C
Christophe Cerisara
Researcher at University of Lorraine
Publications - 94
Citations - 781
Christophe Cerisara is an academic researcher from University of Lorraine. The author has contributed to research in topics: Sentence & Deep learning. The author has an hindex of 16, co-authored 94 publications receiving 725 citations. Previous affiliations of Christophe Cerisara include Centre national de la recherche scientifique & Henri Poincaré University.
Papers
More filters
Proceedings Article
Do Convolutional Networks Need to Be Deep for Text Classification
TL;DR: This work shows on 5 standard text classification and sentiment analysis tasks that deep models indeed give better performances than shallow networks when the text input is represented as a sequence of characters, but a simple shallow-and-wide network outperforms deep models such as DenseNet with word inputs.
Journal ArticleDOI
On noise masking for automatic missing data speech recognition: A survey and discussion
TL;DR: The objective of this study is to identify the mask estimation methods that have been proposed so far, and to open this domain up to other related research, which could be adapted to overcome this difficult challenge.
Proceedings Article
Multi-task dialog act and sentiment recognition on Mastodon
TL;DR: This work annotates a new Twitter-like corpus from an alternative large social medium with licenses that are compatible with reproducible experiments: Mastodon, and trains a multi-task hierarchical recurrent network on joint sentiment and dialog act recognition.
Book
Reconnaissance Automatique de la Parole Du signal à son interprétation
TL;DR: In this article, a caractere pluridisciplinaire de the reconnaissance automatique de la parole is described, which fait appel a des notions variees allant des mathematiques, du traitement du signal, de linformatique et de l'intelligence artificielle jusqu'a la phonetique, a la linguistique, aux sciences cognitives and aux neurosciences.
Proceedings ArticleDOI
The Automatic News Transcription System: ANTS some Real Time experiments
TL;DR: The recent development of ANTS, the Automatic News Transcription System of LORIA is presented and its different components and some segmentation and recognition results on the ESTER database are described.