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

4 Aug 2020  ·  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.

PDF Abstract


Results from the Paper

Task Dataset Model Metric Name Metric Value Global Rank Result Benchmark
Dialogue Rewriting CANARD SARG BLEU 54.80 # 1
Dialogue Rewriting Multi-Rewrite SARG (greedy) BLEU-1 92.2 # 1
BLEU-2 89.6 # 1
ROUGE-1 92.1 # 1
ROUGE-2 86.0 # 1
Rewriting F1 62.4 # 1
Dialogue Rewriting Multi-Rewrite SARG (n_beam=5) Rewriting F3 46.4 # 2
Rewriting F2 52.5 # 1


No methods listed for this paper. Add relevant methods here