Auxiliary Objectives for Neural Error Detection Models

TL;DR

This paper explores the use of auxiliary objectives in neural error detection models, demonstrating that joint learning with multiple objectives enhances performance and training efficiency in learner writing error detection.

Contribution

It introduces auxiliary objectives into neural sequence labeling for error detection, improving accuracy and training efficiency over previous models.

Findings

Joint learning with auxiliary objectives outperforms previous best systems.

Auxiliary costs enable the model to learn more effective linguistic features.

The model achieves better performance without increasing parameters.

Abstract

We investigate the utility of different auxiliary objectives and training strategies within a neural sequence labeling approach to error detection in learner writing. Auxiliary costs provide the model with additional linguistic information, allowing it to learn general-purpose compositional features that can then be exploited for other objectives. Our experiments show that a joint learning approach trained with parallel labels on in-domain data improves performance over the previous best error detection system. While the resulting model has the same number of parameters, the additional objectives allow it to be optimised more efficiently and achieve better performance.