Break It Down: A Question Understanding Benchmark
This work addresses the challenge of question understanding for natural language processing applications, offering a new benchmark and dataset to facilitate decomposition-based approaches.
The authors tackled the problem of understanding natural language questions by introducing a Question Decomposition Meaning Representation (QDMR) to break down questions into steps, and released the Break dataset with over 83K question-QDMR pairs, showing it improves open-domain question answering on HotpotQA and can be converted to pseudo-SQL.
Understanding natural language questions entails the ability to break down a question into the requisite steps for computing its answer. In this work, we introduce a Question Decomposition Meaning Representation (QDMR) for questions. QDMR constitutes the ordered list of steps, expressed through natural language, that are necessary for answering a question. We develop a crowdsourcing pipeline, showing that quality QDMRs can be annotated at scale, and release the Break dataset, containing over 83K pairs of questions and their QDMRs. We demonstrate the utility of QDMR by showing that (a) it can be used to improve open-domain question answering on the HotpotQA dataset, (b) it can be deterministically converted to a pseudo-SQL formal language, which can alleviate annotation in semantic parsing applications. Last, we use Break to train a sequence-to-sequence model with copying that parses questions into QDMR structures, and show that it substantially outperforms several natural baselines.