“29.11.19”@3pm, B4: Seminar & CEID social hour: “Representation learning for text”, Michalis Vazirgiannis, professor at Ecole Polytechnique, Athens University of Economics and Business

pintela's picture
Category: 

Seminar & CEID social hour

 

Date-place: Friday 29 November, 3-5pm, Building Β (Room B4)

Speaker: Michalis Vazirgiannis, professor at Ecole Polytechnique, Athens University of Economics and Business

Title: Representation learning for text 

Summary: Text Mining and NLP are domains with significant history and importance in science spanning a wealth of applications with large industrial and social importance. On the other hand, recent developments in deep learning and the huge industrial investment in this domain by large industrial players have affected this domain very much producing new types or latent representations learned from vast amounts of text data.  In this talk we will resent the basic notions of representation learning in the area of text mining and NLP presenting specific methods and architectures such as word2vec, Fast-text, ELMO, Transformer along with their applications in different NLP tasks such as similarity retrieval, machine translation, entity recognition, sentiment analysis. We will also present briefly the contributions of our team in the area of Greek Language resources with deep learning.

About the speaker:   Dr. Vazirgiannis is a Distinguished Professor at LIX, Ecole Polytechnique in France and leads the Data Science and Mining (DaSciM) group.  He as well has a joint part time affiliation ar AUEB, Athens, Greece. He holds a degree in Physics and a PhD in Informatics from Athens University(Greece) and a Master degree in AI from HerioWatt Univ Edinburgh. He has conducted research in GMD-IPSI, Max Planck MPI (Germany), in INRIA/FUTURS (Paris). He has been a teaching in AUEB (Greece), Ecole Polytechnique, Telecom-Paristech, ENS (France), Tsinghua, Jiaotong Shanghai (China) and in Deusto University (Spain).  His current research interests are on machine learning and combinatorial methods for Graph analysis (including community detection, graph clustering and embeddings, influence maximization), Text mining including Graph of Words, word embeddings with applications to web advertising and marketing, event detection and summarization. He has active cooperation with industrial partners in the area of data analytics and machine learning for large scale data repositories in different application domains. He has supervised fifteen completed PhD theses. He has published three books and more than a 160 papers in international refereed journals and conferences. He has organized large scale conferences in the area of Data Mining and Machine Learning (such as ECML/PKDD) while he participates in the senior PC of AI and ML conferences – such as AAAI and IJCAI, He has received the ERCIM and the Marie Curie EU fellowships, the Tencent “Rhino-Bird International Academic Expert Award” in 2017 and in the period 2015-2018 he lead the AXA Data Science chair.

More information at: http://www.lix.polytechnique.fr/dascim

 

Photos might be posted on the site and Facebook page.

Thanks to Citrix for the kind support of our events.

Startup Growth Lite is a free theme, contributed to the Drupal Community by More than Themes.