SELF-ADAPTIVE REASONING ON SUB-QUESTIONS FOR MULTI-HOP QUESTION ANSWERING

In this paper, we present the Self-Adapting Reasoning Model (SAR) for solving multi-hop question answering (MHQA) tasks, where the QA system is supposed to find the correct answer within the given multiple documents and a multi-hop question. One of the feasible tracks on MHQA is question decomposition, which is based on the idea that a multi-hop question is usually made from several single-hop questions, which are much easier to answer. However, ignoring the inner connection between sub-questions, existing works usually train additional single-hop question-answering models and answer sub-questions separately. To tackle this problem, we design an end-to-end self-adaptive multi-hop reasoning model. Specifically, given a multi-hop question, a question decomposer first decomposes it into two simple questions and identifies the question type. Then, based on the question type, different reasoning strategies are applied for reasoning. This enables our model to be self-adapting and more explainable regarding different types of questions. Experiments are carried out to demonstrate the effectiveness of our model, and SAR achieves remarkable results on the HotpotQA dataset.