Question Answering from Unstructured Text by Retrieval and Comprehension

Abstract

Open domain Question Answering (QA) systems must interact with external knowledge sources, such as web pages, to find relevant information. Information sources like Wikipedia, however, are not well structured and difficult to utilize in comparison with Knowledge Bases (KBs). In this work we present a two-step approach to question answering from unstructured text, consisting of a retrieval step and a comprehension step. For comprehension, we present an RNN based attention model with a novel mixture mechanism for selecting answers from either retrieved articles or a fixed vocabulary. For retrieval we introduce a hand-crafted model and a neural model for ranking relevant articles. We achieve state-of-the-art performance on W IKI M OVIES dataset, reducing the error by 40%. Our experimental results further demonstrate the importance of each of the introduced components.

References in corpus (8)

• Neural Architecture Search with Reinforcement Learning
• SQuAD: 100,000+ Questions for Machine Comprehension of Text
• Large-scale Simple Question Answering with Memory Networks
• Dynamic Coattention Networks For Question Answering
• A Thorough Examination of the CNN/Daily Mail Reading Comprehension Task
• A Neural Knowledge Language Model
• Hierarchical Memory Networks
• Clustering is Efficient for Approximate Maximum Inner Product Search

Cited by in corpus (4)

• PullNet: Open Domain Question Answering with Iterative Retrieval on Knowledge Bases and Text
• Discriminative Nearest Neighbor Few-Shot Intent Detection by Transferring Natural Language Inference
• Open Domain Question Answering Using Early Fusion of Knowledge Bases and Text
• Learning to Search in Long Documents Using Document Structure