Learning from Auxiliary Sources in Argumentative Revision Classification

TL;DR

This paper introduces models that leverage auxiliary data sources using multi-task and transfer learning to improve the classification of reasoning revisions in argumentative writing, demonstrating enhanced performance over baseline methods.

Contribution

It compares multi-task learning and transfer learning approaches for utilizing auxiliary data in argumentative revision classification, highlighting the effectiveness of transfer learning.

Findings

Both approaches improve classifier performance.

Transfer learning better captures data relationships.

Multi-task learning benefits from simultaneous training.

Abstract

We develop models to classify desirable reasoning revisions in argumentative writing. We explore two approaches -- multi-task learning and transfer learning -- to take advantage of auxiliary sources of revision data for similar tasks. Results of intrinsic and extrinsic evaluations show that both approaches can indeed improve classifier performance over baselines. While multi-task learning shows that training on different sources of data at the same time may improve performance, transfer-learning better represents the relationship between the data.