D-REX: Dialogue Relation Extraction with Explanations

Alon Albalak, Varun Embar, Yi-Lin Tuan, Lise Getoor, William Yang Wang


Abstract
Existing research studies on cross-sentence relation extraction in long-form multi-party conversations aim to improve relation extraction without considering the explainability of such methods. This work addresses that gap by focusing on extracting explanations that indicate that a relation exists while using only partially labeled explanations. We propose our model-agnostic framework, D-REX, a policy-guided semi-supervised algorithm that optimizes for explanation quality and relation extraction simultaneously. We frame relation extraction as a re-ranking task and include relation- and entity-specific explanations as an intermediate step of the inference process. We find that human annotators are 4.2 times more likely to prefer D-REX’s explanations over a joint relation extraction and explanation model. Finally, our evaluations show that D-REX is simple yet effective and improves relation extraction performance of strong baseline models by 1.2-4.7%.
Anthology ID:
2022.nlp4convai-1.4
Volume:
Proceedings of the 4th Workshop on NLP for Conversational AI
Month:
May
Year:
2022
Address:
Dublin, Ireland
Venue:
NLP4ConvAI
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
34–46
Language:
URL:
https://aclanthology.org/2022.nlp4convai-1.4
DOI:
10.18653/v1/2022.nlp4convai-1.4
Bibkey:
Cite (ACL):
Alon Albalak, Varun Embar, Yi-Lin Tuan, Lise Getoor, and William Yang Wang. 2022. D-REX: Dialogue Relation Extraction with Explanations. In Proceedings of the 4th Workshop on NLP for Conversational AI, pages 34–46, Dublin, Ireland. Association for Computational Linguistics.
Cite (Informal):
D-REX: Dialogue Relation Extraction with Explanations (Albalak et al., NLP4ConvAI 2022)
Copy Citation:
PDF:
https://aclanthology.org/2022.nlp4convai-1.4.pdf
Video:
 https://aclanthology.org/2022.nlp4convai-1.4.mp4
Code
 alon-albalak/D-REX
Data
DialogRE