Where are we in semantic concept extraction for Spoken Language Understanding?
This work addresses the challenge of improving SLU performance for tasks like slot filling in human-machine dialogue, but it is incremental as it builds on existing end-to-end neural approaches.
The paper tackles the problem of semantic concept extraction in spoken language understanding (SLU) by providing an overview of recent advances and presenting new results that achieve a Concept Error Rate (CER) of 11.2%, outperforming the previous state-of-the-art of 13.6% on the French MEDIA benchmark dataset.
Spoken language understanding (SLU) topic has seen a lot of progress these last three years, with the emergence of end-to-end neural approaches. Spoken language understanding refers to natural language processing tasks related to semantic extraction from speech signal, like named entity recognition from speech or slot filling task in a context of human-machine dialogue. Classically, SLU tasks were processed through a cascade approach that consists in applying, firstly, an automatic speech recognition process, followed by a natural language processing module applied to the automatic transcriptions. These three last years, end-to-end neural approaches, based on deep neural networks, have been proposed in order to directly extract the semantics from speech signal, by using a single neural model. More recent works on self-supervised training with unlabeled data open new perspectives in term of performance for automatic speech recognition and natural language processing. In this paper, we present a brief overview of the recent advances on the French MEDIA benchmark dataset for SLU, with or without the use of additional data. We also present our last results that significantly outperform the current state-of-the-art with a Concept Error Rate (CER) of 11.2%, instead of 13.6% for the last state-of-the-art system presented this year.