Search Results for author:
Found 17 papers, 0 papers with code
The Spoken Language Understanding MEDIA Benchmark Dataset in the Era of Deep Learning: data updates, training and evaluation tools
In this paper, we focus on the French MEDIA SLU dataset, distributed since 2005 and used as a benchmark dataset for a large number of research works.
Impact Analysis of the Use of Speech and Language Models Pretrained by Self-Supersivion for Spoken Language Understanding
Pretrained models through self-supervised learning have been recently introduced for both acoustic and language modeling.
Semantic enrichment towards efficient speech representations
Over the past few years, self-supervised learned speech representations have emerged as fruitful replacements for conventional surface representations when solving Spoken Language Understanding (SLU) tasks.
Findings from Experiments of On-line Joint Reinforcement Learning of Semantic Parser and Dialogue Manager with real Users
The analysis of these experiments gives us some insights, discussed in the paper, into the difficulty for the system's trainers to establish a coherent and constant behavioural strategy to enable a fast and good-quality training phase.
Where are we in semantic concept extraction for Spoken Language Understanding?
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.
Automatic Speech Recognition
Automatic Speech Recognition (ASR)
+7
A Data Efficient End-To-End Spoken Language Understanding Architecture
For that, in many cases, models are combined with an external language model to enhance their performance.
Joint On-line Learning of a Zero-shot Spoken Semantic Parser and a Reinforcement Learning Dialogue Manager
Several variants of joint learning are investigated and tested with user trials to confirm that the overall on-line learning can be obtained after only a few hundred training dialogues and can overstep an expert-based system.
Apprentissage en ligne interactif d'un g\'en\'erateur en langage naturel neuronal pour le dialogue homme-machine (On-line Interactive Learning of Natural Language Neural Generation for Human-machine)
R{\'e}cemment, de nouveaux mod{\`e}les {\`a} base de r{\'e}seaux de neurones r{\'e}currents ont {\'e}t{\'e} propos{\'e}s pour traiter la g{\'e}n{\'e}ration en langage naturel dans des syst{\`e}mes de dialogue (Wen et al., 2016a).
Algorithmes de classification et d'optimisation: participation du LIA/ADOC á DEFT'14
This year, the DEFT campaign (D\'efi Fouilles de Textes) incorporates a task which aims at identifying the session in which articles of previous TALN conferences were presented.
Optimiser l'adaptation en ligne d'un module de compr\'ehension de la parole avec un algorithme de bandit contre un adversaire (Adversarial bandit for optimising online active learning of spoken language understanding)
De nombreux modules de compr{\'e}hension de la parole ont en commun d{'}{\^e}tre probabilistes et bas{\'e}s sur des algorithmes d{'}apprentissage automatique.
Automatic Corpus Extension for Data-driven Natural Language Generation
As data-driven approaches started to make their way into the Natural Language Generation (NLG) domain, the need for automation of corpus building and extension became apparent.
Compr\'ehension automatique de la parole sans donn\'ees de r\'ef\'erence
Cette m{\'e}thode combine une description ontologique minimale de la t{\^a}che vis{\'e}e avec l{'}utilisation d{'}un espace s{\'e}mantique continu appris par des approches {\`a} base de r{\'e}seaux de neurones {\`a} partir de donn{\'e}es g{\'e}n{\'e}riques non-annot{\'e}es.
Leveraging study of robustness and portability of spoken language understanding systems across languages and domains: the PORTMEDIA corpora
The PORTMEDIA project is intended to develop new corpora for the evaluation of spoken language understanding systems.
