Sequence labelling tasks like Dialog Act and Emotion/Sentiment identification are a key component of spoken dialog systems. In this work, we propose a new approach to learn generic representations adapted to spoken dialog, which we evaluate on a new benchmark we call Sequence labellIng evaLuatIon benChmark fOr spoken laNguagE benchmark (\texttt{SILICONE}). \texttt{SILICONE} is model-agnostic and contains 10 different datasets of various sizes. We obtain our representations with a hierarchical encoder based on transformer architectures, for which we extend two well-known pre-training objectives. Pre-training is performed on OpenSubtitles: a large corpus of spoken dialog containing over 2.3 billion of tokens. We demonstrate how hierarchical encoders achieve competitive results with consistently fewer parameters compared to state-of-the-art models and we show their importance for both pre-training and fine-tuning.
@article{arxiv.2009.11152,
title = {Hierarchical Pre-training for Sequence Labelling in Spoken Dialog},
author = {Emile Chapuis and Pierre Colombo and Matteo Manica and Matthieu Labeau and Chloe Clavel},
journal= {arXiv preprint arXiv:2009.11152},
year = {2021}
}