• Publications
  • Influence
CamemBERT: a Tasty French Language Model
TLDR
We train a monolingual Transformer-based language model on the French language using recent large-scale corpora. Expand
  • 146
  • 27
  • PDF
What Does BERT Learn about the Structure of Language?
TLDR
We perform a series of experiments to unpack the elements of English language structure learned by BERT. Expand
  • 264
  • 26
  • PDF
Overview of the SPMRL 2013 Shared Task: A Cross-Framework Evaluation of Parsing Morphologically Rich Languages
TLDR
This paper reports on the first shared task on statistical parsing of morphologically rich languages (MRLs). Expand
  • 147
  • 14
  • PDF
Statistical Parsing of Morphologically Rich Languages (SPMRL) What, How and Whither
TLDR
We synthesize the contributions of researchers working on parsing Arabic, Basque, French, German, Hebrew, Hindi and Korean to point out shared solutions across languages. Expand
  • 121
  • 13
  • PDF
Introducing the SPMRL 2014 Shared Task on Parsing Morphologically-rich Languages
TLDR
This first joint meeting on Statistical Parsing of Morphologically Rich Languages and Syntactic Analysis of Non-Canonical English featured a shared task on statistical parsing of morphologically rich languages (SPMRL). Expand
  • 77
  • 11
  • PDF
Universal Dependencies 2.1
TLDR
Universal Dependencies is a project that seeks to develop cross-linguistically consistent treebank annotation for many languages, with the goal of facilitating multilingual parser development, cross-language learning, and parsing research from a language typology perspective. Expand
  • 59
  • 10
Le corpus Sequoia : annotation syntaxique et exploitation pour l'adaptation d'analyseur par pont lexical (The Sequoia Corpus : Syntactic Annotation and Use for a Parser Lexical Domain Adaptation
TLDR
Nous presentons dans cet article la methodologie de constitution et les caracteristiques du corpus Sequoia, un corpus en francais, syntaxiquement annote d'apres un schema d'annotation tres proche de celui du French Treebank (Abeille et Barrier, 2004), et librement disponible, en constituants et en dependances. Expand
  • 100
  • 9
  • PDF
Universal Dependencies 2.0 – CoNLL 2017 Shared Task Development and Test Data
TLDR
This release complements the UD 2.0 release (http://hdl.handle.net/11234/1-1983) to a full release of UD treebanks. Expand
  • 62
  • 6
Parsing Morphologically Rich Languages: Introduction to the Special Issue
TLDR
This special issue reports on methods that successfully address the challenges involved in parsing a range of morphologically rich languages (MRLs). Expand
  • 62
  • 5
  • PDF
C-Structures and F-Structures for the British National Corpus
TLDR
We describe how the British National Corpus (BNC), a one hundred million word balanced corpus of British English, was parsed into Lexical Functional Grammar (LFG) c-structures and f-Structures, using a treebank-based parsing architecture. Expand
  • 15
  • 5
  • PDF
...
1
2
3
4
5
...