• français
    • English
    français
  • Login
Help
View Item 
  •   Home
  • Institut de Recherche de l’École navale (IRENAV)
  • View Item
  • Home
  • Institut de Recherche de l’École navale (IRENAV)
  • View Item
JavaScript is disabled for your browser. Some features of this site may not work without it.

DRGAT: Dual-relational graph attention networks for aspect-based sentiment classification

Article dans une revue avec comité de lecture
Author
YOU, Lan
313820 Hubei University
PENG, Jiaheng
313820 Hubei University
JIN, Hong
313820 Hubei University
ccCLARAMUNT, Christophe
13094 Institut de Recherche de l'Ecole Navale [IRENAV]
ZENG, Haoqiu
313820 Hubei University
ZHANG, Zhen
313820 Hubei University

URI
http://hdl.handle.net/10985/25202
DOI
10.1016/j.ins.2024.120531
Date
2024-03-28
Journal
Information Sciences

Abstract

Aspect-based sentiment classification has become a popular topic in natural language processing. Exploiting dependency syntactic information with graph neural networks has recently become a popular trend. Despite their success, methods that rely heavily on a dependency tree face major challenges. This concerns the alignment of aspects and their word sentiments due to the richness of the language and the fact that a dependency tree might produce noisy signals from unrelated associations. This paper introduces a Dual-Relational Graph Attention Network (DRGAT) that fully exploits syntactic structural information and then the sentiment-aware context (e.g., phrase segmentation and hierarchical structure) of the constituent tree of a sentence. Additional constituency and dependency attention mechanisms provide comprehensive syntactic information across words, thereby enabling an accurate connection between aspect words and corresponding sentiment words. Considering that the original parsed constituency tree may have a large depth, this could lead to words being far apart increasing the computational overhead. The constituency tree of each sentence is dynamically reconstructed by determining the importance of each relational node. Extensive experimental results on six English datasets demonstrated that fully exploiting syntactic information can achieve excellent sentiment classification results.

Files in this item

Name:
IRENAV_ISCIENCE_2024_Claramunt.pdf
Size:
1.830Mb
Format:
PDF
Embargoed until:
2024-10-01
View/Open

Collections

  • Institut de Recherche de l’École navale (IRENAV)

Related items

Showing items related by title, author, creator and subject.

  • Un modèle spatio-temporel sémantique pour la modélisation de mobilités en milieu urbain 
    Article dans une revue avec comité de lecture
    JIN, Meihan; ccCLARAMUNT, Christophe (Lavoisier, 2018)
    The continuous development and complexity of many modern cities offer many research challenges for urban scientists searching for a better understanding of mobility patterns that happen in space and time. Today, very large ...
  • A semantic model for human mobility in an urban region 
    Article dans une revue avec comité de lecture
    JIN, Meihan; ccCLARAMUNT, Christophe (2018)
    The continuous development and complexity of many modern cities offer many research challenges for urban scientists searching for a better understanding of mobility patterns that happen in space and time. Today, very large ...
  • TripCube: A Trip-oriented vehicle trajectory data indexing structure 
    Article dans une revue avec comité de lecture
    XU, Tao; ZHANG, Xihui; ccCLARAMUNT, Christophe; XIANG, LI (Elsevier, 2018)
    With the dramatic development of location-based services, a large amount of vehicle trajectory data are available and applied to different areas,while there are still many research challenges left, one of thembeing data ...
  • Microstructure, segregation and mechanical properties of A356 alloy components fabricated by rheo-HPDC combined with the swirled enthalpy equilibration device (SEED) process 
    Article dans une revue avec comité de lecture
    GU, Guo-Chao; XIANG, Li-Xin; LI, Rui-Fen; ZHENG, Hong-Liang; LU, Yu-Peng; ccPESCI, Raphaël (Elsevier BV, 2023-09)
    The challenges commonly associated with conventional high pressure die casting (HPDC) have led to increased interest in semi-solid metal (SSM) forming processes. In the present study, semi-solid slurries of A356 alloy ...
  • Dynamic Behaviors of Couple Stress Quadrilateral Thick Microplates within a Refined DQFE Framework 
    Article dans une revue avec comité de lecture
    PENG, Zihao; ZHANG, Bo; JEBAHI, Mohamed; WEN, Pengjun; LI, Cheng; ZHANG, Xu (World Scientific Pub Co Pte Ltd, 2025-03)
    This study proposes a novel refined differential quadrature finite element (DQFE) framework for the size-dependent dynamic analysis of thick quadrilateral microplates, incorporating couple-stress effect and two kinematic ...

Browse

All SAMCommunities & CollectionsAuthorsIssue DateCenter / InstitutionThis CollectionAuthorsIssue DateCenter / Institution

Newsletter

Latest newsletterPrevious newsletters

Statistics

Most Popular ItemsStatistics by CountryMost Popular Authors

ÉCOLE NATIONALE SUPERIEURE D'ARTS ET METIERS

  • Contact
  • Mentions légales

ÉCOLE NATIONALE SUPERIEURE D'ARTS ET METIERS

  • Contact
  • Mentions légales