MuiDial: Improving Dialogue Disentanglement with Intent-Based Mutual Learning

Abstract

The main goal of dialogue disentanglement is to separate the mixed utterances from a chat slice into independent dialogues. Existing models often utilize either an utterance-to-utterance (U2U) prediction to determine whether two utterances that have the “reply-to” relationship belong to one dialogue, or an utterance-to-thread (U2T) prediction to determine which dialogue-thread a given utterance should belong to. Inspired by mutual leaning, we propose MuiDial, a novel dialogue disentanglement model, to exploit the intent of each utterance and feed the intent to a mutual learning U2U-U2T disentanglement model. Experimental results and in-depth analysis on several benchmark datasets demonstrate the effectiveness and generalizability of our approach.

Cite

Text

Jiang et al. "MuiDial: Improving Dialogue Disentanglement with Intent-Based Mutual Learning." International Joint Conference on Artificial Intelligence, 2022. doi:10.24963/IJCAI.2022/578

Markdown

[Jiang et al. "MuiDial: Improving Dialogue Disentanglement with Intent-Based Mutual Learning." International Joint Conference on Artificial Intelligence, 2022.](https://mlanthology.org/ijcai/2022/jiang2022ijcai-muidial/) doi:10.24963/IJCAI.2022/578

BibTeX

@inproceedings{jiang2022ijcai-muidial,
  title     = {{MuiDial: Improving Dialogue Disentanglement with Intent-Based Mutual Learning}},
  author    = {Jiang, Ziyou and Shi, Lin and Chen, Celia and Mu, Fangwen and Zhang, Yumin and Wang, Qing},
  booktitle = {International Joint Conference on Artificial Intelligence},
  year      = {2022},
  pages     = {4164-4170},
  doi       = {10.24963/IJCAI.2022/578},
  url       = {https://mlanthology.org/ijcai/2022/jiang2022ijcai-muidial/}
}