Combining classification-centered and relation-based argument mining methods

Andrew Henninga; Anthony P. Younga; Elizabeth Sklar; Simon Milesa; Elizabeth Blacka

Combining classification-centered and relation-based argument mining methods

Andrew Henninga, Anthony P. Younga, Elizabeth Sklar, Simon Milesa, Elizabeth Blacka

Research output: Contribution to journal › Conference article › peer-review

Abstract

Two key tasks in argument mining (AM) are classification of argument components and identification of relations between argument components. Approaches to solving the argument component classification problem typically take a supervised learning approach, however a lack of suitable datasets makes this a challenge for identification of argument component relations. We propose a pipeline with a recurrent, branched structure that combines supervised learning of argument component classifications with NLP approaches to identification of argument component relations, with the aim of improving both classification of argument components (i.e. premises and claims) and identification of support relationships between components.

Original language	English
Pages (from-to)	135-139
Number of pages	5
Journal	CEUR Workshop Proceedings
Volume	2528
Publication status	Published - Nov 2019
Event	3rd Workshop on Advances In Argumentation In Artificial Intelligence, AI^3 2019 - Rende, Italy Duration: 19 Nov 2019 → 22 Nov 2019

Keywords

Argument mining
Computational argumentation

Access to Document

http://ceur-ws.org/Vol-2528/12_Henning_et_al_AI3_2019.pdfLicence: CC BY

Cite this

@article{a449cfcb1dab4ab6adb247c4ca5e044a,

title = "Combining classification-centered and relation-based argument mining methods",

abstract = "Two key tasks in argument mining (AM) are classification of argument components and identification of relations between argument components. Approaches to solving the argument component classification problem typically take a supervised learning approach, however a lack of suitable datasets makes this a challenge for identification of argument component relations. We propose a pipeline with a recurrent, branched structure that combines supervised learning of argument component classifications with NLP approaches to identification of argument component relations, with the aim of improving both classification of argument components (i.e. premises and claims) and identification of support relationships between components.",

keywords = "Argument mining, Computational argumentation",

author = "Andrew Henninga and Younga, {Anthony P.} and Elizabeth Sklar and Simon Milesa and Elizabeth Blacka",

year = "2019",

month = nov,

language = "English",

volume = "2528",

pages = "135--139",

journal = "CEUR Workshop Proceedings",

issn = "1613-0073",

publisher = "CEUR-WS",

note = "3rd Workshop on Advances In Argumentation In Artificial Intelligence, AI^3 2019 ; Conference date: 19-11-2019 Through 22-11-2019",

}

TY - JOUR

T1 - Combining classification-centered and relation-based argument mining methods

AU - Henninga, Andrew

AU - Younga, Anthony P.

AU - Sklar, Elizabeth

AU - Milesa, Simon

AU - Blacka, Elizabeth

PY - 2019/11

Y1 - 2019/11

N2 - Two key tasks in argument mining (AM) are classification of argument components and identification of relations between argument components. Approaches to solving the argument component classification problem typically take a supervised learning approach, however a lack of suitable datasets makes this a challenge for identification of argument component relations. We propose a pipeline with a recurrent, branched structure that combines supervised learning of argument component classifications with NLP approaches to identification of argument component relations, with the aim of improving both classification of argument components (i.e. premises and claims) and identification of support relationships between components.

AB - Two key tasks in argument mining (AM) are classification of argument components and identification of relations between argument components. Approaches to solving the argument component classification problem typically take a supervised learning approach, however a lack of suitable datasets makes this a challenge for identification of argument component relations. We propose a pipeline with a recurrent, branched structure that combines supervised learning of argument component classifications with NLP approaches to identification of argument component relations, with the aim of improving both classification of argument components (i.e. premises and claims) and identification of support relationships between components.

KW - Argument mining

KW - Computational argumentation

UR - http://www.scopus.com/inward/record.url?scp=85077821464&partnerID=8YFLogxK

M3 - Conference article

AN - SCOPUS:85077821464

SN - 1613-0073

VL - 2528

SP - 135

EP - 139

JO - CEUR Workshop Proceedings

JF - CEUR Workshop Proceedings

T2 - 3rd Workshop on Advances In Argumentation In Artificial Intelligence, AI^3 2019

Y2 - 19 November 2019 through 22 November 2019

ER -

Combining classification-centered and relation-based argument mining methods

Abstract

Keywords

Access to Document

Other files and links

Fingerprint

Cite this