Yi-Lin Tuan
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Yi-Lin Tuan has a total of 4 co-authors. Here are the top co-authors by number of shared publications:
- Alon Albalak
Allen Institute for AI Vector Institute University of Washington Stanford University Massachusetts Institute of Technology Allen Institute for AI University of Toronto Stanford University
1 shared publication - Lise Getoor
UC Santa Cruz Google Research Google Research Harvard University Google Research Google Research Google Research UC Santa Cruz
1 shared publication - Varun Embar
UC Santa Cruz UC Santa Cruz UC Santa Cruz
1 shared publication - William Yang Wang
University of California Santa Barbara
1 shared publication
Latest Publications
- Open Access
D-REX: Dialogue Relation Extraction with Explanations
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 a state-of-the-art F1 score on relation extraction, improving upon existing methods by 13.5%.
Open AccessD-REX: Dialogue Relation Extraction with Explanations
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 a state-of-the-art F1 score on relation extraction, improving upon existing methods by 13.5%.