Argumentation Mining

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.

News

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.

Argumentation Structure

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.

Argumenation structure example
Fig. 1: An example argumentation structure

Contributions

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).

Annotating in GraPAT
Fig. 2: Annotating argumentation structure in GraPAT

Related Resources

Related publications: