Is It Worth the Attention? A Comparative Evaluation of Attention Layers for Argument Unit Segmentation
This addresses the practical question of whether attention mechanisms are beneficial for argumentation mining, showing they're not worth the computational cost for this specific task.
The paper evaluated attention mechanisms and contextualized embeddings for argument unit segmentation, finding that attention layers provided no improvement over simpler approaches and contextualized embeddings generally didn't outperform baseline scores.
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.