Bidirectional Attention Flow for Machine Comprehension

Minjoon Seo, Aniruddha Kembhavi, Ali Farhadi, Hannaneh Hajishirzi
11/5/2016
cs.CL

Official code: allenai/bi-att-flow (1,545 stars, Apache-2.0, TensorFlow, last commit 2023-05-31).

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.

View on arXivView PDF

Code Implementations(1)

allenai/bi-att-flowOfficial100%
TensorFlowApache-2.0

Bi-directional Attention Flow (BiDAF) network is a multi-stage hierarchical process that represents context at different levels of granularity and uses a bi-directional attention flow mechanism to achieve a query-aware context representation without early summarization.

1,545669HTML, ShellJun 22, 20163 years agoApache-2.0
bidafnlpquestion-answeringsquadtensorflow

Similar Papers

Document-Level Neural Machine Translation with Hierarchical Attention Networks

83% match1 repo672018

SDNet: Contextualized Attention-based Deep Network for Conversational Question Answering

82% match1 repo1912018

Fastformer: Additive Attention Can Be All You Need

81% match1 repo1922021

FusionNet: Fusing via Fully-Aware Attention with Application to Machine Comprehension

81% match1 repo1342017

Exploiting Contextual Target Attributes for Target Sentiment Classification

80% match2023

Text Understanding with the Attention Sum Reader Network

80% match1 repo982016

Cite this paper

@article{seo2016bidirectional,
  title  = {Bidirectional Attention Flow for Machine Comprehension},
  author = {Minjoon Seo and Aniruddha Kembhavi and Ali Farhadi and Hannaneh Hajishirzi},
  year   = {2016},
  eprint = {1611.01603},
  archivePrefix = {arXiv},
  url    = {https://arxiv.org/abs/1611.01603}
}

Add a badge to your README

Shows whether official code is linked for this paper.

Code of Paper badge
[![Code of Paper](https://codeofpaper.com/badge/1611.01603.svg)](https://codeofpaper.com/paper/1611.01603)

Discussion