Papers › SARG: A Novel Semi Autoregressive Generator for Multi-turn Incomplete Utterance Restoration

SARG: A Novel Semi Autoregressive Generator for Multi-turn Incomplete Utterance Restoration

4 Aug 2020arXiv:2008.01474archive 2025-07-28

Mengzuo Huang, Feng Li, Wuhe Zou, Weidong Zhang

Dialogue systems in open domain have achieved great success due to the easily obtained single-turn corpus and the development of deep learning, but the multi-turn scenario is still a challenge because of the frequent coreference and information omission. In this paper, we investigate the incomplete utterance restoration which has brought general improvement over multi-turn dialogue systems in recent studies. Meanwhile, jointly inspired by the autoregression for text generation and the sequence labeling for text editing, we propose a novel semi autoregressive generator (SARG) with the high efficiency and flexibility. Moreover, experiments on two benchmarks show that our proposed model significantly outperforms the state-of-the-art models in terms of quality and inference speed.

PaperPDFCode

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

Code

NetEase-GameAI/SARG officialmentioned on GitHubpytorchNOASSERTION 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

Dialogue RewritingText Generation

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Dialogue Rewriting CANARD SARG BLEU 54.80 #1 of 1 Archive leaderboard report
Dialogue Rewriting Multi-Rewrite SARG (n_beam=5) Rewriting F2 52.5 #2 of 3 Archive leaderboard report
Dialogue Rewriting Multi-Rewrite SARG (n_beam=5) Rewriting F3 46.4 #2 of 3 Archive leaderboard report
Dialogue Rewriting Multi-Rewrite SARG (greedy) BLEU-1 92.2 #3 of 3 Archive leaderboard report
Dialogue Rewriting Multi-Rewrite SARG (greedy) BLEU-2 89.6 #3 of 3 Archive leaderboard report
Dialogue Rewriting Multi-Rewrite SARG (greedy) ROUGE-1 92.1 #3 of 3 Archive leaderboard report
Dialogue Rewriting Multi-Rewrite SARG (greedy) ROUGE-2 86.0 #3 of 3 Archive leaderboard report
Dialogue Rewriting Multi-Rewrite SARG (greedy) Rewriting F1 62.4 #3 of 3 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