Interpretable AMR-Based Question Decomposition for Multi-hop Question Answering
This addresses the need for interpretable reasoning in multi-hop QA, which is incremental as it builds on existing decomposition methods.
The authors tackled the problem of interpretable reasoning in multi-hop question answering by proposing QDAMR, a method that decomposes questions into simpler sub-questions using Abstract Meaning Representation, achieving competitive performance on HotpotQA with well-formed sub-questions.
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 sub-questions 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 the 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 multi-hop QA approaches.