SARG: A Novel Semi Autoregressive Generator for Multi-Turn Incomplete Utterance Restoration
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.
Cite
Text
Huang et al. "SARG: A Novel Semi Autoregressive Generator for Multi-Turn Incomplete Utterance Restoration." AAAI Conference on Artificial Intelligence, 2021. doi:10.1609/AAAI.V35I14.17543Markdown
[Huang et al. "SARG: A Novel Semi Autoregressive Generator for Multi-Turn Incomplete Utterance Restoration." AAAI Conference on Artificial Intelligence, 2021.](https://mlanthology.org/aaai/2021/huang2021aaai-sarg/) doi:10.1609/AAAI.V35I14.17543BibTeX
@inproceedings{huang2021aaai-sarg,
title = {{SARG: A Novel Semi Autoregressive Generator for Multi-Turn Incomplete Utterance Restoration}},
author = {Huang, Mengzuo and Li, Feng and Zou, Wuhe and Zhang, Weidong},
booktitle = {AAAI Conference on Artificial Intelligence},
year = {2021},
pages = {13055-13063},
doi = {10.1609/AAAI.V35I14.17543},
url = {https://mlanthology.org/aaai/2021/huang2021aaai-sarg/}
}