D-REX: Dialogue Relation Extraction with Explanations
Albalak, Alon, Embar, Varun, Tuan, Yi-Lin, Getoor, Lise, Wang, William Yang
–arXiv.org Artificial Intelligence
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%.
arXiv.org Artificial Intelligence
Oct-18-2022
- Country:
- Oceania > Australia
- North America > United States
- Texas > Travis County
- Austin (0.04)
- New York > New York County
- New York City (0.04)
- New Mexico > Santa Fe County
- Santa Fe (0.04)
- Minnesota > Hennepin County
- Minneapolis (0.14)
- California
- Santa Cruz County > Santa Cruz (0.04)
- Santa Barbara County > Santa Barbara (0.04)
- Texas > Travis County
- Europe
- United Kingdom > England (0.04)
- Germany > Berlin (0.04)
- Sweden > Uppsala County
- Uppsala (0.04)
- Spain > Valencian Community
- Valencia Province > Valencia (0.04)
- Italy > Tuscany
- Florence (0.04)
- Denmark > Capital Region
- Copenhagen (0.04)
- Asia > China
- Genre:
- Research Report (0.82)
- Technology: