Multi-Task Attentive Residual Networks for Argument Mining
This work provides a more efficient and generalizable method for argument mining across user-generated comments, scientific publications, and persuasive essays, though it appears incremental in combining existing techniques.
The authors tackled argument mining across diverse text types by proposing a multi-task attentive residual network that combines attention mechanisms, multi-task learning, and ensemble methods without structural assumptions. Their approach achieved competitive performance against state-of-the-art models on five corpora while offering reduced computational footprint and model size.
We explore the use of residual networks and neural attention for multiple argument mining tasks. We propose a residual architecture that exploits attention, multi-task learning, and makes use of ensemble, without any assumption on document or argument structure. We present an extensive experimental evaluation on five different corpora of user-generated comments, scientific publications, and persuasive essays. Our results show that our approach is a strong competitor against state-of-the-art architectures with a higher computational footprint or corpus-specific design, representing an interesting compromise between generality, performance accuracy and reduced model size.