Who Is Speaking to Whom? Learning to Identify Utterance Addressee in Multi-Party Conversations

Ran Le, Wenpeng Hu, Mingyue Shang, Zhenjun You, Lidong Bing, Dongyan Zhao, Rui Yan

[How to correct problems with metadata yourself]


Abstract
Previous research on dialogue systems generally focuses on the conversation between two participants, yet multi-party conversations which involve more than two participants within one session bring up a more complicated but realistic scenario. In real multi- party conversations, we can observe who is speaking, but the addressee information is not always explicit. In this paper, we aim to tackle the challenge of identifying all the miss- ing addressees in a conversation session. To this end, we introduce a novel who-to-whom (W2W) model which models users and utterances in the session jointly in an interactive way. We conduct experiments on the benchmark Ubuntu Multi-Party Conversation Corpus and the experimental results demonstrate that our model outperforms baselines with consistent improvements.
Anthology ID:
D19-1199
Volume:
Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP)
Month:
November
Year:
2019
Address:
Hong Kong, China
Editors:
Kentaro Inui, Jing Jiang, Vincent Ng, Xiaojun Wan
Venues:
EMNLP | IJCNLP
SIG:
SIGDAT
Publisher:
Association for Computational Linguistics
Note:
Pages:
1909–1919
Language:
URL:
https://aclanthology.org/D19-1199
DOI:
10.18653/v1/D19-1199
Bibkey:
Cite (ACL):
Ran Le, Wenpeng Hu, Mingyue Shang, Zhenjun You, Lidong Bing, Dongyan Zhao, and Rui Yan. 2019. Who Is Speaking to Whom? Learning to Identify Utterance Addressee in Multi-Party Conversations. In Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP), pages 1909–1919, Hong Kong, China. Association for Computational Linguistics.
Cite (Informal):
Who Is Speaking to Whom? Learning to Identify Utterance Addressee in Multi-Party Conversations (Le et al., EMNLP-IJCNLP 2019)
Copy Citation:
PDF:
https://preview.aclanthology.org/teach-a-man-to-fish/D19-1199.pdf
Attachment:
 D19-1199.Attachment.pdf