LKE/KDSL Research Seminar


On Tuesday, February 10th 2015, the LKE/KDSL Research Seminar will feature a talk by Dr. Ivan Habernal. The talk will occur in S2|02 C110 at 9:50.

Title: Argumentation Mining in User-Generated Web Discourse

Abstract: The goal of argumentation mining, an evolving research field in computational linguistics, is to design methods capable of analyzing people's argumentation. In this talk, I'm going to present our recent achievements, as we go beyond the state of the art by dealing with actual Web data and take up the challenges given by multiple domains, the variety of registers, and unrestricted and noisy user-generated Web discourse. We also try to 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. We create a new gold standard corpus (90k tokens in 340 documents) and experiment with several machine learning methods to identify persuasive documents and argument components. Our findings show that argumentation mining in user-generated Web discourse is a feasible but very challenging task.