A Semi-supervised Learning Approach with Two Teachers to Improve Breakdown Identification in Dialogues

TL;DR

This paper introduces a semi-supervised teacher-student framework with two teachers to enhance dialogue breakdown detection, reducing reliance on costly labeled data and outperforming existing methods.

Contribution

A novel semi-supervised learning approach using two teachers to improve dialogue breakdown classification with less labeled data.

Findings

Outperforms previous approaches on DBDC5 and LIF datasets.

Achieves better accuracy than supervised and semi-supervised baselines.

Demonstrates effectiveness of dual-teacher bootstrapping in dialogue analysis.

Abstract

Identifying breakdowns in ongoing dialogues helps to improve communication effectiveness. Most prior work on this topic relies on human annotated data and data augmentation to learn a classification model. While quality labeled dialogue data requires human annotation and is usually expensive to obtain, unlabeled data is easier to collect from various sources. In this paper, we propose a novel semi-supervised teacher-student learning framework to tackle this task. We introduce two teachers which are trained on labeled data and perturbed labeled data respectively. We leverage unlabeled data to improve classification in student training where we employ two teachers to refine the labeling of unlabeled data through teacher-student learning in a bootstrapping manner. Through our proposed training approach, the student can achieve improvements over single-teacher performance. Experimental results on the Dialogue Breakdown Detection Challenge dataset DBDC5 and Learning to Identify Follow-Up Questions dataset LIF show that our approach outperforms all previous published approaches as well as other supervised and semi-supervised baseline methods.