Dialogue-Based Relation Extraction

Dian Yu, Kai Sun, Claire Cardie, Dong Yu


Abstract
We present the first human-annotated dialogue-based relation extraction (RE) dataset DialogRE, aiming to support the prediction of relation(s) between two arguments that appear in a dialogue. We further offer DialogRE as a platform for studying cross-sentence RE as most facts span multiple sentences. We argue that speaker-related information plays a critical role in the proposed task, based on an analysis of similarities and differences between dialogue-based and traditional RE tasks. Considering the timeliness of communication in a dialogue, we design a new metric to evaluate the performance of RE methods in a conversational setting and investigate the performance of several representative RE methods on DialogRE. Experimental results demonstrate that a speaker-aware extension on the best-performing model leads to gains in both the standard and conversational evaluation settings. DialogRE is available at https://dataset.org/dialogre/.
Anthology ID:
2020.acl-main.444
Volume:
Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics
Month:
July
Year:
2020
Address:
Online
Editors:
Dan Jurafsky, Joyce Chai, Natalie Schluter, Joel Tetreault
Venue:
ACL
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
4927–4940
Language:
URL:
https://aclanthology.org/2020.acl-main.444
DOI:
10.18653/v1/2020.acl-main.444
Bibkey:
Cite (ACL):
Dian Yu, Kai Sun, Claire Cardie, and Dong Yu. 2020. Dialogue-Based Relation Extraction. In Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics, pages 4927–4940, Online. Association for Computational Linguistics.
Cite (Informal):
Dialogue-Based Relation Extraction (Yu et al., ACL 2020)
Copy Citation:
PDF:
https://preview.aclanthology.org/nschneid-patch-2/2020.acl-main.444.pdf
Video:
 http://slideslive.com/38928692
Code
 additional community code
Data
DialogREDocREDKnowledgeNet