Break It Down: A Question Understanding Benchmark

@article{Wolfson2020BreakID,
  title={Break It Down: A Question Understanding Benchmark},
  author={Tomer Wolfson and Mor Geva and Ankit Gupta and Matt Gardner and Yoav Goldberg and D. Deutch and Jonathan Berant},
  journal={Transactions of the Association for Computational Linguistics},
  year={2020},
  volume={8},
  pages={183-198}
}
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… Expand
27 Citations
Unsupervised Question Decomposition for Question Answering
  • 18
  • PDF
QED: A Framework and Dataset for Explanations in Question Answering
  • 6
  • PDF
KILT: a Benchmark for Knowledge Intensive Language Tasks
  • 27
  • PDF
Did Aristotle Use a Laptop? A Question Answering Benchmark with Implicit Reasoning Strategies
  • 3
  • Highly Influenced
  • PDF
R3: A Reading Comprehension Benchmark Requiring Reasoning Processes
  • 1
  • PDF
Text Modular Networks: Learning to Decompose Tasks in the Language of Existing Models
  • 3
  • Highly Influenced
  • PDF
From Natural Language Processing to Neural Databases
  • PDF
Neural Databases
  • 2
  • Highly Influenced
  • PDF
Discrete Reasoning Templates for Natural Language Understanding
  • Highly Influenced
  • PDF
Improving Compositional Generalization in Semantic Parsing
  • 3
  • PDF
...
1
2
3
...

References

SHOWING 1-10 OF 57 REFERENCES
Learning to Reason: End-to-End Module Networks for Visual Question Answering
  • 344
  • PDF
Natural Questions: A Benchmark for Question Answering Research
  • 358
  • PDF
SQuAD: 100, 000+ Questions for Machine Comprehension of Text
  • 2,689
  • PDF
The Web as a Knowledge-base for Answering Complex Questions
  • 140
  • PDF
Search-based Neural Structured Learning for Sequential Question Answering
  • 100
  • PDF
Crowdsourcing Question-Answer Meaning Representations
  • 39
  • PDF
Multi-hop Reading Comprehension through Question Decomposition and Rescoring
  • 54
  • Highly Influential
  • PDF
HotpotQA: A Dataset for Diverse, Explainable Multi-hop Question Answering
  • 405
  • Highly Influential
  • PDF
...
1
2
3
4
5
...