R3: A Reading Comprehension Benchmark Requiring Reasoning Processes
Wang, Ran, Tao, Kun, Song, Dingjie, Zhang, Zhilong, Ma, Xiao, Su, Xi'ao, Dai, Xinyu
–arXiv.org Artificial Intelligence
Existing question answering systems can only predict answers without explicit reasoning processes, which hinder their explainability and make us overestimate their ability of understanding and reasoning over natural language. In this work, we propose a novel task of reading comprehension, in which a model is required to provide final answers and reasoning processes. To this end, we introduce a formalism for reasoning over unstructured text, namely Text Reasoning Meaning Representation (TRMR). TRMR consists of three phrases, which is expressive enough to characterize the reasoning process to answer reading comprehension questions. We develop an annotation platform to facilitate TRMR's annotation, and release the R3 dataset, a \textbf{R}eading comprehension benchmark \textbf{R}equiring \textbf{R}easoning processes. R3 contains over 60K pairs of question-answer pairs and their TRMRs. Our dataset is available at: \url{http://anonymous}.
arXiv.org Artificial Intelligence
Apr-2-2020
- Country:
- North America
- United States
- Texas (0.04)
- Minnesota > Hennepin County
- Minneapolis (0.14)
- Louisiana > Orleans Parish
- New Orleans (0.04)
- Canada > British Columbia
- United States
- Europe
- France (0.04)
- Italy
- Tuscany > Florence (0.05)
- Veneto (0.04)
- Friuli Venezia Giulia > Trieste Province
- Trieste (0.04)
- Denmark > Capital Region
- Copenhagen (0.04)
- Belgium > Brussels-Capital Region
- Brussels (0.05)
- Asia
- Middle East
- China
- Hong Kong (0.05)
- Jiangsu Province > Nanjing (0.04)
- North America
- Genre:
- Research Report (0.50)
- Industry:
- Education > Assessment & Standards > Student Performance (1.00)
- Technology: