Bidirectional Attention Flow for Machine Comprehension

Code

• github.com/allenai/bi-att-flow
  Officialtf★ 0
• github.com/baidu/DuReader
  tf★ 1,167
• github.com/distractor-generation/dg_survey
  none★ 4
• github.com/yugrocks/Question-Answering-with-BIDAF
  tf★ 0
• github.com/rajatgermany/qa-nlp
  pytorch★ 0
• github.com/GauthierDmn/question_answering
  pytorch★ 0
• github.com/WarruzuEndo/BiDAF_mindspore
  mindspore★ 0
• github.com/xiaobaicxy/Bidaf_SQuAD_MC_Pytorch
  pytorch★ 0
• github.com/surekhamedapati/NLPA_NEO
  pytorch★ 0
• github.com/techit-limtiyakul/bidirectional-attention-flow
  pytorch★ 0

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.

Tasks

Benchmark Results

Reproductions