Large-scale Simple Question Answering with Memory Networks
This work addresses the problem of limited training coverage for question answering systems, but it is incremental as it builds on existing Memory Networks with a new dataset.
The paper tackles the challenge of training large-scale question answering systems by studying multitask and transfer learning for simple question answering, introducing a new dataset of 100k questions and achieving excellent performance with Memory Networks.
Training large-scale question answering systems is complicated because training sources usually cover a small portion of the range of possible questions. This paper studies the impact of multitask and transfer learning for simple question answering; a setting for which the reasoning required to answer is quite easy, as long as one can retrieve the correct evidence given a question, which can be difficult in large-scale conditions. To this end, we introduce a new dataset of 100k questions that we use in conjunction with existing benchmarks. We conduct our study within the framework of Memory Networks (Weston et al., 2015) because this perspective allows us to eventually scale up to more complex reasoning, and show that Memory Networks can be successfully trained to achieve excellent performance.