Search Results for author:
Found 31 papers, 5 papers with code
Vers la compréhension automatique de la parole bout-en-bout à moindre effort (Towards automatic end-to-end speech understanding with less effort)
Les approches de compréhension automatique de la parole ont récemment bénéficié de l’apport de modèles préappris par autosupervision sur de gros corpus de parole.
TArC: Tunisian Arabish Corpus, First complete release
In this paper we present the final result of a project focused on Tunisian Arabic encoded in Arabizi, the Latin-based writing system for digital conversations.
LeBenchmark 2.0: a Standardized, Replicable and Enhanced Framework for Self-supervised Representations of French Speech
Self-supervised learning (SSL) is at the origin of unprecedented improvements in many different domains including computer vision and natural language processing.
Encoding Sentence Position in Context-Aware Neural Machine Translation with Concatenation
Context-aware translation can be achieved by processing a concatenation of consecutive sentences with the standard Transformer architecture.
Focused Concatenation for Context-Aware Neural Machine Translation
A straightforward approach to context-aware neural machine translation consists in feeding the standard encoder-decoder architecture with a window of consecutive sentences, formed by the current sentence and a number of sentences from its context concatenated to it.
TArC: Tunisian Arabish Corpus First complete release
In this paper we present the final result of a project on Tunisian Arabic encoded in Arabizi, the Latin-based writing system for digital conversations.
Toward Low-Cost End-to-End Spoken Language Understanding
Recent advances in spoken language understanding benefited from Self-Supervised models trained on large speech corpora.
Vers la compréhension automatique de la parole bout-en-bout à moindre effort
Recent advances in spoken language understanding benefited from Self-Supervised models trained on large speech corpora.
LeBenchmark: A Reproducible Framework for Assessing Self-Supervised Representation Learning from Speech
In this paper, we propose LeBenchmark: a reproducible framework for assessing SSL from speech.
Automatic Speech Recognition
Automatic Speech Recognition (ASR)
+6
Divide and Rule: Effective Pre-Training for Context-Aware Multi-Encoder Translation Models
Multi-encoder models are a broad family of context-aware neural machine translation systems that aim to improve translation quality by encoding document-level contextual information alongside the current sentence.
Multi-Task Sequence Prediction For Tunisian Arabizi Multi-Level Annotation
We show also how we used the system in order to annotate a Tunisian Arabizi corpus, which has been afterwards manually corrected and used to further evaluate sequence models on Tunisian data.
TArC. Un corpus d'arabish tunisien
TArC : Incrementally and Semi-Automatically Collecting a Tunisian arabish Corpus This article describes the collection process of the first morpho-syntactically annotated Tunisian arabish Corpus (TArC).
TArC: Incrementally and Semi-Automatically Collecting a Tunisian Arabish Corpus
This article describes the constitution process of the first morpho-syntactically annotated Tunisian Arabish Corpus (TArC).
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.
Hybrid Neural Models For Sequence Modelling: The Best Of Three Worlds
We propose a neural architecture with the main characteristics of the most successful neural models of the last years: bidirectional RNNs, encoder-decoder, and the Transformer model.
Mod\`eles neuronaux hybrides pour la mod\'elisation de s\'equences : le meilleur de trois mondes ()
Nous proposons une architecture neuronale avec les caract{\'e}ristiques principales des mod{\`e}les neuronaux de ces derni{\`e}res ann{\'e}es : les r{\'e}seaux neuronaux r{\'e}currents bidirectionnels, les mod{\`e}les encodeur-d{\'e}codeur, et le mod{\`e}le Transformer.
Seq2Biseq: Bidirectional Output-wise Recurrent Neural Networks for Sequence Modelling
During the last couple of years, Recurrent Neural Networks (RNN) have reached state-of-the-art performances on most of the sequence modelling problems.
Effective Spoken Language Labeling with Deep Recurrent Neural Networks
Understanding spoken language is a highly complex problem, which can be decomposed into several simpler tasks.
Label-Dependencies Aware Recurrent Neural Networks
In this work we propose a solution far simpler but very effective: an evolution of the simple Jordan RNN, where labels are re-injected as input into the network, and converted into embeddings, in the same way as words.
Apports des analyses syntaxiques pour la d\'etection automatique de mentions dans un corpus de fran\ccais oral (Experiences in using deep and shallow parsing to detect entity mentions in oral French)
Cet article pr{\'e}sente trois exp{\'e}riences de d{\'e}tection de mentions dans un corpus de fran{\c{c}}ais oral : ANCOR.
D\'etection des mots non-standards dans les tweets avec des r\'eseaux de neurones (Detecting non-standard words in tweets with neural networks)
Dans cet article, nous proposons un mod{\`e}le pour d{\'e}tecter dans les textes g{\'e}n{\'e}r{\'e}s par des utilisateurs (en particulier les tweets), les mots non-standards {\`a} corriger.
R\'eseaux neuronaux profonds pour l'\'etiquetage de s\'equences (Deep Neural Networks for Sequence Labeling)
R{\'e}cemment, une variante de r{\'e}seau neuronal particuli{\`e}rement adapt{\'e} {\`a} l{'}{\'e}tiquetage de s{\'e}quences textuelles a {\'e}t{\'e} propos{\'e}e, utilisant des repr{\'e}sentations distributionnelles des {\'e}tiquettes.
\'Etude des r\'eseaux de neurones r\'ecurrents pour \'etiquetage de s\'equences (A study of Recurrent Neural Networks for Sequence Labelling)
Dans cet article nous {\'e}tudions plusieurs types de r{\'e}seaux neuronaux r{\'e}currents (RNN) pour l{'}{\'e}tiquetage de s{\'e}quences.
Improving Recurrent Neural Networks For Sequence Labelling
In this paper we study different types of Recurrent Neural Networks (RNN) for sequence labeling tasks.
Domain Adaptation for Named Entity Recognition Using CRFs
We explain the specificities of this corpus with examples and describe some baseline experiments.
Evaluation of different strategies for domain adaptation in opinion mining
The work presented in this article takes place in the field of opinion mining and aims more particularly at finding the polarity of a text by relying on machine learning methods.
Tree-Structured Named Entity Recognition on OCR Data: Analysis, Processing and Results
We evaluate our procedure for preprocessing OCR-ized data in two ways: in terms of perplexity and OOV rate of a language model on development and evaluation data, and in terms of the performance of the named entity detection system on the preprocessed data.
