D-REX: Dialogue Relation Extraction with Explanations
Alon Albalak, Varun R. Embar, Yi-Lin Tuan, Lise Getoor, William Yang Wang · 2022
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 modelagnostic 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 entityspecific 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%. 1