[1611.01603] Bidirectional Attention Flow for Machine Comprehension
source link: https://arxiv.org/abs/1611.01603
Go to the source link to view the article. You can view the picture content, updated content and better typesetting reading experience. If the link is broken, please click the button below to view the snapshot at that time.
Computer Science > Computation and Language
[Submitted on 5 Nov 2016 (v1), last revised 21 Jun 2018 (this version, v6)]
Bidirectional Attention Flow for Machine Comprehension
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.
Submission history
From: Minjoon Seo [view email][v1] Sat, 5 Nov 2016 04:49:00 UTC (1,009 KB)
[v2] Mon, 21 Nov 2016 21:34:22 UTC (1,010 KB)
[v3] Tue, 29 Nov 2016 18:46:50 UTC (1,011 KB)
[v4] Tue, 7 Feb 2017 22:01:42 UTC (1,018 KB)
[v5] Fri, 24 Feb 2017 19:57:53 UTC (1,017 KB)
[v6] Thu, 21 Jun 2018 10:53:20 UTC (1,301 KB)
Recommend
About Joyk
Aggregate valuable and interesting links.
Joyk means Joy of geeK