Dialogue systems in the open domain have achieved great success due to large conversation data and the development of deep learning, but multi-turn scenarios are still a challenge because of the frequent coreference and information omission. In this paper, we investigate the incomplete utterance restoration since it has brought general improvement over multi-turn dialogue systems in recent studies. Inspired by the autoregression for 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 Restoration-200k show that our proposed model significantly outperforms the state-of-the-art models with faster inference speed.
View on arXiv