Improving Supervised Learning in Conversational Analysis through Reusing Preprocessing Data as Auxiliary Supervisors

Abstract

Emotions recognition 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 – multi-task learning (MTL). In this paper, we explore how the preprocessed data used for creating the textual multimodal description of the conversation, that supports conversational analysis, can be re-used as auxiliary tasks (e.g. predicting future or previous labels and predicting the ranked expressions of actions and prosody), 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.