e-QRAQ: A Multi-turn Reasoning Dataset and Simulator with Explanations
arXiv:1708.01776
Abstract
In this paper we present a new dataset and user simulator e-QRAQ (explainable Query, Reason, and Answer Question) which tests an Agent's ability to read an ambiguous text; ask questions until it can answer a challenge question; and explain the reasoning behind its questions and answer. The User simulator provides the 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 The story is ambiguous because some of the entities have been replaced by variables.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.
arXiv comment7 pages, 3 figures, presented at 2017 ICML Workshop on Human Interpretability in Machine Learning (WHI 2017), Sydney, NSW, Australia
References in corpus (9)
- Adam: A Method for Stochastic Optimization
- Model-Agnostic Interpretability of Machine Learning
- Not Just a Black Box: Learning Important Features Through Propagating Activation Differences
- A large annotated corpus for learning natural language inference
- Grad-CAM: Why did you say that?
- Language Understanding for Text-based Games Using Deep Reinforcement Learning
- Dialog-based Language Learning
- Making Tree Ensembles Interpretable
- Evaluating Prerequisite Qualities for Learning End-to-End Dialog Systems