Text Mining
Machine Learning
Natural Language Processing
Search and Information Retrieval
Data Science
Shortest-Path Graph Kernels for Document Similarity.
Giannis Nikolentzos, Polykarpos Meladianos, François Rousseau, Yannis Stavrakas and Michalis Vazirgiannis.
2017 Conference on Empirical Methods in Natural Language Processing, EMNLP '17.
Community-preserving Anonymization of Graphs.
François Rousseau, Jordi Casas-Roma and Michalis Vazirgiannis.
Knowledge and Information Systems, 2017.
Multivariate Gaussian Document Representation from Word Embeddings for Text Categorization.
Giannis Nikolentzos, Polykarpos Meladianos, François Rousseau, Yannis Stavrakas and Michalis Vazirgiannis.
15th Conference of the European Chapter of the Association for Computational Linguistics, EACL '17.
Graph-based Term Weighting Scheme for Topic Modeling.
Giannis Bekoulis and François Rousseau.
2nd International Workshop on Data Science for Social Media and Risk, SoMeRis '16.
Regularizing Text Categorization with Clusters of Words.
Konstantinos Skianis, François Rousseau and Michalis Vazirgiannis.
2016 Conference on Empirical Methods in Natural Language Processing, EMNLP '16.
Convolutional Sentence Kernel with Word Embedding for Short Text Categorization.
Jonghoon Kim, François Rousseau and Michalis Vazirgiannis.
2015 Conference on Empirical Methods in Natural Language Processing, EMNLP '15.
Community-preserving generalization of social networks.
Jordi Casas-Roma and François Rousseau.
1st International Workshop on Data Science for Social Media and Risk, SoMeRis '15.
Text Categorization as a Graph Classification Problem.
François Rousseau, Emmanouil Kiagias and Michalis Vazirgiannis.
52th Annual Meeting of the Association for Computational Linguistics and the 6th International Joint Conference on Natural Language Processing, ACL-IJCNLP '15.
Degeneracy-based Real-Time Sub-Event Detection in Twitter Stream.
Polykarpos Meladianos, Giannis Nikolentzos, François Rousseau, Yannis Stavrakas and Michalis Vazirgiannis.
9th AAAI International Conference on Web and Social Media, ICWSM '15.
Main Core Retention on Graph-of-words for Single-Document Keyword Extraction.
François Rousseau and Michalis Vazirgiannis.
37th European Conference on Information Retrieval, ECIR '15.
Graph-of-word and TW-IDF: New Approach to Ad Hoc IR.
François Rousseau and Michalis Vazirgiannis. Best Paper, Honorable Mention.
22nd ACM International Conference on Information & Knowledge Management, CIKM '13.
Efficient Online Novelty Detection in News Streams.
Margarita Karkali, François Rousseau, Alexandros Ntoulas and Michalis Vazirgiannis.
14th International Conference on Web Information System Engineering, WISE '13.
Composition of TF Normalizations: New Insights on Scoring Functions for Ad Hoc IR.
François Rousseau and Michalis Vazirgiannis.
38th ACM International Conference on Information Retrieval, SIGIR '13.
AAAI '17
CIKM '16
WWW '15, ASONAM '15 and ACM TIST
WWW '14, SIGKDD '14 and ECML PKDD '14
WWW '13, SIGKDD '13, ASONAM '13 and ECML PKDD '13
ICDM '12
November 2015 - Now
Targeting queries for mobile apps.
October 2012 - September 2015
Explored graph-of-words to mine and retrieve text with networks of features.
June 2014 - August 2014
Enhanced the Q&A part of Google Search using NLP and ML techniques.
June 2013 - August 2013
Made the machine learning system real-time. Developed a device fingerprinting system.
October 2011 - July 2012
Built the Text-To-Speech system for French (released with Android 4.1).
April 2011 - September 2011
Designed a low-dimension barycenter-based semantic space for sentiment classification.
2012 - 2015
PhD in Computer Science under the supervision of Michalis Vazirgiannis.
Dissertation on Graph-of-words: mining and retrieving text with networks of features.
2010 - 2011
MSc in Computer Science (Major in Machine Learning and Web Mining).
Thesis on Word Embeddings for Opinion mining and Sentiment Analysis.
2008 - 2011
Engineering Diploma in Telecommunications (Major in Computer Science).