Large-scale Simple Question Answering with Memory Networks

Abstract

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.

Cited by in corpus (14)

• Learning to Remember Rare Events
• A Neural Knowledge Language Model
• Dataset and Neural Recurrent Sequence Labeling Model for Open-Domain Factoid Question Answering
• Automatic Rule Extraction from Long Short Term Memory Networks
• Visual Question Answering: A Survey of Methods and Datasets
• Towards Transparent AI Systems: Interpreting Visual Question Answering Models
• Dynamic Neural Turing Machine with Soft and Hard Addressing Schemes
• CFO: Conditional Focused Neural Question Answering with Large-scale Knowledge Bases
• Gaussian Attention Model and Its Application to Knowledge Base Embedding and Question Answering
• Question Answering from Unstructured Text by Retrieval and Comprehension
• Hierarchical Memory Networks for Answer Selection on Unknown Words
• Multimodal Memory Modelling for Video Captioning
• Dynamic Key-Value Memory Networks for Knowledge Tracing
• Hierarchical Attention Model for Improved Machine Comprehension of Spoken Content