# Is It Worth the Attention? A Comparative Evaluation of Attention Layers for Argument Unit Segmentation

## TL;DR

This paper evaluates the effectiveness of attention layers and contextualized embeddings in argument unit segmentation, finding that added complexity does not significantly improve performance over simpler models.

## Contribution

It provides a comparative analysis of attention mechanisms and embeddings in argument unit segmentation, highlighting that increased complexity may not always yield better results.

## Key findings

- Attention layers do not improve segmentation performance.
- Contextualized embeddings often do not outperform baseline embeddings.
- Simpler models perform comparably to more complex attention-based models.

## Abstract

Attention mechanisms have seen some success for natural language processing downstream tasks in recent years and generated new State-of-the-Art results. A thorough evaluation of the attention mechanism for the task of Argumentation Mining is missing, though. With this paper, we report a comparative evaluation of attention layers in combination with a bidirectional long short-term memory network, which is the current state-of-the-art approach to the unit segmentation task. We also compare sentence-level contextualized word embeddings to pre-generated ones. Our findings suggest that for this task the additional attention layer does not improve upon a less complex approach. In most cases, the contextualized embeddings do also not show an improvement on the baseline score.