CLApr 20, 2017

Neural End-to-End Learning for Computational Argumentation Mining

arXiv:1704.06104v2217 citations
Originality Incremental advance
AI Analysis

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.

Code Implementations2 repos
Foundations

The foundational work for this paper's niche, ranked by how specifically the neighbourhood builds on it — not by global fame.

Your Notes