D-REX: Dialogue Relation Extraction with Explanations
Preprint
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 a state-of-the-art F1 score on relation extraction, improving upon existing methods by 13.5%.Keywords
All Related Versions
This publication has 17 references indexed in Scilit:
- Dialogue Relation Extraction with Document-Level Heterogeneous Graph Attention NetworksCognitive Computation, 2023
- FETA: A Benchmark for Few-Sample Task Transfer in Open-Domain Dialogue2022
- GDPNet: Refining Latent Multi-View Graph for Relation ExtractionProceedings of the AAAI Conference on Artificial Intelligence, 2021
- A Novel Document-Level Relation Extraction Method Based on BERT and Entity InformationIEEE Access, 2020
- Relation Extraction with Explanation2020
- Dialogue-Based Relation Extraction2020
- NILE : Natural Language Inference with Faithful Natural Language Explanations2020
- Cross-Sentence N-ary Relation Extraction with Graph LSTMsTransactions of the Association for Computational Linguistics, 2017
- "Why Should I Trust You?"2016
- Rationalizing Neural Predictions2016