Decomposing Complex Questions Makes Multi-Hop QA Easier and More Interpretable
This work addresses the challenge of interpretable reasoning in multi-hop QA for AI systems, representing an incremental improvement with a novel method for a known bottleneck.
The paper tackles multi-hop question answering by proposing a three-stage framework called RERC that decomposes complex questions into sub-questions, achieving state-of-the-art performance with a joint F1 score of 53.58 on the 2WikiMultiHopQA dataset and coming within 1.95 F1 points of human performance in support fact accuracy.
Multi-hop QA requires the machine to answer complex questions through finding multiple clues and reasoning, and provide explanatory evidence to demonstrate the machine reasoning process. We propose Relation Extractor-Reader and Comparator (RERC), a three-stage framework based on complex question decomposition, which is the first work that the RERC model has been proposed and applied in solving the multi-hop QA challenges. The Relation Extractor decomposes the complex question, and then the Reader answers the sub-questions in turn, and finally the Comparator performs numerical comparison and summarizes all to get the final answer, where the entire process itself constitutes a complete reasoning evidence path. In the 2WikiMultiHopQA dataset, our RERC model has achieved the most advanced performance, with a winning joint F1 score of 53.58 on the leaderboard. All indicators of our RERC are close to human performance, with only 1.95 behind the human level in F1 score of support fact. At the same time, the evidence path provided by our RERC framework has excellent readability and faithfulness.