Nguyen Gia-Hung

Myriad Data · Paris

Ph.D. in Natural Language Processing, I'm interested in Knowledge Discovery and Data Mining.
I am currently working as a Data Scientist at Myriad Data.


Experience

Data Scientist

Myriad Data

Applying machine learning techniques for business automation solutions.

  • Neural network models for image and text understanding
  • ORC and NLP
  • Deploying solution on Amazon Web Services
July 2019 - Present

Research Assistance

IRIT

Design, development and validation of models for information retrieval, using machine learning and semantics in ontological resources.

  • Study of the state of the art (search engines, neural networks, etc.)
  • Data pre-processing (document indexing, text cleaning, etc.)
  • Annotations of entities/concepts from a semantic resource (WordNet, Dbpedia, UMLS)
  • Word-embedding enhancing with entities/concepts
  • Tests of different deep learning models with hyper-parameters choosing

Teaching:

  • Programming in Python [coding 101 with Python]
  • Algorithmic [algorithms with Python]
  • Programming in C [algorithms with C]
  • Databases [SQL with Oracle]
  • Information Systems and WEB programming [SQL, HTLM, CSS, PHP, javascript]
October 2015 - December 2018

Research Intern

IRIT

Design, development and validation of a Twitter-based user recommendation system based on expertise.

  • Study of the state of the art (search engines, expertise profile on social networks, etc.)
  • Data collection: retrieve tweets via TwitterAPI with thematic filters
  • Training of classification/clustering models on user profiles
  • Modeling and implementation of an expert recommendation model on Twitter
  • Validation of the model with the CrowdFlower platform
February 2015 - August 2015

Education

University of Toulouse III – Paul Sabatier

PhD in Computer Science
Thesis subject: « Neural models for Information retrieval: semantic source-driven approaches »
October 2015 - December 2018

Publication list

University of Toulouse III – Paul Sabatier

MSc in Computer Science

Specialization: Information Retrieval and Database

September 2014 - September 2015

Cantho University, Vietnam

Engineer in IT

Specialization: Information Systems and Database

September 2010 - September 2014

Skills

Programming Languages & Tools
Expertise
  • Machine learning: Keras, TensorFlow, scikit-learn
  • Search Engines: Lucene, ElasticSearch, Indri
  • Databases: MySQL, Oracle, SQLServer, MongoDB
  • Semantic: RDF, DBpedia, SPARQL