Learning to Recover Reasoning Chains for Multi-Hop Question Answering via Cooperative Games Article Swipe

PDF

Related Concepts

Computer science Question answering Artificial intelligence Task (project management) Hop (telecommunications) Natural language processing Machine learning Theoretical computer science Management Computer network Economics

Yufei Feng , Mo Yu , Wenhan Xiong , Xiaoxiao Guo , Junjie Huang , Shiyu Chang , Murray Campbell , Michael Greenspan , Xiaodan Zhu ·

YOU? · · 2021 · Open Access · · DOI: https://doi.org/10.21428/594757db.ce391ef3 · OA: W3176749433

We extend the formats of explanations in interpretable NLP with the proposed entity-centric reasoning chains for multi-hop question answering. We also propose a cooperative game approach to learn to recover such explanations from weakly supervised signals, i.e., the question-answer pairs. We evaluate our task and method via newly created benchmarks based on two multi-hop datasets, HotpotQA and MedHop; and hand-labeled reasoning chains for the latter. The experiments demonstrate the effectiveness of our approach.