A Pilot Study on Argument Simplification in Stance-Based Opinions



Rajendran, Pavithra, Bollegala, Danushka ORCID: 0000-0003-4476-7003 and Parsons, Simon
(2020) A Pilot Study on Argument Simplification in Stance-Based Opinions. In: International Conference of the Pacific Association for Computational Linguistics, 2019-10-11 - 2019-10-13, Hanoi, Vietnam.

[img] Text
Pavithra_PACLING_2019.pdf - Accepted Version

Download (268kB) | Preview

Abstract

Prior work has investigated the problem mining arguments from online reviews by classifying opinions based on the stance expressed explicitly or implicitly. An implicit opinion has the stance left unexpressed linguistically while an explicit opinion has the stance expressed explicitly. In this paper, we propose a bipartite graph-based approach to relate a given set of explicit opinions as simplified arguments for a given set of implicit opinions using three different features (a) sentence similarity, (b) sentiment and (c) target. Experiments are carried out on a manually annotated set of explicit-implicit opinions and show that unsupervised sentence representations can be used to accurately match arguments with their corresponding simplified versions.

Item Type: Conference or Workshop Item (Unspecified)
Uncontrolled Keywords: Argument mining, Argument simplification
Depositing User: Symplectic Admin
Date Deposited: 28 Aug 2020 07:59
Last Modified: 13 Dec 2021 19:11
DOI: 10.1007/978-981-15-6168-9_19
Related URLs:
URI: https://livrepository.liverpool.ac.uk/id/eprint/3099006