Transfer Learning in Conversational Analysis through Reusing Preprocessing Data as Supervisors
This work addresses overfitting issues in conversational analysis for researchers, but it is incremental as it builds on existing multi-task learning methods.
The paper tackles the problem of overfitting in conversational analysis systems by reusing preprocessed data as auxiliary tasks in a transfer learning approach, showing improvements over single-task methods on IEMOCAP and SEMAINE datasets.
Conversational analysis systems are trained using noisy human labels and often require heavy preprocessing during multi-modal feature extraction. Using noisy labels in single-task learning increases the risk of over-fitting. Auxiliary tasks could improve the performance of the primary task learning during the same training -- this approach sits in the intersection of transfer learning and multi-task learning (MTL). In this paper, we explore how the preprocessed data used for feature engineering can be re-used as auxiliary tasks, thereby promoting the productive use of data. Our main contributions are: (1) the identification of sixteen beneficially auxiliary tasks, (2) studying the method of distributing learning capacity between the primary and auxiliary tasks, and (3) studying the relative supervision hierarchy between the primary and auxiliary tasks. Extensive experiments on IEMOCAP and SEMAINE data validate the improvements over single-task approaches, and suggest that it may generalize across multiple primary tasks.