Learning to Recover Reasoning Chains for Multi-Hop Question Answering via Cooperative Games
arXiv:2004.02393
Abstract
We propose the new problem of learning to recover reasoning chains from weakly supervised signals, i.e., the question-answer pairs. We propose a cooperative game approach to deal with this problem, in which how the evidence passages are selected and how the selected passages are connected are handled by two models that cooperate to select the most confident chains from a large set of candidates (from distant supervision). For evaluation, we created benchmarks based on two multi-hop QA datasets, HotpotQA and MedHop; and hand-labeled reasoning chains for the latter. The experimental results demonstrate the effectiveness of our proposed approach.
References in corpus (7)
- Go for a Walk and Arrive at the Answer: Reasoning Over Paths in Knowledge Bases using Reinforcement Learning
- Learning to Retrieve Reasoning Paths over Wikipedia Graph for Question Answering
- Multi-hop Question Answering via Reasoning Chains
- Dynamically Fused Graph Network for Multi-hop Reasoning
- Multi-step Entity-centric Information Retrieval for Multi-Hop Question Answering
- Do Multi-hop Readers Dream of Reasoning Chains?
- Rethinking Cooperative Rationalization: Introspective Extraction and Complement Control