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 arguments 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 arguments and their components in different text types
- Recognizing argumentative relations between arguments and their components
- Automatic assessment of argumentation quality
Our recent work is concerned, amongst others, with language adaptation of argument mining methods (Eger et al. 2017) and the extraction of arguments from heterogeneous text types (Stab et al. 2018).
Large-scale UKP projects
- ArgumenText: In this project, we aim to generalize argument mining to various different text types and to validate the latest models in industrial applications. More information about the project can be found on argumentext.de.
Collaborative Projects with external Partners
- 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 (learn more).
- Kritis: The goal of Kritis is to investigate critical infrastructures, their construction, functional crises and the protection in cities. Within this interdisciplinary Research Training Group, we investigate novel interactive machine learning methods for extracting arguments and argumentative structures from historical tests (learn more).
- Famulus: The interdisciplinary Famulus project aims to study how online case simulations that provide automatic adaptive feedback can foster students' diagnostic skills. To generate automatic feedback, we will develop novel methods for identifying and evaluating diagnostic reasoning in student essays (learn more).
- Aiphes: Within this Research Training Group Aiphes we develop novel, we develop novel claim validation methods by extracting evidence from various online sources. Our vision is to develop novel approaches for supporting the laborious task of uncovering fake news (learn more).
- 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.
- Iryna Gurevych, Christian Stab, and Ivan Habernal are organizing “Argument Mining”, a course to be held at the Second Summer School on Argumentation: Computational and Linguistic Perspectives (SSA'16) in Potsdam.
- Iryna Gurevych of the UKP Lab is co-organizing “NLP Approaches to Computational Argumentation”, a tutorial to be held at ACL 2016 in Berlin.
- Iryna Gurevych of the UKP Lab is co-organizing the 3rd Workshop on Argument Mining, to be held at ACL 2016 in Berlin.
To highlight the importance of, and close connection with, the emerging area of Debating Technologies, the workshop will introduce a Special Track on Debating Technologies, co-managed by Prof. Gurevych. The workshop also includes an Unshared Task on Argument Mining, co-chaired by Prof. Gurevych and Ivan Habernal.
- Iryna Gurevych of the UKP Lab co-organized “Debating Technologies”, a five-day seminar held on 13 to 18 December 2015 at the Leibniz-Zentrum für Informatik in Dagstuhl.
- Existing Resources for Debating Technologies (joint talk by Ivan Habernal and Christian Stab), Dagstuhl Seminar on Debating Technologies, Wadern, Germany, December 2015 (slides in PDF)
- Detecting Argument Components and Structures (joint talk by Christian Stab and Ivan Habernal), Dagstuhl Seminar on Debating Technologies, Wadern, Germany, December 2015 (slides in PDF)
- A brief introduction to argument(ation) mining (talk by Iryna Gurevych), Dagstuhl Seminar on Debating Technologies, Wadern, Germany, December 2015 (slides in PDF)
- Iryna Gurevych of the UKP Lab co-organized the 2nd Workshop on Argumentation Mining, which was held on 4 June 2015 at NAACL 2015 in Denver, Colorado.
- UKP Sentential Argument Mining Corpus: A corpus of heterogeneous web content including 25,492 annotated sentences over eight controversial topics.
- 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.