Break It Down: A Question Understanding Benchmark

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.

[1]  Nitish Gupta,et al.  Neural Compositional Denotational Semantics for Question Answering , 2018, EMNLP.

[2]  Yoav Artzi,et al.  A Corpus for Reasoning about Natural Language Grounded in Photographs , 2018, ACL.

[3]  Ming-Wei Chang,et al.  Driving Semantic Parsing from the World’s Response , 2010, CoNLL.

[4]  H. V. Jagadish,et al.  Bridging the Semantic Gap with SQL Query Logs in Natural Language Interfaces to Databases , 2019, 2019 IEEE 35th International Conference on Data Engineering (ICDE).

[5]  Sebastian Riedel,et al.  Constructing Datasets for Multi-hop Reading Comprehension Across Documents , 2017, TACL.

[6]  Zijian Wang,et al.  Answering Complex Open-domain Questions Through Iterative Query Generation , 2019, EMNLP.

[7]  Luke S. Zettlemoyer,et al.  AllenNLP: A Deep Semantic Natural Language Processing Platform , 2018, ArXiv.

[8]  Sameer Singh,et al.  Compositional Questions Do Not Necessitate Multi-hop Reasoning , 2019, ACL.

[9]  Ming-Wei Chang,et al.  BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding , 2019, NAACL.

[10]  Ming-Wei Chang,et al.  The Value of Semantic Parse Labeling for Knowledge Base Question Answering , 2016, ACL.

[11]  Nils J. Nilsson,et al.  A Formal Basis for the Heuristic Determination of Minimum Cost Paths , 1968, IEEE Trans. Syst. Sci. Cybern..

[12]  Fei Li,et al.  Schema-free SQL , 2014, SIGMOD Conference.

[13]  P. J. Price,et al.  Evaluation of Spoken Language Systems: the ATIS Domain , 1990, HLT.

[14]  Jason Weston,et al.  Reading Wikipedia to Answer Open-Domain Questions , 2017, ACL.

[15]  Christopher D. Manning,et al.  GQA: A New Dataset for Real-World Visual Reasoning and Compositional Question Answering , 2019, 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR).

[16]  Ming-Wei Chang,et al.  Search-based Neural Structured Learning for Sequential Question Answering , 2017, ACL.

[17]  Peter Thanisch,et al.  Natural language interfaces to databases – an introduction , 1995, Natural Language Engineering.

[18]  Mohit Bansal,et al.  Avoiding Reasoning Shortcuts: Adversarial Evaluation, Training, and Model Development for Multi-Hop QA , 2019, ACL.

[19]  Luke S. Zettlemoyer,et al.  Large-Scale QA-SRL Parsing , 2018, ACL.

[20]  Dan Klein,et al.  Learning to Compose Neural Networks for Question Answering , 2016, NAACL.

[21]  Ming-Wei Chang,et al.  Natural Questions: A Benchmark for Question Answering Research , 2019, TACL.

[22]  Gabriel Stanovsky,et al.  DROP: A Reading Comprehension Benchmark Requiring Discrete Reasoning Over Paragraphs , 2019, NAACL.

[23]  Trevor Darrell,et al.  Learning to Reason: End-to-End Module Networks for Visual Question Answering , 2017, 2017 IEEE International Conference on Computer Vision (ICCV).

[24]  Luke S. Zettlemoyer,et al.  Learning to Map Sentences to Logical Form: Structured Classification with Probabilistic Categorial Grammars , 2005, UAI.

[25]  Jonathan Berant,et al.  The Web as a Knowledge-Base for Answering Complex Questions , 2018, NAACL.

[26]  Philipp Koehn,et al.  Abstract Meaning Representation for Sembanking , 2013, LAW@ACL.

[27]  Ari Rappoport,et al.  Universal Conceptual Cognitive Annotation (UCCA) , 2013, ACL.

[28]  Yoshua Bengio,et al.  HotpotQA: A Dataset for Diverse, Explainable Multi-hop Question Answering , 2018, EMNLP.

[29]  Percy Liang,et al.  Compositional Semantic Parsing on Semi-Structured Tables , 2015, ACL.

[30]  Alvin Cheung,et al.  Learning a Neural Semantic Parser from User Feedback , 2017, ACL.

[31]  Donald D. Chamberlin,et al.  SEQUEL: A structured English query language , 1974, SIGFIDET '74.

[32]  Hannaneh Hajishirzi,et al.  Multi-hop Reading Comprehension through Question Decomposition and Rescoring , 2019, ACL.

[33]  Tao Yu,et al.  Spider: A Large-Scale Human-Labeled Dataset for Complex and Cross-Domain Semantic Parsing and Text-to-SQL Task , 2018, EMNLP.

[34]  Ido Dagan,et al.  Crowdsourcing Question-Answer Meaning Representations , 2017, NAACL.

[35]  Mirella Lapata,et al.  Building a Neural Semantic Parser from a Domain Ontology , 2018, ArXiv.

[36]  Alexander I. Rudnicky,et al.  Expanding the Scope of the ATIS Task: The ATIS-3 Corpus , 1994, HLT.

[37]  Dan Klein,et al.  Learning Dependency-Based Compositional Semantics , 2011, CL.

[38]  Chris Callison-Burch,et al.  Optimizing Statistical Machine Translation for Text Simplification , 2016, TACL.

[39]  Raymond J. Mooney,et al.  Learning to Parse Database Queries Using Inductive Logic Programming , 1996, AAAI/IAAI, Vol. 2.

[40]  F. J. Pelletier The Principle of Semantic Compositionality , 1994 .

[41]  Hang Li,et al.  “ Tony ” DNN Embedding for “ Tony ” Selective Read for “ Tony ” ( a ) Attention-based Encoder-Decoder ( RNNSearch ) ( c ) State Update s 4 SourceVocabulary Softmax Prob , 2016 .

[42]  Greg Durrett,et al.  Understanding Dataset Design Choices for Multi-hop Reasoning , 2019, NAACL.

[43]  H. V. Jagadish,et al.  NaLIR: an interactive natural language interface for querying relational databases , 2014, SIGMOD Conference.

[44]  Mark Steedman,et al.  Transforming Dependency Structures to Logical Forms for Semantic Parsing , 2016, TACL.

[45]  Eunsol Choi,et al.  Scaling Semantic Parsers with On-the-Fly Ontology Matching , 2013, EMNLP.

[46]  Margaret Mitchell,et al.  VQA: Visual Question Answering , 2015, International Journal of Computer Vision.

[47]  Yan Gao,et al.  Towards Complex Text-to-SQL in Cross-Domain Database with Intermediate Representation , 2019, ACL.

[48]  Jian Zhang,et al.  SQuAD: 100,000+ Questions for Machine Comprehension of Text , 2016, EMNLP.

[49]  Li Fei-Fei,et al.  CLEVR: A Diagnostic Dataset for Compositional Language and Elementary Visual Reasoning , 2016, 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[50]  F. E. A Relational Model of Data Large Shared Data Banks , 2000 .

[51]  Luke S. Zettlemoyer,et al.  Human-in-the-Loop Parsing , 2016, EMNLP.

[52]  Eunsol Choi,et al.  Scalable Semantic Parsing with Partial Ontologies , 2015, ACL.

[53]  Gerhard Weikum,et al.  ComQA: A Community-sourced Dataset for Complex Factoid Question Answering with Paraphrase Clusters , 2018, NAACL.