Classifying Argumentative Relations Using Logical Mechanisms and Argumentation Schemes
While argument mining has achieved significant success in classifying argumentative relations between statements (support, attack, and neutral), we have a limited computational understanding of logical mechanisms that constitute those relations. Most recent studies rely on black-box...
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
The MIT Press
2021-01-01
|
| Series: | Transactions of the Association for Computational Linguistics |
| Online Access: | https://direct.mit.edu/tacl/article/doi/10.1162/tacl_a_00394/106790/Classifying-Argumentative-Relations-Using-Logical |
| _version_ | 1817988054876422144 |
|---|---|
| author | Yohan Jo Seojin Bang Chris Reed Eduard Hovy |
| author_facet | Yohan Jo Seojin Bang Chris Reed Eduard Hovy |
| author_sort | Yohan Jo |
| collection | DOAJ |
| description |
While argument mining has achieved significant success in classifying argumentative relations between statements (support, attack, and neutral), we have a limited computational understanding of logical mechanisms that constitute those relations. Most recent studies rely on black-box models, which are not as linguistically insightful as desired. On the other hand, earlier studies use rather simple lexical features, missing logical relations between statements. To overcome these limitations, our work classifies argumentative relations based on four logical and theory-informed mechanisms between two statements, namely, (i) factual consistency, (ii) sentiment coherence, (iii) causal relation, and (iv) normative relation. We demonstrate that our operationalization of these logical mechanisms classifies argumentative relations without directly training on data labeled with the relations, significantly better than several unsupervised baselines. We further demonstrate that these mechanisms also improve supervised classifiers through representation learning. |
| first_indexed | 2024-04-14T00:29:28Z |
| format | Article |
| id | doaj.art-ad87f2331e6749f2bab79167b966d2a8 |
| institution | Directory Open Access Journal |
| issn | 2307-387X |
| language | English |
| last_indexed | 2024-04-14T00:29:28Z |
| publishDate | 2021-01-01 |
| publisher | The MIT Press |
| record_format | Article |
| series | Transactions of the Association for Computational Linguistics |
| spelling | doaj.art-ad87f2331e6749f2bab79167b966d2a82022-12-22T02:22:34ZengThe MIT PressTransactions of the Association for Computational Linguistics2307-387X2021-01-01972173910.1162/tacl_a_00394Classifying Argumentative Relations Using Logical Mechanisms and Argumentation SchemesYohan Jo0Seojin Bang1Chris Reed2Eduard Hovy3School of Computer Science, Carnegie Mellon University, United States. yohanj@andrew.cmu.eduSchool of Computer Science, Carnegie Mellon University, United States. seojinb@andrew.cmu.eduCentre for Argument Technology, University of Dundee, United Kingdom. ehovy@andrew.cmu.eduSchool of Computer Science, Carnegie Mellon University, United States. c.a.reed@dundee.ac.kr While argument mining has achieved significant success in classifying argumentative relations between statements (support, attack, and neutral), we have a limited computational understanding of logical mechanisms that constitute those relations. Most recent studies rely on black-box models, which are not as linguistically insightful as desired. On the other hand, earlier studies use rather simple lexical features, missing logical relations between statements. To overcome these limitations, our work classifies argumentative relations based on four logical and theory-informed mechanisms between two statements, namely, (i) factual consistency, (ii) sentiment coherence, (iii) causal relation, and (iv) normative relation. We demonstrate that our operationalization of these logical mechanisms classifies argumentative relations without directly training on data labeled with the relations, significantly better than several unsupervised baselines. We further demonstrate that these mechanisms also improve supervised classifiers through representation learning.https://direct.mit.edu/tacl/article/doi/10.1162/tacl_a_00394/106790/Classifying-Argumentative-Relations-Using-Logical |
| spellingShingle | Yohan Jo Seojin Bang Chris Reed Eduard Hovy Classifying Argumentative Relations Using Logical Mechanisms and Argumentation Schemes Transactions of the Association for Computational Linguistics |
| title | Classifying Argumentative Relations Using Logical Mechanisms and Argumentation Schemes |
| title_full | Classifying Argumentative Relations Using Logical Mechanisms and Argumentation Schemes |
| title_fullStr | Classifying Argumentative Relations Using Logical Mechanisms and Argumentation Schemes |
| title_full_unstemmed | Classifying Argumentative Relations Using Logical Mechanisms and Argumentation Schemes |
| title_short | Classifying Argumentative Relations Using Logical Mechanisms and Argumentation Schemes |
| title_sort | classifying argumentative relations using logical mechanisms and argumentation schemes |
| url | https://direct.mit.edu/tacl/article/doi/10.1162/tacl_a_00394/106790/Classifying-Argumentative-Relations-Using-Logical |
| work_keys_str_mv | AT yohanjo classifyingargumentativerelationsusinglogicalmechanismsandargumentationschemes AT seojinbang classifyingargumentativerelationsusinglogicalmechanismsandargumentationschemes AT chrisreed classifyingargumentativerelationsusinglogicalmechanismsandargumentationschemes AT eduardhovy classifyingargumentativerelationsusinglogicalmechanismsandargumentationschemes |