Multi-hop Reading Comprehension through Question Decomposition and Rescoring

Multi-hop Reading Comprehension (RC) requires reasoning and aggregation across several paragraphs. We propose a system for multi-hop RC that decomposes a compositional question into simpler sub-questions that can be answered by off-the-shelf single-hop RC models. Since annotations for such decomposition are expensive, we recast sub-question generation as a span prediction problem and show that our method, trained using only 400 labeled examples, generates sub-questions that are as effective as human-authored sub-questions. We also introduce a new global rescoring approach that considers each decomposition (i.e. the sub-questions and their answers) to select the best final answer, greatly improving overall performance. Our experiments on HotpotQA show that this approach achieves the state-of-the-art results, while providing explainable evidence for its decision making in the form of sub-questions.

PDF Abstract ACL 2019 PDF ACL 2019 Abstract


Results from the Paper

Task Dataset Model Metric Name Metric Value Global Rank Result Benchmark
Question Answering HotpotQA DecompRC ANS-EM 0.300 # 60
ANS-F1 0.407 # 60
SUP-EM 0.000 # 65
SUP-F1 0.000 # 67
JOINT-EM 0.000 # 64
JOINT-F1 0.000 # 67


No methods listed for this paper. Add relevant methods here