Bidirectional Attention Flow for Machine Comprehension
Published in
International Conference on Learning Representa...(2016)External Links:
TL
TL;DR
The BIDAF network is introduced, a multi-stage hierarchical process that represents the context at different levels of granularity and uses bi-directional attention flow mechanism to obtain a query-aware context representation without early summarization.
Abstract
Machine comprehension (MC), answering a query about a given context paragraph, requires modeling complex interactions between the context and the query. Recently, attention mechanisms have been successfully extended to MC. Typically these methods use attention to focus on a small portion of the context and summarize it with a fixed-size vector, couple attentions temporally, and/or often form a uni-directional attention. In this paper we introduce the Bi-Directional Attention Flow (BIDAF) network, a multi-stage hierarchical process that represents the context at different levels of granularity and uses bi-directional attention flow mechanism to obtain a query-aware context representation without early summarization. Our experimental evaluations show that our model achieves the state-of-the-art results in Stanford Question Answering Dataset (SQuAD) and CNN/DailyMail cloze test.
References40 items
1
Dynamic Coattention Networks For Question Answering
2
Words or Characters? Fine-grained Gating for Reading Comprehension
3
Learning Recurrent Span Representations for Extractive Question Answering
4
End-to-End Answer Chunk Extraction and Ranking for Reading Comprehension
5