Papers by Hervé Blanchon
DOLFIN - Document-Level Financial Test-Set for Machine Translation (2025.findings-naacl)
Copied to clipboard
| Challenge: | Existing document-level machine translation test-sets cover general domain but fall short on specialised domains, such as legal and financial. |
| Approach: | They propose to use a document-level machine translation test-set to replace perfectly aligned sentences by presenting data in units of sections rather than sentences. |
| Outcome: | The proposed dataset is built from specialised financial documents and it shows that it can discriminate between context-sensitive and context-agnostic models and shows the weaknesses when models fail to accurately translate financial texts. |
A Spoken Drug Prescription Dataset in French for Spoken Language Understanding (2022.lrec-1)
Copied to clipboard
Ali Can Kocabiyikoglu, François Portet, Prudence Gibert, Hervé Blanchon, Jean-Marc Babouchkine, Gaëtan Gavazzi
| Challenge: | Existing systems for medical drug prescriptions are in text form and in English. |
| Approach: | They propose to provide a natural language interface to a smartphone that would allow medical practitioners to enter their prescriptions orally at the point of care. |
| Outcome: | The proposed system would allow medical practitioners to enter prescriptions orally at the point of care while leaving the system some control to make sure no legal information is forgotten. |