Automatic Argumentation Extraction

Sergeant, Alan

doi:10.1007/978-3-642-38288-8_46

Cited by 4 publications

(3 citation statements)

References 9 publications

(11 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Most of the existing argumentation mining methods focus solely on the identification of argument components. However, identifying argumentative discourse structures is an important task (Sergeant, 2013) in particular for providing feedback about argumentation. First, argumentative discourse structures are essential for evaluating the quality of an argument, since it is not possible to examine how well a claim is justified without knowing which premises belong to it.…”

Section: Introductionmentioning

confidence: 99%

Identifying Argumentative Discourse Structures in Persuasive Essays

Stab

Gurevych

2014

Proceedings of the 2014 Conference on Empirical Methods in Natural Language Processing (EMNLP)

297

307

View full text Add to dashboard Cite

In this paper, we present a novel approach for identifying argumentative discourse structures in persuasive essays. The structure of argumentation consists of several components (i.e. claims and premises) that are connected with argumentative relations. We consider this task in two consecutive steps. First, we identify the components of arguments using multiclass classification. Second, we classify a pair of argument components as either support or non-support for identifying the structure of argumentative discourse. For both tasks, we evaluate several classifiers and propose novel feature sets including structural, lexical, syntactic and contextual features. In our experiments, we obtain a macro F1-score of 0.726 for identifying argument components and 0.722 for argumentative relations.

show abstract

Section: Introductionmentioning

confidence: 99%

Identifying Argumentative Discourse Structures in Persuasive Essays

Stab

Gurevych

2014

Proceedings of the 2014 Conference on Empirical Methods in Natural Language Processing (EMNLP)

297

307

View full text Add to dashboard Cite

show abstract

“…In this context, the unstructured texts correspond to briefs presented by various authors in a public hearing process to a commission (decision making body) who must produce a report containing a conclusion. At the present time, when dealing with unstructured text, content analysis for argument and value extraction and definition has to be conducted manually, as in PulfreyTaylor et al (2011), since no automatic tools for argument mining from unstructured text exist yet (Boltužić 2013;Sergeant 2013).…”

Section: Content Analysis For Argument Constructionmentioning

confidence: 98%

Value-based argumentation for policy decision analysis: methodology and an exploratory case study of a hydroelectric project in Québec

Tremblay

Abi‐Zeid

2015

Ann Oper Res

View full text Add to dashboard Cite

In many countries, development projects that may have a substantial impact on the environment are submitted to a public evaluation process within which citizens use argumentation to express and justify their positions regarding a project. These justifications typically refer to various values. Subsequently, a public commission in charge of the evaluation process arrives at a conclusion. But how are the arguments of the various participants taken into account? How do values influence the commission's recommendation? In order to arrive to an understanding of a commission's decision process, we focus on the argumentative nature of the process and apply a methodology combining content analysis and a value-based argumentative framework. This methodology was illustrated using a case study of a hydroelectric project in Québec. First, we analysed a corpus of unstructured texts produced during public hearings and extracted the arguments and values of the participants. We then used a computational model to obtain the commission's possible hypothetical decisions which we compared with the commission's actual conclusion. Furthermore, we identified some preference elements of the commission, and we partially explained their attitude towards conflicting and incoherent arguments. Finally, based on our experience, we formulated some conclusions regarding the ability and promise of argumentative methods to support decision making in a participatory context.

show abstract

“…gumentative relation mining -beyond argument component mining -is perceived as an essential step towards more fully identifying the argumentative structure of a text (Peldszus and Stede, 2013;Sergeant, 2013;Stab et al, 2014). Consider the second paragraph shown in Figure 1.…”

Section: Introductionmentioning

confidence: 99%

Context-aware Argumentative Relation Mining

Nguyen¹,

Litman²

2016

Proceedings of the 54th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)

View full text Add to dashboard Cite

Context is crucial for identifying argumentative relations in text, but many argument mining methods make little use of contextual features. This paper presents contextaware argumentative relation mining that uses features extracted from writing topics as well as from windows of context sentences. Experiments on student essays demonstrate that the proposed features improve predictive performance in two argumentative relation classification tasks.

show abstract

Automatic Argumentation Extraction

Cited by 4 publications

References 9 publications

Identifying Argumentative Discourse Structures in Persuasive Essays

Identifying Argumentative Discourse Structures in Persuasive Essays

Value-based argumentation for policy decision analysis: methodology and an exploratory case study of a hydroelectric project in Québec

Context-aware Argumentative Relation Mining

Contact Info

Product

Resources

About