Jean-Marc Marty

Jean-Marc Marty

Paris et périphérie
3 k abonnés + de 500 relations

Devenir membre pour voir le profil

Activité

S’inscrire pour voir toute l’activité

Expérience

  • Graphique LVMH

    LVMH

    Paris, Île-de-France, France

  • -

    Paris, Île-de-France, France

  • -

    Paris, Île-de-France, France

  • -

    Paris, Île-de-France, France

  • -

    Paris Area, France

  • -

    Paris, Ile-de-France, France

  • -

    Paris Area, France

  • -

    Paris Area, France

  • -

    Paris Area, France

  • -

    San Francisco Bay Area

  • -

    Neuilly s/ Seine

  • -

    Vannes Area, France

Formation

  • Graphique École Polytechnique

    Ecole polytechnique

    -

    Activités et associations :Took the initiative to organize various university events (such as overseas university group trip to Morocco); competitively practiced Judo; been part of several student associations: musical association, RDCF (a type of local fraternity), played in a jazz band (with several concerts in Paris).

  • -

    Classes Préparatoires aux Grandes Écoles. Réussite du concours d'entrée à l'École Polytechnique, filière MP.

Expériences de bénévolat

  • Organizer

    Meetup NLP Paris

    - aujourd’hui 9 ans

    Sciences et technologie

    Interested in applications of Natural Language Processing in your favorite field? Join us! We talk about NLP tech, research, and business applications.

    http://www.nlp.paris/

Publications

  • Trans-Gram: Fast Cross-Lingual Embeddings

    EMNLP 2015

    We introduce Trans-gram, a simple and computationally-efficient method to simultaneously learn and align word embeddings for a variety of languages, usingonly monolingual data and a smaller set of sentence-aligned data. We use our new method to compute aligned word embeddings for twenty-one languages using English as a pivot language. We show that some linguistic features are aligned across languages for which we do not have aligned data, even though those properties
    do not exist in the…

    We introduce Trans-gram, a simple and computationally-efficient method to simultaneously learn and align word embeddings for a variety of languages, usingonly monolingual data and a smaller set of sentence-aligned data. We use our new method to compute aligned word embeddings for twenty-one languages using English as a pivot language. We show that some linguistic features are aligned across languages for which we do not have aligned data, even though those properties
    do not exist in the pivot language. We also achieve state of the art results on standard cross-lingual text classification and word translation tasks.

    Voir la publication

  • Convolutional Neural Network for Twitter Sentiment Analysis

    TALN 2015

    Sentiment Analysis is a common task in natural language processing that aims to detect polarity of a text document (from the most negative to the most positive). We introduce in this article a neural network that classifies in a weakly supervised fashion a set of tweets in three classes : negative, neutral or positive. The architecture of the model is that of a convolutional neural network with three parallel layers where each layer detects distinct features. The network is fed with word…

    Sentiment Analysis is a common task in natural language processing that aims to detect polarity of a text document (from the most negative to the most positive). We introduce in this article a neural network that classifies in a weakly supervised fashion a set of tweets in three classes : negative, neutral or positive. The architecture of the model is that of a convolutional neural network with three parallel layers where each layer detects distinct features. The network is fed with word embeddings learned on a set of corpus among which the French Wikipedia with few linguistic informations. This model achieves a macro-precision in average 25% higher than classical methods based on bag of words.

    Voir la publication

Projets

  • Cabbuccino

    -

    Developed a cab-sharing mobile application that geolocates people in the same area who wish to go to the same place. Subsequently developed a business-plan based on this concept.

    Autres créateurs

  • Third Eye

    -

    Third Eye is an Augmented-Reality Glasses project. We developed 3 different aspects:
    - the software part, with algorithms such as: face recognition, writing recognition, translation of writing (with an application to translating Japanese kanjis for instance);
    - an interface designed to select parts of the field of vision, in order to capture and interpret the reality before the user;
    - the glasses itself, connected to a smartphone that would project the virtual information.

    Autres créateurs

Langues

  • French

    Bilingue ou langue natale

  • English

    Capacité professionnelle complète

  • German

    Compétence professionnelle limitée

  • Japanese

    Notions

Recommandations reçues

4 personnes ont recommandé Jean-Marc

Inscrivez-vous pour y accéder

Plus d’activités de Jean-Marc

Voir le profil complet de Jean-Marc

  • Découvrir vos relations en commun
  • Être mis en relation
  • Contacter Jean-Marc directement
Devenir membre pour voir le profil complet

Autres profils similaires

Autres personnes nommées Jean-Marc Marty (France)

France : 10 autres personnes nommées Jean-Marc Marty sont sur LinkedIn

Autres personnes nommées Jean-Marc Marty

Ajoutez de nouvelles compétences en suivant ces cours

Voir tous les cours