A Semi-supervised Learning Approach with Two Teachers to Improve Breakdown Identification in Dialogues
This work addresses the challenge of expensive labeled data for dialogue breakdown detection, offering a method to leverage unlabeled data for improved communication effectiveness.
The paper tackles the problem of identifying breakdowns in dialogues by proposing a semi-supervised teacher-student framework with two teachers, achieving state-of-the-art performance on datasets like DBDC5 and LIF.
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.