Mathieu Avanzi


2018

pdf
Strategies and Challenges for Crowdsourcing Regional Dialect Perception Data for Swiss German and Swiss French
Jean-Philippe Goldman | Simon Clematide | Mathieu Avanzi | Raphael Tandler
Proceedings of the Eleventh International Conference on Language Resources and Evaluation (LREC 2018)

pdf
Crowdsourcing Regional Variation Data and Automatic Geolocalisation of Speakers of European French
Jean-Philippe Goldman | Yves Scherrer | Julie Glikman | Mathieu Avanzi | Christophe Benzitoun | Philippe Boula de Mareüil
Proceedings of the Eleventh International Conference on Language Resources and Evaluation (LREC 2018)

2015

pdf
DisMo : un annotateur multi-niveaux pour les corpus oraux
George Christodoulides | Giulia Barreca | Mathieu Avanzi
Actes de la 22e conférence sur le Traitement Automatique des Langues Naturelles. Démonstrations

Dans cette démonstration, nous présentons l’annotateur multi-niveaux DisMo, un outil conçu pour faire face aux spécificités des corpus oraux. Il fournit une annotation morphosyntaxique, une lemmatisation, une détection des unités poly-lexicales, une détection des phénomènes de disfluence et des marqueurs de discours.

2014

pdf
DisMo: A Morphosyntactic, Disfluency and Multi-Word Unit Annotator. An Evaluation on a Corpus of French Spontaneous and Read Speech
George Christodoulides | Mathieu Avanzi | Jean-Philippe Goldman
Proceedings of the Ninth International Conference on Language Resources and Evaluation (LREC'14)

We present DisMo, a multi-level annotator for spoken language corpora that integrates part-of-speech tagging with basic disfluency detection and annotation, and multi-word unit recognition. DisMo is a hybrid system that uses a combination of lexical resources, rules, and statistical models based on Conditional Random Fields (CRF). In this paper, we present the first public version of DisMo for French. The system is trained and its performance evaluated on a 57k-token corpus, including different varieties of French spoken in three countries (Belgium, France and Switzerland). DisMo supports a multi-level annotation scheme, in which the tokenisation to minimal word units is complemented with multi-word unit groupings (each having associated POS tags), as well as separate levels for annotating disfluencies and discourse phenomena. We present the system’s architecture, linguistic resources and its hierarchical tag-set. Results show that DisMo achieves a precision of 95% (finest tag-set) to 96.8% (coarse tag-set) in POS-tagging non-punctuated, sound-aligned transcriptions of spoken French, while also offering substantial possibilities for automated multi-level annotation.

2012

pdf
A la recherche des temps perdus : Variations sur le rythme en français (Regional Variations of Speech Rhythm in French: In Search of Lost Times) [in French]
Nicolas Obin | Mathieu Avanzi | Guri Bordal | Alice Bardiaux
Proceedings of the Joint Conference JEP-TALN-RECITAL 2012, volume 1: JEP

pdf
La variation prosodique dialectale en français. Données et hypothèses (Speech Prosody of Dialectal French: Data and Hypotheses) [in French]
Mathieu Avanzi | Nicolas Obin | Guri Bordal | Alice Bardiaux
Proceedings of the Joint Conference JEP-TALN-RECITAL 2012, volume 1: JEP

pdf
Etude de l’influence de la variété dialectale sur la vitesse d’articulation en français (Dialectal Effect on Articulation Rate in French) [in French]
Sandra Schwab | Pauline Dubosson | Mathieu Avanzi
Proceedings of the Joint Conference JEP-TALN-RECITAL 2012, volume 1: JEP

2010

pdf
Design and Evaluation of Shared Prosodic Annotation for Spontaneous French Speech: From Expert Knowledge to Non-Expert Annotation
Anne Lacheret-Dujour | Nicolas Obin | Mathieu Avanzi
Proceedings of the Fourth Linguistic Annotation Workshop