Bidirectional Attention Flow for Machine Comprehension
@article{Seo2017BidirectionalAF, title={Bidirectional Attention Flow for Machine Comprehension}, author={Minjoon Seo and Aniruddha Kembhavi and Ali Farhadi and Hannaneh Hajishirzi}, journal={ArXiv}, year={2017}, volume={abs/1611.01603} }
Machine comprehension (MC), answering a query about a given context paragraph, requires modeling complex interactions between the context and the query. [...] Key Method 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…Expand
Figures, Tables, and Topics from this paper
1,310 Citations
Pay More Attention - Neural Architectures for Question-Answering
- Computer Science
- ArXiv
- 2018
- 1
- Highly Influenced
- PDF
GSA-Net: gated scaled dot-product attention based neural network for reading comprehension
- Computer Science
- 2020
A new model for Machine Comprehension via multi-perspective context matching and bidrectional attention flow
- 2017
- Highly Influenced
- PDF
Question Answering with Gated Attention and Multitask Learning-Option 3 (Graded)
- 2020
- Highly Influenced
- PDF
Query Attention GloVe GloVe CNN Attention Flow Layer Modeling Layer Output Layer
- 2017
- Highly Influenced
- PDF
Multi-Granularity Hierarchical Attention Fusion Networks for Reading Comprehension and Question Answering
- Computer Science
- ACL
- 2018
- 112
- Highly Influenced
- PDF
Document Modeling with Graph Attention Networks for Multi-grained Machine Reading Comprehension
- Computer Science
- ACL
- 2020
- 7
- PDF
References
SHOWING 1-10 OF 39 REFERENCES
Learning Recurrent Span Representations for Extractive Question Answering
- Computer Science
- ArXiv
- 2016
- 121
- PDF
Stacked Attention Networks for Image Question Answering
- Computer Science, Mathematics
- 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)
- 2016
- 1,189
- PDF