Search research articles

ABOUT JoVE

Overview Leadership Blog JoVE Help Center

AUTHORS

Publishing Process Editorial Board Scope & Policies Peer Review FAQ Submit

LIBRARIANS

Testimonials Subscriptions Access Resources Library Advisory Board FAQ

RESEARCH

JoVE Journal Methods Collections JoVE Encyclopedia of Experiments Archive

EDUCATION

JoVE Core JoVE Business JoVE Science Education JoVE Lab Manual Faculty Resource Center Faculty Site

Terms & Conditions of Use

Search research articles

Related Experiment Video

Updated: Dec 18, 2025

Author Spotlight: Enhancement of Salient Object Detection for Smart Grid Applications

Author Spotlight: Enhancement of Salient Object Detection for Smart Grid Applications

Published on: December 15, 2023

Double attention recurrent convolution neural network for answer selection.

Ganchao Bao¹, Yuan Wei¹, Xin Sun¹

¹School of Mechatronic Engineering and Automation, Shanghai University, Shanghai 200444, People's Republic of China.

Royal Society Open Science

|June 16, 2020

Summary

This summary is machine-generated.

Related Concept Videos

You might also read

Related Articles

Articles linked to this work by shared authors, journal, and citation graph.

Sort by

Same author

Mapping the analytical toolbox for next-generation adjuvant immunology: A bibliometric analysis of characterization techniques and emerging trends (2006-2025).

Talanta·2026

Same author

Corrigendum to: Sortilin as a Culprit in the Atherosclerosis Plaque Progression: Evidence from Clinical and Experimental Studies.

Current molecular medicine·2026

Same author

Impact of rehabilitation trajectory on affective and cognitive impairment after intracerebral hemorrhage: a cohort study.

Frontiers in neurology·2026

Same author

Identification of small-molecule TNF-α inhibitor candidates using machine learning-guided screening and multiscale molecular modelling.

Scientific reports·2026

Same author

Corrigendum to "Exploring post‑stroke depression: Exosomal proteomics reveals underlying mechanisms and potential plasma biomarkers" [Brain Res. Bull. 242 (2026) 111940].

Brain research bulletin·2026

Same author

Overexpression of novel CYP6ER1 variants mediates the resistance of Nilaparvata lugens to sulfoxaflor and the cross-resistance to neonicotinoid insecticides.

Pest management science·2026

Same journal

Desert lizards modulate nutritional responses to match seasonal biological needs.

Royal Society open science·2026

Same journal

Multi-generational fidelity, ecological and social determinants of roosting in a cooperatively breeding bird (<i>Argya squamiceps</i>).

Royal Society open science·2025

Same journal

Multifaceted polarization and information reliability in climate change discussions on social media platforms.

Royal Society open science·2025

Same journal

Comparing the kinematics related to inflicted head injury between violent shaking of a 6-week-old and a 1-year-old infant surrogate.

Royal Society open science·2025

Same journal

Partner choice increases observed reciprocity-based cooperation but decreases unobserved stake-based cooperation.

Royal Society open science·2025

Same journal

Importation models for travel-related SARS-CoV-2 cases reported in Newfoundland and Labrador during the COVID-19 pandemic.

Royal Society open science·2025

See all related articles

A new deep learning model, DARCNN, enhances answer selection in question answering (QA) by using double attention mechanisms. This model improves accuracy by considering word relationships and question-answer interactions.

Area of Science:

Natural Language Processing
Artificial Intelligence
Machine Learning

Background:

Answer selection is crucial for question answering (QA) systems.
Existing models often struggle with capturing complex word dependencies and interactions between questions and answers.

Purpose of the Study:

To propose a novel deep model, the Double Attention Recurrent Convolution Neural Network (DARCNN), for improved answer selection.
To leverage self-attention and cross-attention mechanisms inspired by machine translation transformers.

Main Methods:

Developed DARCNN incorporating self-attention, decay self-attention (prioritizing local words), and cross-attention for question-answer interaction.
Utilized elementwise multiplication and a multilayer perceptron for predicting matching scores based on feature vectors.

Keywords:

Siamese network answer selection attention mechanism bidirectional LSTM convolutional neural network

More Related Videos

Author Spotlight: Addressing Technical and Subjective Challenges in Measuring Classroom Attention

Author Spotlight: Addressing Technical and Subjective Challenges in Measuring Classroom Attention

Published on: December 15, 2023

Related Experiment Videos

Last Updated: Dec 18, 2025

Author Spotlight: Enhancement of Salient Object Detection for Smart Grid Applications

Author Spotlight: Enhancement of Salient Object Detection for Smart Grid Applications

Published on: December 15, 2023

Author Spotlight: Addressing Technical and Subjective Challenges in Measuring Classroom Attention

Author Spotlight: Addressing Technical and Subjective Challenges in Measuring Classroom Attention

Published on: December 15, 2023

Main Results:

DARCNN demonstrated superior performance compared to existing answer selection models.
Experiments were conducted on four diverse QA datasets in both Chinese and English.

Conclusions:

The proposed DARCNN model effectively enhances answer selection.
The study validates the effectiveness of self-attention, decay self-attention, and cross-attention in QA tasks.