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

Authors

  • Mengzuo Huang Dalian University of Technology Netease Games AI Lab
  • Feng Li Netease Games AI Lab
  • Wuhe Zou Netease Games AI Lab
  • Weidong Zhang Netease Games AI Lab

Keywords:

Conversational AI/Dialog Systems

Abstract

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, 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 Restoration-200k show that our proposed model significantly outperforms the state-of-the-art models in terms of quality and inference speed.

Downloads

Published

2021-05-18

How to Cite

Huang, M., Li, F., Zou, W., & Zhang, W. (2021). SARG: A Novel Semi Autoregressive Generator for Multi-turn Incomplete Utterance Restoration. Proceedings of the AAAI Conference on Artificial Intelligence, 35(14), 13055-13063. Retrieved from https://ojs.aaai.org/index.php/AAAI/article/view/17543

Issue

Section

AAAI Technical Track on Speech and Natural Language Processing I