Double attention recurrent convolution neural network for answer selection
Answer selection is one of the key steps in many question answering (QA) applications. In this paper, a new deep model with two kinds of attention is proposed for answer selection: the double attention recurrent convolution neural network (DARCNN). Double attention means self-attention and cross-att...
Main Authors: | Ganchao Bao, Yuan Wei, Xin Sun, Hongli Zhang |
---|---|
Format: | Article |
Language: | English |
Published: |
The Royal Society
2020-05-01
|
Series: | Royal Society Open Science |
Subjects: | |
Online Access: | https://royalsocietypublishing.org/doi/pdf/10.1098/rsos.191517 |
Similar Items
-
A Multi-Dimension Question Answering Network for Sarcasm Detection
by: Yufeng Diao, et al.
Published: (2020-01-01) -
Attend It Again: Recurrent Attention Convolutional Neural Network for Action Recognition
by: Haodong Yang, et al.
Published: (2018-03-01) -
Cooperative Use of Recurrent Neural Network and Siamese Region Proposal Network for Robust Visual Tracking
by: Xuechen Zhao, et al.
Published: (2021-01-01) -
Fully Convolutional CaptionNet: Siamese Difference Captioning Attention Model
by: Ariyo Oluwasanmi, et al.
Published: (2019-01-01) -
Multi-Scale Deformable CNN for Answer Selection
by: Donglei Liu, et al.
Published: (2019-01-01)