Argument Mining: A Survey

Lawrence, John; Reed, Chris

doi:10.1162/coli_a_00364

Cited by 243 publications

(214 citation statements)

References 170 publications

Supporting

Mentioning

186

Contrasting

Unclassified

Order By: Relevance

“…Consequently, we present a text corpus annotated on the basis of two distinct typologies of schemes: Walton’s taxonomy of argumentation schemes and Wagemans’ Periodic Table of Arguments (PTA). The two resulting annotated corpora should prove useful both for quantitative empirical approaches to the study of argumentation, and to computational research into argument mining—the automated reconstruction of argumentative content in natural language texts of arbitrary length (Stede and Schneider 2018 ; Lawrence and Reed 2019 ).…”

Section: Discussionmentioning

confidence: 99%

“…For this reason, the 2008 system of classifying schemes is to be regarded as a provisional hypothesis that should be subject to improvement as further empirical and analytical work on schemes classification continues. In the ten year interval, the explosion of research on argument mining (Lawrence and Reed 2019 ; Stede and Schneider 2018 ) has raised many fine-grained questions about how particular groups of schemes should be fitted together into the larger picture of any general classification system.…”

Section: Annotation Guidelines For Argument Schemesmentioning

confidence: 99%

“…Argument mining (Stede and Schneider 2018 ; Lawrence and Reed 2019 ) is a rapidly growing field, with an increasing number of methods being developed to automatically process textual data and reconstruct argumentative content. However, most of these techniques are limited by the lack of consistently annotated argument data at sufficiently large scale.…”

Section: Applications Of Annotated Argument Scheme Corporamentioning

confidence: 99%

See 2 more Smart Citations

Annotating Argument Schemes

et al. 2020

Self Cite

View full text Add to dashboard Cite

Argument schemes are abstractions substantiating the inferential connection between premise(s) and conclusion in argumentative communication. Identifying such conventional patterns of reasoning is essential to the interpretation and evaluation of argumentation. Whether studying argumentation from a theory-driven or data-driven perspective, insight into the actual use of argumentation in communicative practice is essential. Large and reliably annotated corpora of argumentative discourse to quantitatively provide such insight are few and far between. This is all the more true for argument scheme corpora, which tend to suffer from a combination of limited size, poor validation, and the use of ad hoc restricted typologies. In the current paper, we describe the annotation of schemes on the basis of two distinct classifications: Walton's taxonomy of argument schemes, and Wagemans' Periodic Table of Arguments. We describe the annotation procedure for each, and the quantitative characteristics of the resulting annotated text corpora. In doing so, we extend the annotation of the preexisting US2016 corpus of televised election debates, resulting in, to the best of our knowledge, the two largest consistently annotated corpora of schemes in argumentative dialogue publicly available. Based on evaluation in terms of inter-annotator agreement, we propose further improvements to the guidelines for annotating schemes: the argument scheme key, and the Argument Type Identification Procedure.

show abstract

Section: Discussionmentioning

confidence: 99%

Section: Annotation Guidelines For Argument Schemesmentioning

confidence: 99%

Section: Applications Of Annotated Argument Scheme Corporamentioning

confidence: 99%

See 1 more Smart Citation

Annotating Argument Schemes

et al. 2020

Self Cite

View full text Add to dashboard Cite

show abstract

“…Argument mining (e.g. [23,24]) seeks to identify and extract structured, self-contained arguments and inter-argument relationships from natural language text to (amongst many other applications) resolve conflicting points of view expressed in online debates (e.g. [6,7]).…”

Section: Argument Mining and The Analysis Of Online Debatesmentioning

confidence: 99%

Ranking comment sorting policies in online debates

Young

Joglekar

Boschi

et al. 2021

AAC

View full text Add to dashboard Cite

Online debates typically possess a large number of argumentative comments. Most readers who would like to see which comments are winning arguments often only read a part of the debate. Many platforms that host such debates allow for the comments to be sorted, say from the earliest to latest. How can argumentation theory be used to evaluate the effectiveness of such policies of sorting comments, in terms of the actually winning arguments displayed to a reader who may not have read the whole debate? We devise a pipeline that captures an online debate tree as a bipolar argumentation framework (BAF), which is sorted depending on the policy, giving a sequence of induced sub-BAFs representing how and how much of the debate has been read. Each sub-BAF has its own set of winning arguments, which can be quantitatively compared to the set of winning arguments of the whole BAF. We apply this pipeline to evaluate policies on Kialo debates, where it is shown that reading comments from most to least liked, on average, displays more winners than reading comments earliest first. Therefore, in Kialo, reading comments from most to least liked is on average more effective than reading from the earliest to the most recent.

show abstract

“…The implemented argument mining technology automatically extracts the argumentative content from the news articles -provided the chosen article has any explicit argumentative content in it to begin with. Argument mining builds on the successes of Opinion Mining and Sentiment Analysis [7] to identify not only what views are being expressed in a text, but also why those views are held [4] -the software automatically processes the natural language text to produce the analysis otherwise performed by human experts.…”

Section: Argument Mining For Reason-checkingmentioning

confidence: 99%