Multi-Task Learning for Argumentation Mining

TL;DR

This paper evaluates multi-task learning across four NLP scenarios, demonstrating its potential to improve performance especially with sparse data and long sequences, while also analyzing when it may not help.

Contribution

It extends empirical research on multi-task learning by systematically analyzing its effectiveness in argumentation mining and related tasks, and introduces a flexible framework for such experiments.

Findings

Multi-task learning improves performance in all evaluated scenarios.

Dataset properties like entropy influence multi-task learning success.

Multi-task learning is especially beneficial for long input sequences and data-sparse tasks.

Abstract

Multi-task learning has recently become a very active field in deep learning research. In contrast to learning a single task in isolation, multiple tasks are learned at the same time, thereby utilizing the training signal of related tasks to improve the performance on the respective machine learning tasks. Related work shows various successes in different domains when applying this paradigm and this thesis extends the existing empirical results by evaluating multi-task learning in four different scenarios: argumentation mining, epistemic segmentation, argumentation component segmentation, and grapheme-to-phoneme conversion. We show that multi-task learning can, indeed, improve the performance compared to single-task learning in all these scenarios, but may also hurt the performance. Therefore, we investigate the reasons for successful and less successful applications of this paradigm and find that dataset properties such as entropy or the size of the label inventory are good indicators for a potential multi-task learning success and that multi-task learning is particularly useful if the task at hand suffers from data sparsity, i.e. a lack of training data. Moreover, multi-task learning is particularly effective for long input sequences in our experiments. We have observed this trend in all evaluated scenarios. Finally, we develop a highly configurable and extensible sequence tagging framework which supports multi-task learning to conduct our empirical experiments and to aid future research regarding the multi-task learning paradigm and natural language processing.