarizationDecoderDiversityDocument SummarizationMixture-of-ExpertsQuestion GenerationQuestion-Generation

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Abstractive Text Summarization CNN / Daily Mail Selector & Pointer-Generator ROUGE-1 41.72 #29 of 53 Archive leaderboard report
Abstractive Text Summarization CNN / Daily Mail Selector & Pointer-Generator ROUGE-2 18.74 #29 of 53 Archive leaderboard report
Abstractive Text Summarization CNN / Daily Mail Selector & Pointer-Generator ROUGE-L 38.79 #29 of 53 Archive leaderboard report
Document Summarization CNN / Daily Mail Selector+Pointer Generator ROUGE-1 41.72 #14 of 26 Archive leaderboard report
Document Summarization CNN / Daily Mail Selector+Pointer Generator ROUGE-2 18.74 #14 of 26 Archive leaderboard report
Document Summarization CNN / Daily Mail Selector+Pointer Generator ROUGE-L 38.79 #14 of 26 Archive leaderboard report
Question Generation SQuAD1.1 Selector & NQG++ BLEU-4 15.874 #10 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.

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