Linking the Thoughts: Analysis of Argumentation Structures in Scientific Publications

Kirschner, Christian; Eckle‐Kohler, Judith; Gurevych, Iryna

doi:10.3115/v1/w15-0501

Cited by 59 publications

(83 citation statements)

References 24 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…[24,142,157,163], and (2) connecting said arguments through attack and support relations, as in e.g. [105,163]. Continuing our above example, say we wanted to analyse the following excerpt of a fictional news article:…”

Section: Relation-based Argumentation Mining (Rbam)mentioning

confidence: 99%

Using Argumentation to Improve Classification in Natural Language Problems

Carstens

Toni

2017

ACM Trans. Internet Technol.

View full text Add to dashboard Cite

Argumentation has proven successful in a number of domains, including multi-agent systems and decision support in medicine and engineering. We propose its application to a domain yet largely unexplored by argumentation research: computational linguistics. Over the past decade or so advances in this field have commonly relied on data-driven solutions, i.e. machine learning. Recently, however, there appears to be a growing consent that, in order to achieve significant advances in certain areas of artificial intelligence, in general, and computational linguistics, in particular, we may need to consider data-driven approaches in unison with reasoning-, logic-and rule-based solutions. To this end we have developed a novel classification methodology that incorporates reasoning through argumentation with supervised classifiers. We train classifiers and then argue about the validity of their output.To do so we identify arguments that formalise prototypical knowledge of a problem and use them to correct misclassifications. We thus have at our disposal multiple ways of incorporating knowledge in classification and are able to integrate knowledge as it becomes available, without the need to retrain classifiers.We illustrate our methodology on two tasks. On the one hand we address binary cross-domain sentiment polarity classification, where we train classifiers on one corpus, e.g. Tweets, to identify positive/negative polarity, and classify instances from another corpus, e.g. sentences from movie reviews. On the other hand we address a form of argumentation mining that we call Relation-based Argumentation Mining, where we classify pairs of sentences based on whether the first sentence attacks or supports the second, or whether it does neither. Whenever we find that one sentence attacks/supports the other we consider both to be argumentative, irrespective of their stand-alone argumentativeness. For both tasks we improve classification performance when using our methodology, compared to using standard classifiers, only.3

show abstract

Section: Relation-based Argumentation Mining (Rbam)mentioning

confidence: 99%

Using Argumentation to Improve Classification in Natural Language Problems

Carstens

Toni

2017

ACM Trans. Internet Technol.

View full text Add to dashboard Cite

show abstract

“…As far as agreement on detection of argumentative components is concerned, Kirschner et al (2015) point out that measures such as kappa and F1 score may cause some inappropriate penalty for slight differences of annotation between annotators, and proposed a graph-based metric based on pair-wise comparison of predefined argument components. This particular metric, while addressing some of the problems of kappa and F1, is not directly applicable to our annotation where annotators can freely chose the beginnings and ends of spans.…”

Section: Related Workmentioning

confidence: 99%

Annotation of argument structure in Japanese legal documents

Yamada¹,

Teufel²,

Tokunaga³

2017

Proceedings of the 4th Workshop on Argument Mining

View full text Add to dashboard Cite

We propose a method for the annotation of Japanese civil judgment documents, with the purpose of creating flexible summaries of these. The first step, described in the current paper, concerns content selection, i.e., the question of which material should be extracted initially for the summary. In particular, we utilize the hierarchical argument structure of the judgment documents. Our main contributions are a) the design of an annotation scheme that stresses the connection between legal issues (called issue topics) and argument structure, b) an adaptation of rhetorical status to suit the Japanese legal system and c) the definition of a linked argument structure based on legal sub-arguments. In this paper, we report agreement between two annotators on several aspects of the overall task.

show abstract

“…(Sardianos et al, 2015;Oraby et al, 2015)) and three others used different methods (cf. (Kirschner et al, 2015;Yanase et al, 2015;). To calculate the results of argument mining, four papers used accuracy (cf.…”

Section: Related Workmentioning

confidence: 99%

“…In the comparative statistics module we look to extend the solution in (Kirschner et al, 2015) in seven ways, by: (i) Calculating the segmentation differences between two annotations; (ii) Calculating propositional content relations using confusion matrices, accounting for all the nodes within an argument map and accounting for a differing segmentation; (iii) Calculating dialogical content relations (if they are contained in an argument map) using confusion matrices, accounting for all the nodes within an argument map and accounting for a differing segmentation; (iv) Defining the CASS technique to allow calculation scores to be combined; (v) Allowing the use of any metric for the CASS technique, which uses a confusion matrix, to give consistency to the area of argument mining; (vi) Providing results for not just inter-annotator agreement, but also, the comparison of manually annotated corpora against corpora automatically created by argument mining; (vii) Allowing the comparison of analysis given in different annotation schemes but migrated to AIF (e.g. compare text annotated in IAC to the annotation scheme from the Microtext corpus).…”

Section: Comparing Analysismentioning

confidence: 99%

See 1 more Smart Citation

The CASS Technique for Evaluating the Performance of Argument Mining

Duthie¹,

Lawrence²,

Budzyńska³

et al. 2016

Proceedings of the Third Workshop on Argument Mining (ArgMining2016)

View full text Add to dashboard Cite

Argument mining integrates many distinct computational linguistics tasks, and as a result, reporting agreement between annotators or between automated output and gold standard is particularly challenging. More worrying for the field, agreement and performance are also reported in a wide variety of different ways, making comparison between approaches difficult. To solve this problem, we propose the CASS technique for combining metrics covering different parts of the argument mining task. CASS delivers a justified method of integrating results yielding confusion matrices from which CASS-κ and CASS-F1 scores can be calculated.

show abstract

Linking the Thoughts: Analysis of Argumentation Structures in Scientific Publications

Cited by 59 publications

References 24 publications

Using Argumentation to Improve Classification in Natural Language Problems

Using Argumentation to Improve Classification in Natural Language Problems

Annotation of argument structure in Japanese legal documents

The CASS Technique for Evaluating the Performance of Argument Mining

Contact Info

Product

Resources

About