ArguAna: Argumentation Analysis for the Web

Motivation

arguana logo

Many questions in real life do not have a clear answer but are subject to controversy, e.g., who is right in some political discussion or what is the best product for a particular purpose. Controversy is the central concept that fosters argumentation. Argumentation includes to exchange ideas and opinions, to defend positions, and to convince others of certain stances.Nowadays, in a vast number of situations, a search for relevant arguments is performed on the web, which is considered the richest and most up-to-date source of information, and which is a dynamic environment for controversial topics. While today’s search engines achieve to rank links to the most relevant web pages highest for a large proportion of search queries, a web search for arguments is not explicitly envisaged.

 

Goals

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

  1. apply argument mining to various forms of web argumentation,
  2. efficiently leverage the scale of the web, and
  3. complement argumentation mining with an argumentation analysis to effectively assess important quality dimensions.

The rationale of the project is that people compare arguments in many decision-making situations, e.g., when buying products or when forming opinions on political controversies. Nowadays, the richest and most up-to-date argument source is the web. However, searching for arguments on the web is challenging, as dozens of web pages need to be read through in order to identify and relate the relevant arguments. State-of-the-art research on argumentation mining tackles the identification and relation of arguments within a particular domain, but it does not suffice to successfully mine argumentation on the web.

 

Overview of the foci of the four objectives (left) with respect to the three main research questions (top)
as well as the responsibilities of the Webis group and UKP group in the resulting eight work packages (right).

Methods

In this project, we aim to evolve models from argumentation theory to make them comply with major forms of web argumentation. Then, we will create annotated corpora with tens of thousands of argumentative web texts. To keep the annotation effort tractable, we plan to employ distant supervision and games with a purpose. Based on the corpora, we will develop and evaluate novel algorithms that mine web argumentation and that learn patterns in it, which affect measurable quality dimensions. While the size of the corpora raises the need for efficiency, it will also bring unprecedented statistical insights into web argumentation across domains.

We expect to obtain new knowledge about common, good, and bad ways in which people argue on the web, thereby bridging the existing gap between theory and the practical use of argumentation. The created corpora will serve as valuable resources for other researchers, and the algorithms will be able to mine argumentation that meets specific quality constraints from web texts. We believe that leveraging such argumentation will shape the future of the web search.

 

Team

Partners

This project is established in cooperation with Webis: Web Technology and Information Systems Group, Bauhaus-Universität Weimar.

 

Publications

Additional Attributes

Type

The Argument Reasoning Comprehension Task

Ivan Habernal, Iryna Gurevych, Henning Wachsmuth, Benno Stein
August 2017
[Online-Edition: https://github.com/UKPLab/argument-reasoning-comprehension-task]
[Techreport]

Funding

This project is funded by Deutsche Forschungsgemeinschaft (German Research Foundation).

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