NLP Developer

VO TUAN ANH AN

MASTER STUDENT IN COMPUTATIONAL LINGUISTICS

PROFESSIONAL EXPERIENCE

Intern computational linguist specializing in semantics and pragmatics Laboratory of Formal Linguistics, CNRS, Université Paris Cité, 75013 Paris, France May - August 2019 Annotation of the discursive structure of a written or oral text in English, French, and Vietnamese. The annotation involves finding the 'question under discussion' (implicit question) that precedes each statement in a text, following precise instructions. Intern computational linguist specializing in Vietnamese Text-To-Speech (TTS) and Deep Learning for Audio De-noising

LUDO-VIC SAS – 103 Boulevard Macdonald 75019 PARIS, France Jan - May 2022 Improved sound quality in noisy recordings for languages lacking TTS systems (e.g., Ukrainian, Bangladeshi, Afghan) using deep learning.

Evaluated and selected appropriate deep learning algorithms for audio signal denoising. Contributed to a French language learning app with Vietnamese TTS, targeting Vietnamese speakers. Intern computational linguist specializing in Neural Machine Translation CEA-LIST – CEA Paris Saclay 91477 PALAISEAU, France June - Sept 2022 Developed and integrated robust transfer learning models for domain adaptation in neural translation. Evaluated suitable transfer learning algorithms to enhance neural translation system quality. Specialized in various domains including pharmacy, health, medicine, and law. Conducted focused experiments on the English-French language pair. Intern computational linguist specializing in Generative Artificial Intelligence Research internship Laboratory of Formal Linguistics, CNRS, Université Paris Cité, 75013 Paris, France Jan - July 2023

Conducted comparative analysis of BERT and ALBERT's attention matrices and token representation mechanisms.

Investigated Large Language Models (LLMs) like BART, T5, T5v1.1, FLAN T5 for their utilization of structured and unstructured data to enhance predictive capacities. Engaged in coding based on the framework of TextWorld, a tool introduced by Microsoft Research in 2018. TextWorld serves as an influential platform for AI research, particularly in studying reinforcement learning agents within the frameworks of Natural Language Processing (NLP) and Natural Language Understanding (NLU).

Utilized TextWorld to pre-process the dataset "First TextWorld Problems: A Reinforcement and Language Learning Challenge" from Microsoft Research, creating training, validating, and testing datasets for further study.

EDUCATION

Advanced Deep learning for NLP & Multilingual NLP

Specialized Database (Weak consistency, Cassandra, Property Graph Model, Neo4j, Introduction to Semantic Web and Linked Open Data (LOD)), Database (SQLite) Algorithms & Graph Theory, Advanced Formal and Computational Semantics Advanced Semantics and Pragmatics,

Formal Language and Parsing (Automatic Syntax Analysis) Advanced Experimental Syntax, New Theories of Syntax Computational terminology, SQL, XML, Industrialization of NLP Technical skills in Experimental and Computational Phonology / Signal Processing Automatic Speech Recognition (ASR), Advanced Phonology, Phonology & Phonetics Morphology, TAM (Tense, Aspect, Mood)

Master in Computational linguistics

Université Paris Cité UFR Linguistics Sept 2022 - June 2024 University of Rouen Normandy, France Sept 2012 - Oct 2015 PhD in Sciences of Language - Specialization in Terminology Thesis: "Terminology of computer science: socioterminological approach" HTML, DHTML, Javascript, CSS, SQL Server, Core & Advanced Java, XML, UML, ASP.NET, Adv.Net & Security.Net, XML Webservices, JSP, STRUTS, EJB, JMS, J2EE, XMJ, XMJ Webservice, eProject Can Tho University, Vietnam Sept 2008 - Jan 2010 HDSE (Higher Diploma in Software Engineering)

Master student in Computational

Linguistics

PhD in Sciences of Language -

Terminology

Postal address: 271A/7 Zone 6, An

Binh Ward, Ninh Kieu District, Can

Tho City, Vietnam

Email: **.**.****.***@*****.***

Contact this candidate