Soutenance de thèse, Edwin Simonnet

Date : 12/02/2019
Heure : 13h00
Lieu : amphithéâtre, bâtiment IC2, LIUM, Université du Mans

Title : Deep learning applied to spoken langage understanding

jury members:
Reviewers :
– Ms Sophie Rosset
– Mr. Frédéric Béchet
Examiners :
– Mr. Marco Dinarelli
– Mr. Bassam Jabaian
Supervisor : Mr. Yannick Estève
Co-supervisor : Ms Nathalie Camelin
Invited : Mr. Paul Deléglise

Abstract :

This thesis is a part of the emergence of deep learning and focuses on spoken language understanding assimilated to the automatic extraction and representation of the meaning supported by the words in a spoken utterance. We study a semantic concept tagging task used in a spoken dialogue system and evaluated with the French corpus MEDIA. For the past decade, neural models have emerged in many natural language processing tasks through algorithmic advances or powerful computing tools such as graphics processors. Many obstacles make the understanding task complex, such as the difficult interpretation of automatic speech transcriptions, as many errors are introduced by the automatic recognition process upstream of the comprehension module. We present a state of the art describing spoken language understanding and then supervised automatic learning methods to solve it, starting with classical systems and finishing with deep learning techniques. The contributions are then presented along three axes. First, we develop an efficient neural architecture consisting of a bidirectional recurrent network encoder-decoder with attention mechanism. Then we study the management of automatic recognition errors and solutions to limit their impact on our performances. Finally, we envisage a disambiguation of the comprehension task making the systems more efficient.

Keywords :
Spoken Language Understanding, Corpus MEDIA, Semantic concept tagging, Deep learning, Attention mechanism, Automatic speech recognition errors, Simulation of recognition errors, Disambiguation of understanding