no code implementations • EACL 2021 • Betty Fabre, Tanguy Urvoy, Jonathan Chevelu, Damien Lolive
We study a search-based paraphrase generation scheme where candidate paraphrases are generated by iterated transformations from the original sentence and evaluated in terms of syntax quality, semantic distance, and lexical distance.
no code implementations • COLING 2020 • Rashedur Rahman, Gw{\'e}nol{\'e} Lecorv{\'e}, Aline {\'E}tienne, Delphine Battistelli, Nicolas B{\'e}chet, Jonathan Chevelu
Children have less linguistic skills than adults, which makes it more difficult for them to understand some texts, for instance when browsing the Internet.
no code implementations • NeurIPS Workshop LMCA 2020 • Betty Fabre, Tanguy Urvoy, Jonathan Chevelu, Damien Lolive
A good paraphrase is semantically similar to the original sentence but it must be also well formed, and syntactically different to ensure diversity.
no code implementations • JEPTALNRECITAL 2020 • C{\'e}dric Fayet, Alexis Blond, Gr{\'e}goire Coulombel, Claude Simon, Damien Lolive, Gw{\'e}nol{\'e} Lecorv{\'e}, Jonathan Chevelu, S{\'e}bastien Le Maguer
Nous pr{\'e}sentons FlexEval, un outil de conception et d{\'e}ploiement de tests perceptifs multim{\'e}dias sous la forme d{'}un site web l{\'e}ger.
no code implementations • JEPTALNRECITAL 2018 • Gw{\'e}nol{\'e} Lecorv{\'e}, Hugo Ayats, Fournier Beno{\^\i}t, Jade Mekki, Jonathan Chevelu, Delphine Battistelli, Nicolas B{\'e}chet
Dans cet article, nous pr{\'e}sentons une approche semi-supervis{\'e}e permettant la construction conjointe d{'}un corpus de textes {\'e}tiquet{\'e}s en registres et d{'}un classifieur associ{\'e}.
no code implementations • JEPTALNRECITAL 2016 • Jonathan Chevelu, Damien Lolive, S{\'e}bastien Le Maguer, David Guennec
Cette m{\'e}thode est appliqu{\'e}e sur un syst{\`e}me de synth{\`e}se de type HTS et un second par s{\'e}lection d{'}unit{\'e}s. La comparaison avec l{'}approche classique montre que cette m{\'e}thode r{\'e}v{\`e}le des {\'e}carts qui jusqu{'}alors n{'}{\'e}taient pas significatifs.
no code implementations • LREC 2014 • Jonathan Chevelu, Gw{\'e}nol{\'e} Lecorv{\'e}, Damien Lolive
The development of new methods for given speech and natural language processing tasks usually consists in annotating large corpora of data before applying machine learning techniques to train models or to extract information.