Neural End-to-End Learning for Computational Argumentation Mining
This work addresses argumentation mining for natural language processing applications, presenting an incremental improvement in method comparison.
The paper tackles computational argumentation mining by comparing neural approaches, finding that token-based sequence tagging with BiLSTMs performs robustly across scenarios, while dependency parsing yields subpar results, and multi-task learning with subtasks improves performance.
We investigate neural techniques for end-to-end computational argumentation mining (AM). We frame AM both as a token-based dependency parsing and as a token-based 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 BiLSTMs perform robustly across classification scenarios, being able to catch long-range dependencies inherent to the AM problem. Moreover, we find that jointly learning 'natural' subtasks, in a multi-task learning setup, improves performance.