Hierarchical neural network: Integrate divide-and-conquer and unified approach for argument unit recognition and classification

Page view(s)
40
Checked on Feb 17, 2024
Hierarchical neural network: Integrate divide-and-conquer and unified approach for argument unit recognition and classification
Title:
Hierarchical neural network: Integrate divide-and-conquer and unified approach for argument unit recognition and classification
Journal Title:
Information Sciences
Publication Date:
20 December 2022
Citation:
Fu, Y., Wang, S., Li, X., Li, D., Li, Y., Liao, J., & Zheng, J. (2023). Hierarchical neural network: Integrate divide-and-conquer and unified approach for argument unit recognition and classification. Information Sciences, 624, 796–810. https://doi.org/10.1016/j.ins.2022.12.050
Abstract:
Argument unit recognition and classification (AURC) is a promising and critical research topic in argument mining, which aims to extract the argument units that express support or opposing stance in a given argumentative text under controversial topics. Existing studies treated the AURC as a sequence labeling problem and designed a unified approach to predict argument unit boundary and argument unit stance simultaneously. In this paper, we propose a general framework hierarchical neural network (HNN) for AURC, by fusing two different approach: divide-and-conquer approach and unified approach. The divide-and-conquer approach considers the correlation of the two tasks inherent in AURC (task 1: argument unit recognition, AUR and task 2: argument unit classification, AUC), and jointly optimize them for prediction by a novel probability transition matrix. Finally, we used a token-level attention mechanism to efficiently fuse probability distributions obtained by our proposed divide-and-conquer approach and existing unified approach. Experimental results on two benchmark datasets demonstrate the effectiveness of our proposed framework.
License type:
Attribution-NonCommercial-NoDerivatives 4.0 International (CC BY-NC-ND 4.0)
Funding Info:
This research is supported by core funding from: I2R CORE FUNDING
Grant Reference no. : Nil

Supported by the National Natural Science Foundation of China (62076158, 62072294, 62106130, 61906112), Natural Science Foundation of Shanxi Province, China (20210302124084), Scientific and Technological Innovation Programs of Higher Education Institutions in Shanxi (2021L284).
Description:
ISSN:
0020-0255
Files uploaded:

File Size Format Action
submission.pdf 577.09 KB PDF Request a copy