About me

I am currently a teaching and research assistant at University of Paris-Saclay. I completed my PhD on sub-sentential translation techniques in the ILES group of the laboratory CNRS, LIMSI in 2019, under the supervision of Anne Vilnat and Gabriel Illouz.

RESEARCH EXPERIENCE

Teaching and Research Assistant

2019 - Present
University of Paris-Saclay, CNRS, LIMSI, France

PhD in Computer Science

2016 - 2019
University of Paris-Saclay, CNRS, LIMSI, France

Master internship

2015 - 2016

develop linguistic resources, text mining
prepare configuration file for crawling web pages
compare and implement methods of feature selection for automatic document classification
Supervised by Gaël Patin and Damien Nouvel

PUBLICATIONS

CONFERENCE PROCEEDINGS

Building an English-Chinese Parallel Corpus Annotated with Sub-sentential Translation Techniques
Yuming Zhai, Lufei Liu, Xinyi Zhong, Gabriel Illouz and Anne Vilnat (2020), In Proceedings of the 12th International Conference on Language Resources and Evaluation (LREC'20). Marseille, France. (to appear)
Classification automatique des procédés de traduction
Yuming Zhai, Gabriel Illouz and Anne Vilnat (2019), In Proceedings of the 26th Conférence sur le Traitement Automatique des Langues Naturelles (TALN'19). Toulouse, France. [slide][code][bibtex]
Conception d'un outil d'aide à la compréhension écrite pour les apprenants de français langue étrangère
Yuming Zhai, Gabriel Illouz and Anne Vilnat (2019), In Proceedings of the 9th Conférence Environnements Informatiques pour l'Apprentissage Humain (EIAH'19). Paris, France. [poster][bibtex]
Towards Recognizing Phrase Translation Processes: Experiments on English-French
Yuming Zhai, Pooyan Safari, Gabriel Illouz, Alexandre Allauzen and Anne Vilnat (2019), preprint version In Proceedings of the 20th International Conference on Computational Linguistics and Intelligent Text Processing (CICLING'19). La Rochelle, France. [code][poster][bibtex]
Construction of a Multilingual Corpus Annotated with Translation Relations
Yuming Zhai, Aurélien Max and Anne Vilnat (2018), In Proceedings of the First Workshop on Linguistic Resources for Natural Language Processing@COLING (LR4NLP'18). Santa Fe, New Mexico, USA. [slide][bibtex]
Construction d'un corpus multilingue annoté en relations de traduction
Yuming Zhai (2018), In Proceedings of the 20th REncontres jeunes Chercheurs en Informatique pour le TAL (RECITAL'18). Rennes, France. [poster][bibtex]

MASTER THESIS

Étude sur l'apport de la sélection des caractéristiques dans la classification multi-classe des textes
Yuming Zhai (2016), Master thesis defended at National Institute for Oriental Languages and Civilizations (INALCO) (18/20). [slide]
Supervised by Gaël Patin and Damien Nouvel

TALKS

Construction of a Multilingual Corpus Annotated with Translation Relations
Yuming Zhai (2018), In the workshop of Cross-lingual Analysis and Multilingual Parallel and Comparable Corpus Annotation: Present and Future Tendency. University of Paris Diderot, France. [slide]

RESOURCES

Last modification: 05/12/2019. Licence: Attribution-NonCommercial-ShareAlike 4.0
If you reuse the EN-ZH annotation guidelines, please cite our LREC2020 paper.
If you reuse the EN-FR annotation guidelines, please use this citation.
Annotation Guidelines of Translation Techniques for English-French
Annotation Guidelines of Translation Techniques for English-Chinese

TEACHING EXPERIENCE

Programming and database administration (Oracle SQL)

2017
IUT of Orsay, France

bachelor 1st-year practical classes (21hrs)

Operating systems and concurrent computing (C)

2019
University of Paris-Saclay, France

bachelor 3rd-year practical classes (30hrs)

Introduction to object-oriented programming (Java)

2019
University of Paris-Saclay, France

bachelor 2nd-year practical classes (24hrs)

Database management system (Oracle SQL)

2020
University of Paris-Saclay, France

bachelor 3rd-year practical classes (18hrs)

Advanced programming of interactive interfaces (JavaFX)

2020
University of Paris-Saclay, France

bachelor 3rd-year practical classes (27hrs)