Question-Interlocutor Scope Realized Graph Modeling over Key Utterances for Dialogue Reading Comprehension

Jiangnan Li, Mo Yu, Fandong Meng, Zheng Lin, Peng Fu, Weiping Wang, Jie Zhou


Abstract
We focus on dialogue reading comprehension (DRC) that extracts answers from dialogues. Compared to standard RC tasks, DRC has raised challenges because of the complex speaker information and noisy dialogue context. Essentially, the challenges come from the speaker-centric nature of dialogue utterances — an utterance is usually insufficient in its surface form, but requires to incorporate the role of its speaker and the dialogue context to fill the latent pragmatic and intention information. We propose to deal with these problems in two folds. First, we propose a new key-utterances-extracting method, which can realize more answer-contained utterances. Second, based on the extracted utterances, we then propose a Question-Interlocutor Scope Realized Graph (QuISG). QuISG involves the question and question-mentioning speaker as nodes. To realize interlocutor scopes, utterances are connected with corresponding speakers in the dialogue. Experiments on the benchmarks show that our method achieves state-of-the-art performance against previous works.
Anthology ID:
2023.findings-acl.306
Volume:
Findings of the Association for Computational Linguistics: ACL 2023
Month:
July
Year:
2023
Address:
Toronto, Canada
Editors:
Anna Rogers, Jordan Boyd-Graber, Naoaki Okazaki
Venue:
Findings
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
4956–4968
Language:
URL:
https://aclanthology.org/2023.findings-acl.306
DOI:
10.18653/v1/2023.findings-acl.306
Bibkey:
Cite (ACL):
Jiangnan Li, Mo Yu, Fandong Meng, Zheng Lin, Peng Fu, Weiping Wang, and Jie Zhou. 2023. Question-Interlocutor Scope Realized Graph Modeling over Key Utterances for Dialogue Reading Comprehension. In Findings of the Association for Computational Linguistics: ACL 2023, pages 4956–4968, Toronto, Canada. Association for Computational Linguistics.
Cite (Informal):
Question-Interlocutor Scope Realized Graph Modeling over Key Utterances for Dialogue Reading Comprehension (Li et al., Findings 2023)
Copy Citation:
PDF:
https://aclanthology.org/2023.findings-acl.306.pdf