Article on argumentation mining accepted for publication in Computational Linguistics journal
2016/06/20

The article “” by Argumentation Mining in User-Generated Web Discourse and Ivan Habernal has been accepted for publication in the Computational Linguistics journal. Iryna Gurevych
is the longest-running publication devoted exclusively to the computational and mathematical properties of language and the design and analysis of natural language processing systems. From this highly-regarded quarterly, university and industry linguists, computational linguists, artificial intelligence and machine learning investigators, cognitive scientists, speech specialists, and philosophers get information about the computational aspects of all the facets of research on language. In 2015, the journal's impact factor was 2.017 (with 2.500 5-year impact factor), according to Thomson Reuters Journal Citation Reports. Computational Linguistics
The article focuses on argumentation mining using actual Web data and takes up the challenges given by the variety of registers, multiple domains, and unrestricted noisy user-generated Web discourse. In particular, the authors bridge the gap between normative argumentation theories and argumentation phenomena encountered in actual data by adapting an argumentation model tested in an extensive annotation study, create a new gold standard corpus, and experiment with several machine learning methods to identify argument components. The data, source codes, and annotation guidelines are made available to the community under free licenses.
