Did Aristotle Use a Laptop? A Question Answering Benchmark with Implicit Reasoning Strategies
Published
2022-01-04
Mor Geva
,
Daniel Khashabi
,
Elad Segal
,
Tushar Khot
,
Dan Roth
,
Jonathan Berant
Mor Geva
Tel-Aviv University, Allen Institute for AI
Daniel Khashabi
Allen Institute for AI
Elad Segal
Tel-Aviv University
Tushar Khot
Allen Institute for AI
Dan Roth
University of Pennsylvania
Jonathan Berant
Tel-Aviv University, Allen Institute for AI
Abstract
A key limitation in current datasets for multi-hop reasoning is that the required steps for answering the question are mentioned in it explicitly. In this work, we introduce StrategyQA, a question answering (QA) benchmark where the required reasoning steps are implicit in the question, and should be inferred using a strategy. A fundamental challenge in this setup is how to elicit such creative questions from crowdsourcing workers, while covering a broad range of potential strategies. We propose a data collection procedure that combines term-based priming to inspire annotators, careful control over the annotator population, and adversarial filtering for eliminating reasoning shortcuts. Moreover, we annotate each question with (1) a decomposition into reasoning steps for answering it, and (2) Wikipedia paragraphs that contain the answers to each step. Overall, StrategyQA includes 2,780 examples, each consisting of a strategy question, its decomposition, and evidence paragraphs. Analysis shows that questions in StrategyQA are short, topic-diverse, and cover a wide range of strategies. Empirically, we show that humans perform well (87%) on this task, while our best baseline reaches an accuracy of ∼66%.
Presented at NAACL 2021
Article at MIT Press
,