Neural End-to-End Learning for Computational Argumentation Mining
Steffen Eger, Johannes Daxenberger, Iryna Gurevych · 2017
We investigate neural techniques for endto-end computational argumentation mining (AM).We frame AM both as a tokenbased dependency parsing and as a tokenbased sequence tagging problem, including a multi-task learning setup.Contrary to models that operate on the argument component level, we find that framing AM as dependency parsing leads to subpar performance results.In contrast, less complex (local) tagging models based on BiL-STMs perform robustly across classification scenarios, being able to catch longrange dependencies inherent to the AM problem.Moreover, we find that jointly learning 'natural' subtasks, in a multi-task learning setup, improves performance.