Reusing Preprocessing Data as Auxiliary Supervision in Conversational Analysis

Joshua Yee Kim, Kalina Yacef

Keywords: Multitask Learning, Multimodal Conversational Analysis

Abstract: 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. However, auxiliary tasks could improve the performance of the primary task learning. This approach is known as Primary Multi-Task Learning (MTL). A challenge of MTL is the selection of beneficial auxiliary tasks that avoid negative transfer. In this paper, we explore how the preprocessed data used for feature engineering can be re-used as auxiliary tasks in Primary MTL, thereby promoting the productive use of data in the form of auxiliary supervision learning. Our main contributions are: (1) the identification of sixteen beneficially auxiliary tasks, (2) the method of distributing learning capacity between the primary and auxiliary tasks, and (3) 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.

One-sentence Summary: For multimodal conversational analysis, we have identified what are the beneficially auxiliary tasks, how to construct them through reusing preprocessing data, and the model architecture design to improve the primary tasks performances.

Code Of Ethics: I acknowledge that I and all co-authors of this work have read and commit to adhering to the ICLR Code of Ethics

Reviewed Version (pdf): https://openreview.net/references/pdf?id=4opwOgUwm