Multi-Task Learning based Online Dialogic Instruction Detection with Pre-trained Language Models

TL;DR

This paper introduces a multi-task learning approach using pre-trained language models and contrastive loss to effectively detect online dialogic instructions, improving classification accuracy in educational data.

Contribution

It proposes a novel multi-task paradigm with contrastive loss and a misclassified example exploitation strategy for dialogic instruction detection.

Findings

Achieves superior performance over baseline methods

Effectively distinguishes different classes of dialogic instructions

Demonstrates robustness on real-world educational data

Abstract

In this work, we study computational approaches to detect online dialogic instructions, which are widely used to help students understand learning materials, and build effective study habits. This task is rather challenging due to the widely-varying quality and pedagogical styles of dialogic instructions. To address these challenges, we utilize pre-trained language models, and propose a multi-task paradigm which enhances the ability to distinguish instances of different classes by enlarging the margin between categories via contrastive loss. Furthermore, we design a strategy to fully exploit the misclassified examples during the training stage. Extensive experiments on a real-world online educational data set demonstrate that our approach achieves superior performance compared to representative baselines. To encourage reproducible results, we make our implementation online available at \url{https://github.com/AIED2021/multitask-dialogic-instruction}.