Open Peer Review. Open Publishing. Open Access. Open Discussion. Open Directory. Open Recommendations. Open API. Open Source.
e-QRAQ: A Multi-turn Reasoning Dataset and Simulator with Explanations
Clemens Rosenbaum, Tian Gao, Tim Klinger
Jun 16, 2017 (modified: Jun 19, 2017)ICML 2017 WHI Submissionreaders: everyone
Abstract:In this paper we present a new dataset and simulator e-QRAQ (explainable Query, Reason, and Answer Question) in which a User simulator provides an Agent with a short, ambiguous story and a challenge question about the story. The story is ambiguous because some of the entities have been replaced by variables. At each turn the Agent may ask for the value of a variable or try to answer the challenge question. In response the User simulator provides a natural language explanation of why the Agent's query or answer was useful in narrowing down the set of possible answers, or not. To demonstrate one potential application of the e-QRAQ dataset, we train a new neural architecture based on End-to-End Memory Networks to successfully generate both predictions and partial explanations of its current understanding of the problem. We observe a strong correlation between the quality of the prediction and explanation.
Enter your feedback below and we'll get back to you as soon as possible.