Interpretable AMR-Based Question Decomposition for Multi-hop Question Answering

Interpretable AMR-Based Question Decomposition for Multi-hop Question Answering

Zhenyun Deng, Yonghua Zhu, Yang Chen, Michael Witbrock, Patricia Riddle

Proceedings of the Thirty-First International Joint Conference on Artificial Intelligence
Main Track. Pages 4093-4099. https://doi.org/10.24963/ijcai.2022/568

Effective multi-hop question answering (QA) requires reasoning over multiple scattered paragraphs and providing explanations for answers. Most existing approaches cannot provide an interpretable reasoning process to illustrate how these models arrive at an answer. In this paper, we propose a Question Decomposition method based on Abstract Meaning Representation (QDAMR) for multi-hop QA, which achieves interpretable reasoning by decomposing a multi-hop question into simpler subquestions and answering them in order. Since annotating the decomposition is expensive, we first delegate the complexity of understanding the multi-hop question to an AMR parser. We then achieve decomposition of a multi-hop question via segmentation of the corresponding AMR graph based on the required reasoning type. Finally, we generate sub-questions using an AMR-to-Text generation model and answer them with an off-the-shelf QA model. Experimental results on HotpotQA demonstrate that our approach is competitive for interpretable reasoning and that the sub-questions generated by QDAMR are well-formed, outperforming existing question-decomposition-based multihop QA approaches.
Keywords:
Natural Language Processing: Question Answering
Natural Language Processing: Interpretability and Analysis of Models for NLP
Natural Language Processing: Language Generation
AI Ethics, Trust, Fairness: Explainability and Interpretability
Data Mining: Mining Graphs