Argumentation is omnipresent in our daily communication and an important part of each decision making process. The recent research field of Argumentation Mining aims at automatically recognizing argumentation structures in written discourse in order to establish new intelligent systems for facilitating information access, writing skills acquisition and text summarization. This research area includes the following objectives:

  • Identifying argument components in different text types

  • Recognizing relations between argument components

  • Automatic assessment of argumentation quality

The research at UKP focuses on analyzing argumentation structures in written discourse. Our recent work is concerned with the analysis of argumentation structures in user-generated Web content (Habernal & Gurevych, 2015), scientific articles (Kirschner et al., 2015), and student texts (Stab & Gurevych, 2014).

Current Projects

  • Argumentative Writing Support (AWS): The goal of this project is to develop a novel writing assistance system in order to support authors in writing persuasive arguments and to improve their writing skills.

  • Large-scale argumentation mining on the Web: We aim at analyzing argumentation in various types of user-generated Web content, such as comments to articles, discussion forums, or blogs with the goal to overcome the current information overload and support users in decision-making.

  • Knowledge extraction and consolidation: This project focuses on the analysis of argumentation structures in scientific publications on a fine-grained level. The goal is to reveal how an author connects her thoughts in order to create a convincing line of argumentation. Such a fine-grained analysis of the argumentation structure will enable new ways information access, and could be integrated, for example, in summarization or faceted search applications as part of digital libraries.

  • ArguAna: Argumentation mining deals with the automatic identification of arguments and their relations from natural language text. This research project targets at the specific challenges of argumentation mining for the web. We seek to establish foundations of algorithms that apply argument mining to various forms of web argumentation, efficiently leverage the scale of the web, and complement argumentation mining with an argumentation analysis to effectively assess important quality dimensions.



  • Argument Annotated Essays: A corpus of persuasive essays annotated with argumentation structures.
  • Argument Annotated Essays (version 2): An extended corpus of persuasive essays annotated with argumentation structures.
  • Argument Annotated User-Generated Web Discourse: A corpus contains user comments, forum posts, blogs and newspaper articles annotated with argument scheme based on extended Toulmin's model
  • Argument Annotated News Articles: A corpus of German documents on controversial educational topics (crawled from the Web, ca. 80% news articles) annotated with arguments according to the claim-premises scheme.
  • Argument Annotated Scientific Articles: A corpus of German scientific articles from the field of educational research, annotated with graph-structures of argumentative relations.
  • UKPConvArg1 Corpus: A corpus of 16k pairs of arguments for studying convincingness of Web arguments, as presented in our ACL 2016 paper.
  • UKPConvArg2 Corpus: A crowd-sourced corpus containing 9,111 argument pairs, multi-labeled with 17 classes, which was cleaned and curated by employing several strict quality measures. We proposed two tasks on this data set in our EMNLP 2016 paper, namely predicting the full label distribution and  classifying types of flaws in less convincing arguments.
  • Opposing Arguments: A corpus of 402 persuasive essays annotated with myside biases.
  • Insufficiently Supported Arguments: A corpus of 1,029 arguments annotated with the sufficiency criterion.


Reference publications

Argumentative Writing Support by means of Natural Language Processing

Author Christian Stab
Date March 2017
Kind Phdthesis
LocationDarmstadt, Germany
Research Areas Ubiquitous Knowledge Processing, reviewed, UKP_a_ArMin, AIPHES
Abstract Persuasive essay writing is a powerful pedagogical tool for teaching argumentation skills. So far, the provision of feedback about argumentation has been considered a manual task since automated writing evaluation systems are not yet capable of analyzing written arguments. Computational argumentation, a recent research field in natural language processing, has the potential to bridge this gap and to enable novel argumentative writing support systems that automatically provide feedback about the merits and defects of written arguments. The automatic analysis of natural language arguments is, however, subject to several challenges. First of all, creating annotated corpora is a major impediment for novel tasks in natural language processing. At the beginning of this research, it has been mostly unknown whether humans agree on the identification of argumentation structures and the assessment of arguments in persuasive essays. Second, the automatic identification of argumentation structures involves several interdependent and challenging subtasks. Therefore, considering each task independently is not sufficient for identifying consistent argumentation structures. Third, ordinary arguments are rarely based on logical inference rules and are hardly ever in a standardized form which poses additional challenges to human annotators and computational methods. To approach these challenges, we start by investigating existing argumentation theories and compare their suitability for argumentative writing support. We derive an annotation scheme that models arguments as tree structures. For the first time, we investigate whether human annotators agree on the identification of argumentation structures in persuasive essays. We show that human annotators can reliably apply our annotation scheme to persuasive essays with substantial agreement. As a result of this annotation study, we introduce a unique corpus annotated with fine-grained argumentation structures at the discourse-level. Moreover, we present a novel end-to-end approach for parsing argumentation structures. We identify the boundaries of argument components using sequence labeling at the token level and propose a novel joint model that globally optimizes argument component types and argumentative relations for identifying consistent argumentation structures. We show that our model considerably improves the performance of local base classifiers and significantly outperforms challenging heuristic baselines. In addition, we introduce two approaches for assessing the quality of natural language arguments. First, we introduce an approach for identifying myside biases which is a well-known tendency to ignore opposing arguments when formulating arguments. Our experimental results show that myside biases can be recognized with promising accuracy using a combination of lexical features, syntactic features and features based on adversative transitional phrases. Second, we investigate for the first time the characteristics of insufficiently supported arguments. We show that insufficiently supported arguments frequently exhibit specific lexical indicators. Moreover, our experimental results indicate that convolutional neural networks significantly outperform several challenging baselines.
Website http://tuprints.ulb.tu-darmstadt.de/6006/
[Export this entry to BibTeX]

Important Copyright Notice:

The documents contained in these directories are included by the contributing authors as a means to ensure timely dissemination of scholarly and technical work on a non-commercial basis. Copyright and all rights therein are maintained by the authors or by other copyright holders, notwithstanding that they have offered their works here electronically. It is understood that all persons copying this information will adhere to the terms and constraints invoked by each author's copyright. These works may not be reposted without the explicit permission of the copyright holder.

Cooperation partners

  • Educational Testing Service (NLP division)

  • Prof. Fischer (network of excellence)

  • Prof. Dr. Benno Stein

  • Macmillan Science and Education

Primary Contact

A A A | Drucken Print | Impressum Impressum | Sitemap Sitemap | Suche Search | Kontakt Contact | Webseitenanalyse: Mehr Informationen
zum Seitenanfangzum Seitenanfang