Bidirectional Attention Flow for Machine Comprehension

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.

7 Figures and Tables

Showing 1-10 of 34 references

Memory networks. In ICLR

  • Jason Weston, Sumit Chopra, Antoine Bordes
  • 2015
Highly Influential
4 Excerpts

Published as a conference paper at ICLR

  • 2017

2016) 71.3 72.9 - - Iterative Attention

  • Memnn, Hill
  • 2016
Showing 1-10 of 84 extracted citations

Statistics

010020020162017
Citations per Year

109 Citations

Semantic Scholar estimates that this publication has received between 86 and 146 citations based on the available data.

See our FAQ for additional information.