The task of argumenation mining involves identifying the different aspects of the argumentation structure of a text, i.e. finding the central claim of a text, supporting reasons, possible objections and counters to those objections. Ultimately, the goal is to integrate the different argumentative elements and relations in a global argumentation structure spanning over the whole text (similar to discourse parsing).
A variety of applications involving automatic text processing can profit from access to the argumentative structure of text: the retrieval of relevant court decisions from legal databases, the analysis of scientific papers in biomedical text mining, automatic document summarization systems, essay scoring systems, as well as opinion mining applications, not only for commercial purposes, but also as a tool for assessing public opinion in political decision-making. To make argumentation structures available for these applications, a robust automatic recognition of it is required, based on resources that have been created in a reproducable fashion with a coding scheme shown to be reliably applied to new instances.
We are currently preparing a special issue of the journal Argument & Computation with follow-up papers of our recent COMMA workshop on the language of argumentation.
The argumentation structure of a text is a graph-like representation of the argumentative relations between the propositions expressed in the segments of the text (i.e. typically sentences or clauses). It identifies the central claim of the text, supporting premises, possible objections and counters to these objections.
Fig. 1: An example argumentation structure
We devised a scheme for annotating argumentation structure (see Peldszus Stede 2013) and developed a tool for annotating it (GraPAT).
We distribute a corpus of short argumentative texts (parallel in English and German; annotated according to the scheme mentioned above) and present results on automatically recognizing the argumentation structures (e.g., Peldszus/Stede 2015). The corpus has also been annotated with discourse structure trees, and we present results on their correlation with argumentation in (Peldszus/Stede 2016).
We also investigate the argumentation in the newspaper editorials of our Potsdam Commentary Corpus. One angle here is to distinguish different "depths" of argumentation, see (Stede 2016).
Fig. 2: Annotating argumentation structure in GraPAT
- arg-microtexts: A German English parallel corpus of 112 short argumentative texts annotated with argumentation structures
- GraPAT: A graph-based, web-based annotation tool suited for sentiment and argumentation structure annotation
- Andreas Peldszus and Manfred Stede. An annotated corpus of argumentative microtexts. In D. Mohammed, and M. Lewinski, editors, Argumentation and Reasoned Action - Proc. of the 1st European Conference on Argumentation, Lisbon, 2015. College Publications, London, 2016. [Bibtex]
- Tatjana Scheffler and Manfred Stede. Realizing argumentative coherence relations in German: a contrastive study of newspaper editorials and Twitter posts. In Proceedings of the COMMA Workshop "Foundations of the Language of Argumentation". Potsdam, Germany, 2016. [Bibtex] [PDF]
- Andreas Peldszus and Manfred Stede. Rhetorical structure and argumentation structure in monologue text. In Proceedings of the 3rd Workshop on Argumentation Mining. Berlin, September 2016. Association for Computational Linguistics. [Bibtex] [PDF]
- Pietro Baroni, Thomas F. Gordon, Tatjana Scheffler, and Manfred Stede. Computational Models of Argument: Proceedings of COMMA 2016 volume 287 of Frontiers in Artificial Intelligence and Applications. IOS Press, 2016. [Bibtex] [PDF]
- K. Budzynska,, M. Janier, B. Konat, J. Kang, C. Reed, P. Saint-Dizier, M. Stede, and O. Yaskorska. Automatically identifying transitions between locutions in dialogue. In D. Mohammed, and M. Lewinski, editors, Argumentation and Reasoned Action - Proc. of the 1st European Conference on Argumentation, Lisbon, 2015. College Publications, London, 2016. [Bibtex]
- Manfred Stede. Toward assessing depth of argumentation. In Proceedings of COLING 2016. Osaka, Japan, 2016. [Bibtex] [PDF]
- Andreas Peldszus and Manfred Stede. Towards detecting counter-considerations in text. In Proceedings of the 2nd Workshop on Argumentation Mining, 104–109. Denver, CO, June 2015. Association for Computational Linguistics. [Bibtex] [PDF]
- Andreas Peldszus and Manfred Stede. Joint prediction in MST-style discourse parsing for argumentation mining. In Proceedings of the 2015 Conference on Empirical Methods in Natural Language Processing (EMNLP), 938–948. Lisbon, Portugal, September 2015. Association for Computational Linguistics. [Bibtex] [PDF]
- K. Budzynska, M. Janier, J. Kang, C. Reed, P. Saint-Dizier, M. Stede, and O. Yakorska. Towards argument mining from dialogue. In Proc. of the Fifth Int'l Conference on Computational Models of Argument (COMMA). 2014. [Bibtex]
- Andreas Peldszus. Towards segment-based recognition of argumentation structure in short texts. In Proceedings of the First Workshop on Argumentation Mining, 88–97. Baltimore, Maryland, June 2014. Association for Computational Linguistics. [Bibtex] [PDF]
- Andreas Peldszus and Manfred Stede. From argument diagrams to argumentation mining in texts: a survey. International Journal of Cognitive Informatics and Natural Intelligence (IJCINI), 7(1):1–31, 2013. [Bibtex] [DOI] [PDF]
- Andreas Peldszus and Manfred Stede. Ranking the annotators: an agreement study on argumentation structure. In Proceedings of the 7th Linguistic Annotation Workshop and Interoperability with Discourse, 196–204. Sofia, Bulgaria, August 2013. Association for Computational Linguistics. [Bibtex] [PDF]
- Manfred Stede and Antje Sauermann. Linearization of arguments in commentary text. In Proceedings of the Workshop on Multidisciplinary Approaches to Discourse (MAD). Oslo, 2008. [Bibtex]