François Remy

ORCID iD: 0000-0003-4775-6975
Bio (via ORCID): Hello there! I'm François REMY, a young Belgian developer. I was born on August 3, 1991 and I graduated as Software Engineer at Université Libre de Bruxelles in 2014. I appreciate everything which is related to computer sciences, linguistics, and to the web as an open communication platform. I am currently employed as doctoral candidate at the Internet and Data Science Lab of UGent, working on NLP, AI, Web, and Speech Recognition. Prior to that, I had been working for about four years at Microsoft in Redmond (Seattle area) as Technical Program Manager for CSS, Text Layout, and Web Accessibility. I spend a lot of my free time inside w3c working groups, and in particular the CSS Working Group.

Add to list
RobBERT-2023 : keeping Dutch language models up-to-date at a lower cost thanks to model conversion

Pieter Delobelle and François Remy (UGent)

(2024) COMPUTATIONAL LINGUISTICS IN THE NETHERLANDS JOURNAL. 13. p.193-203
Add to list
- Conference Paper
- C1
- open access
Trans-tokenization and cross-lingual vocabulary transfers : language adaptation of LLMs for low-resource NLP

François Remy (UGent) , P. Delobelle, H. Avetisyan, Alfiya Khabibullina, M. de Lhoneux and Thomas Demeester (UGent)

(2024) 1st Conference on Language Modeling (COLM 2024), Proceedings.
Add to list
- PhD Thesis
Deciphering the semantics of biomedical texts

François Remy (UGent)

(2024)
Add to list
- Journal Article
- A1
- open access
BioLORD-2023 : semantic textual representations fusing large language models and clinical knowledge graph insights

François Remy (UGent) , Kris Demuynck (UGent) and Thomas Demeester (UGent)

(2024) JOURNAL OF THE AMERICAN MEDICAL INFORMATICS ASSOCIATION. 31(9). p.1844-1855
Add to list
Boosting adverse drug event normalization on social media: general-purpose model initialization and biomedical semantic text similarity benefit zero-shot linking in informal contexts

François Remy (UGent) , S. Scaboro and B. Portelli

(2023) Proceedings of the 11th International Workshop on Natural Language Processing for Social Media. p.47-52
Add to list
- Conference Paper
- C1
- open access
BioDEX : large-scale biomedical adverse drug event extraction for real-world pharmacovigilance

Karel D'Oosterlinck (UGent) , François Remy (UGent) , Johannes Deleu (UGent) , Thomas Demeester (UGent) , Chris Develder (UGent) , Klim Zaporojets, Arya Ghodsi, S Ellershaw, J. Collins and C. Potts

(2023) 2023 Conference on Empirical Methods in Natural Language Processing (EMNLP 2023), Proceedings.
Add to list
Automatic glossary of clinical terminology : a large-scale dictionary of biomedical definitions generated from ontological knowledge

François Remy (UGent) , Kris Demuynck (UGent) and Thomas Demeester (UGent)

(2023) The 22nd Workshop on Biomedical Natural Language Processing and BioNLP Shared Tasks. p.265-272
Add to list
Detecting idiomatic multiword expressions in clinical terminology using definition-based representation learning

François Remy (UGent) , Alfiya Khabibullina and Thomas Demeester (UGent)

(2023) Proceedings of the 19th Workshop on Multiword Expressions (MWE 2023). p.73-80
Add to list
BioLORD : learning ontological representations from definitions for biomedical concepts and their textual descriptions

François Remy (UGent) , Kris Demuynck (UGent) and Thomas Demeester (UGent)

(2022) Findings of the Association for Computational Linguistics : EMNLP 2022. p.1454-1465
Add to list
- Conference Paper
- C1
- open access
Taming large lexicons : translating clinical text using medical ontologies and sentence templates

François Remy (UGent) , P. De Jaeger and Kris Demuynck (UGent)

(2022) EmP : 1st RADar conference on Engineer meets Physician, Proceedings.

Academic Bibliography

François Remy

RobBERT-2023 : keeping Dutch language models up-to-date at a lower cost thanks to model conversion

Trans-tokenization and cross-lingual vocabulary transfers : language adaptation of LLMs for low-resource NLP

Deciphering the semantics of biomedical texts

BioLORD-2023 : semantic textual representations fusing large language models and clinical knowledge graph insights

Boosting adverse drug event normalization on social media: general-purpose model initialization and biomedical semantic text similarity benefit zero-shot linking in informal contexts

BioDEX : large-scale biomedical adverse drug event extraction for real-world pharmacovigilance

Automatic glossary of clinical terminology : a large-scale dictionary of biomedical definitions generated from ontological knowledge

Detecting idiomatic multiword expressions in clinical terminology using definition-based representation learning

BioLORD : learning ontological representations from definitions for biomedical concepts and their textual descriptions

Taming large lexicons : translating clinical text using medical ontologies and sentence templates

Contents

Support

Contact