scispace - formally typeset
A

Anne-Laure Ligozat

Researcher at École Normale Supérieure

Publications -  92
Citations -  1311

Anne-Laure Ligozat is an academic researcher from École Normale Supérieure. The author has contributed to research in topics: Question answering & Annotation. The author has an hindex of 16, co-authored 87 publications receiving 781 citations. Previous affiliations of Anne-Laure Ligozat include Centre national de la recherche scientifique & Université Paris-Saclay.

Papers
More filters
Journal ArticleDOI

BLOOM: A 176B-Parameter Open-Access Multilingual Language Model

Teven Le Scao, +386 more
- 09 Nov 2022 - 
TL;DR: BLOOM as discussed by the authors is a decoder-only Transformer language model that was trained on the ROOTS corpus, a dataset comprising hundreds of sources in 46 natural and 13 programming languages (59 in total).
Proceedings ArticleDOI

Syntactic Sentence Simplification for French

TL;DR: This approach is based on the study of two parallel corpora and aims to identify the linguistic phenomena involved in the manual simplification of French texts and organise them within a typology to generate simplified sentences.
Journal ArticleDOI

Hybrid methods for improving information access in clinical documents: concept, assertion, and relation identification

TL;DR: The authors confirm that the use of only machine-learning methods is highly dependent on the annotated training data, and thus obtained better results for well-represented classes.

CARAMBA: Concept, Assertion, and Relation Annotation using Machine-learning Based Approaches

TL;DR: This year’s i2b2/VA challenge is dedicated to medical concept extraction as well as the annotation of assertions and relationships of concepts, mainly based upon machine-learning systems.
Journal ArticleDOI

A French clinical corpus with comprehensive semantic annotations: development of the Medical Entity and Relation LIMSI annOtated Text corpus (MERLOT)

TL;DR: A corpus of clinical narratives in French annotated for linguistic, semantic and structural information, aimed at clinical information extraction is presented and harmonization tools to automatically identify annotation differences to be addressed to improve the overall corpus quality are introduced.