CONFERENCE PROCEEDINGS
Advanced Search
Home > Proceedings > Volume 12596 > Article
Paper
28 February 2023 Connective-aware interaction attention for implicit discourse relation classification
Yatian Shen, Ning Liu
Author Affiliations +
Proceedings Volume 12596, International Conference on Mechatronics Engineering and Artificial Intelligence (MEAI 2022); 125961Y (2023) https://doi.org/10.1117/12.2672170
Event: International Conference on Mechatronics Engineering and Artificial Intelligence (MEAI 2022), 2022, Changsha, China
Abstract
Implicit discourse relation classification, identifying relationships between arguments without explicit linguistic cues, is a challenging task. Previous studies have shown that connectives are important for recognizing implicit discourse relations. Most previous works applied connective prediction as an auxiliary task to promote knowledge transfer from connectives to labels which did not make full use of the relational mapping information of connectives. In this work, we propose an innovative Connective-aware Interactive Attention (CAIA) joint learning approach. Specifically, we use BERT to predict connectives and incorporate connective information into the interaction of the attention mechanism. Our experimental results on the PDTB dataset show that our approach achieves competitive results compared to recent state-of-the-art systems.
© (2023) COPYRIGHT Society of Photo-Optical Instrumentation Engineers (SPIE). Downloading of the abstract is permitted for personal use only.
Citation Download Citation
Yatian Shen and Ning Liu "Connective-aware interaction attention for implicit discourse relation classification", Proc. SPIE 12596, International Conference on Mechatronics Engineering and Artificial Intelligence (MEAI 2022), 125961Y (28 February 2023); https://doi.org/10.1117/12.2672170
ACCESS THE FULL ARTICLE
ORGANIZATIONAL
Sign in with credentials provided by your organization.
INSTITUTIONAL
Select your institution to access the SPIE Digital Library.
SELECT YOUR INSTITUTION
PERSONAL
Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.
PERSONAL SIGN IN
No SPIE Account? Create one
PURCHASE THIS CONTENT
SUBSCRIBE TO DIGITAL LIBRARY
50 downloads per 1-year subscription
Members: $195
Non-members: $335 ADD TO CART
25 downloads per 1 - year subscription
Members: $145
Non-members: $250 ADD TO CART
PURCHASE SINGLE ARTICLE
Includes PDF, HTML & Video, when available
Members: $17.00
Non-members: $21.00 ADD TO CART
PROCEEDINGS
 5 PAGES
DOWNLOAD PAPER SAVE TO MY LIBRARY
GET CITATION
Advertisement
Advertisement
RIGHTS & PERMISSIONS
Get copyright permission  Get copyright permission on Copyright Marketplace
KEYWORDS
Ablation
Neural networks
Feature extraction
Connectors
Network architectures
Transformers
RELATED CONTENT
Subscribe to Digital Library
Receive Erratum Email Alert
Back to Top