D-REX: Dialogue Relation Extraction with Explanations
Alon Albalak, Varun Embar, Yi-Lin Tuan, Lise Getoor, William Yang Wang

TL;DR
D-REX is a semi-supervised, model-agnostic framework that improves dialogue relation extraction by providing explanations and ranking relations, achieving state-of-the-art performance and human-preferred explanations.
Contribution
The paper introduces D-REX, a novel policy-guided semi-supervised approach that incorporates explanations into relation extraction in conversations, a gap not addressed by prior work.
Findings
D-REX outperforms existing methods with a 13.5% F1 score improvement.
Human annotators prefer D-REX's explanations over other models 90% of the time.
D-REX effectively combines relation extraction and explanation generation in a semi-supervised setting.
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 data. We propose our model-agnostic framework, D-REX, a policy-guided semi-supervised algorithm that explains and ranks relations. 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 about 90% of the time, human annotators prefer D-REX's explanations over a strong BERT-based joint relation extraction and explanation model. Finally, our evaluations on a dialogue relation extraction dataset show that our method is simple yet effective and achieves…
Peer Reviews
No public reviews on file for this paper yet. If you reviewed it on a platform where reviews are public (OpenReview, ICLR, NeurIPS, ICML), you can paste yours below so the community can read it here.
Code & Models
Videos
No videos yet. Explain this paper in a talk, walkthrough, or lecture? Add one.
Taxonomy
TopicsTopic Modeling · Natural Language Processing Techniques · Advanced Text Analysis Techniques
MethodsMulti-Head Attention · Attention Is All You Need · Linear Layer · Layer Normalization · WordPiece · Linear Warmup With Linear Decay · Softmax · Attention Dropout · Dropout · Weight Decay
