Christophe Cerisara


Unsupervised multiple-choice question generation for out-of-domain Q&A fine-tuning
Guillaume Le Berre | Christophe Cerisara | Philippe Langlais | Guy Lapalme
Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 2: Short Papers)

Pre-trained models have shown very good performances on a number of question answering benchmarks especially when fine-tuned on multiple question answering datasets at once. In this work, we propose an approach for generating a fine-tuning dataset thanks to a rule-based algorithm that generates questions and answers from unannotated sentences. We show that the state-of-the-art model UnifiedQA can greatly benefit from such a system on a multiple-choice benchmark about physics, biology and chemistry it has never been trained on. We further show that improved performances may be obtained by selecting the most challenging distractors (wrong answers), with a dedicated ranker based on a pretrained RoBERTa model.


Multi-task dialog act and sentiment recognition on Mastodon
Christophe Cerisara | Somayeh Jafaritazehjani | Adedayo Oluokun | Hoa T. Le
Proceedings of the 27th International Conference on Computational Linguistics

Because of license restrictions, it often becomes impossible to strictly reproduce most research results on Twitter data already a few months after the creation of the corpus. This situation worsened gradually as time passes and tweets become inaccessible. This is a critical issue for reproducible and accountable research on social media. We partly solve this challenge by annotating a new Twitter-like corpus from an alternative large social medium with licenses that are compatible with reproducible experiments: Mastodon. We manually annotate both dialogues and sentiments on this corpus, and train a multi-task hierarchical recurrent network on joint sentiment and dialog act recognition. We experimentally demonstrate that transfer learning may be efficiently achieved between both tasks, and further analyze some specific correlations between sentiments and dialogues on social media. Both the annotated corpus and deep network are released with an open-source license.


Weakly-supervised text-to-speech alignment confidence measure
Guillaume Serrière | Christophe Cerisara | Dominique Fohr | Odile Mella
Proceedings of COLING 2016, the 26th International Conference on Computational Linguistics: Technical Papers

This work proposes a new confidence measure for evaluating text-to-speech alignment systems outputs, which is a key component for many applications, such as semi-automatic corpus anonymization, lips syncing, film dubbing, corpus preparation for speech synthesis and speech recognition acoustic models training. This confidence measure exploits deep neural networks that are trained on large corpora without direct supervision. It is evaluated on an open-source spontaneous speech corpus and outperforms a confidence score derived from a state-of-the-art text-to-speech aligner. We further show that this confidence measure can be used to fine-tune the output of this aligner and improve the quality of the resulting alignment.


A Domain Agnostic Approach to Verbalizing n-ary Events without Parallel Corpora
Bikash Gyawali | Claire Gardent | Christophe Cerisara
Proceedings of the 15th European Workshop on Natural Language Generation (ENLG)


Unsupervised structured semantic inference for spoken dialog reservation tasks
Alejandra Lorenzo | Lina Rojas-Barahona | Christophe Cerisara
Proceedings of the SIGDIAL 2013 Conference


Unsupervised frame based Semantic Role Induction: application to French and English
Alejandra Lorenzo | Christophe Cerisara
Proceedings of the ACL 2012 Joint Workshop on Statistical Parsing and Semantic Processing of Morphologically Rich Languages


Vers la détection des dislocations à gauche dans les transcriptions automatiques du Français parlé (Towards automatic recognition of left dislocation in transcriptions of Spoken French)
Corinna Anderson | Christophe Cerisara | Claire Gardent
Actes de la 18e conférence sur le Traitement Automatique des Langues Naturelles. Articles courts

Ce travail prend place dans le cadre plus général du développement d’une plate-forme d’analyse syntaxique du français parlé. Nous décrivons la conception d’un modèle automatique pour résoudre le lien anaphorique présent dans les dislocations à gauche dans un corpus de français parlé radiophonique. La détection de ces structures devrait permettre à terme d’améliorer notre analyseur syntaxique en enrichissant les informations prises en compte dans nos modèles automatiques. La résolution du lien anaphorique est réalisée en deux étapes : un premier niveau à base de règles filtre les configurations candidates, et un second niveau s’appuie sur un modèle appris selon le critère du maximum d’entropie. Une évaluation expérimentale réalisée par validation croisée sur un corpus annoté manuellement donne une F-mesure de l’ordre de 40%.