Loïc Grobol
YOU?
Author Swipe
View article: Uncovering patterns of semantic predictability in sentence processing
Uncovering patterns of semantic predictability in sentence processing Open
Psycholinguistic researchers have used the cloze task to measure the predictability of upcoming words, but have largely discarded the variability in the structure of responses people provide. This variability in the semantic structure of r…
View article: Inclusive Language Usage and Perception. A Study of Divisive Language Practices
Inclusive Language Usage and Perception. A Study of Divisive Language Practices Open
International audience
View article: Large-scale cloze evaluation reveals that token prediction tasks are neither lexically nor semantically aligned
Large-scale cloze evaluation reveals that token prediction tasks are neither lexically nor semantically aligned Open
In this work we compare the generative behavior at the next token prediction level in several language models by comparing them to human productions in the cloze task. We find that while large models trained for longer are typically better…
View article: Uncovering patterns of semantic predictability in sentence processing
Uncovering patterns of semantic predictability in sentence processing Open
Psycholinguistic researchers have used the cloze task to measure the predictability of upcoming words, but have largely discarded the variability in the structure of responses people provide. This variability in the semantic structure of r…
View article: ARBRES Kenstur: a Breton-French Parallel Corpus Rooted in Field Linguistics
ARBRES Kenstur: a Breton-French Parallel Corpus Rooted in Field Linguistics Open
International audience
View article: Kreyòl-MT: Building MT for Latin American, Caribbean and Colonial African Creole Languages
Kreyòl-MT: Building MT for Latin American, Caribbean and Colonial African Creole Languages Open
A majority of language technologies are tailored for a small number of high-resource languages, while relatively many low-resource languages are neglected. One such group, Creole languages, have long been marginalized in academic study, th…
View article: CreoleVal: Multilingual Multitask Benchmarks for Creoles
CreoleVal: Multilingual Multitask Benchmarks for Creoles Open
Creoles represent an under-explored and marginalized group of languages, with few available resources for NLP research. While the genealogical ties between Creoles and a number of highly resourced languages imply a significant potential fo…
View article: Gwnewch Ramadegau Wici!
Gwnewch Ramadegau Wici! Open
International audience
View article: CreoleVal: Multilingual Multitask Benchmarks for Creoles
CreoleVal: Multilingual Multitask Benchmarks for Creoles Open
Creoles represent an under-explored and marginalized group of languages, with few available resources for NLP research.While the genealogical ties between Creoles and a number of highly-resourced languages imply a significant potential for…
View article: Zelda Rose: a tool for hassle-free training of transformer models
Zelda Rose: a tool for hassle-free training of transformer models Open
Zelda Rose is a command line interface for pretraining transformer-based models. Its purpose is to enable an easy start for users interested in training these ubiquitous models, but unable or unwilling to engage with more comprehensive — b…
View article: We thought the eyes of coreference were shut to multiword expressions and they mostly are
We thought the eyes of coreference were shut to multiword expressions and they mostly are Open
International audience
View article: A Methodology for the Comparison of Human Judgments With Metrics for Coreference Resolution
A Methodology for the Comparison of Human Judgments With Metrics for Coreference Resolution Open
International audience
View article: Coreference resolution for spoken French
Coreference resolution for spoken French Open
Une chaîne de coréférences est l'ensemble des expressions linguistiques — ou mentions — qui font référence à une même entité ou un même objet du discours.La tâche de reconnaissance des chaînes de coréférences consiste à détecter l'ensemble…
View article: Hybrid Neural Models For Sequence Modelling: The Best Of Three Worlds
Hybrid Neural Models For Sequence Modelling: The Best Of Three Worlds Open
Publication dans le système de "pre-print" arXiv de la traduction en anglais de l'article accepté à la conférence française TALN 2019.
View article: Hybrid Neural Models For Sequence Modelling: The Best Of Three Worlds
Hybrid Neural Models For Sequence Modelling: The Best Of Three Worlds Open
We propose a neural architecture with the main characteristics of the most successful neural models of the last years: bidirectional RNNs, encoder-decoder, and the Transformer model. Evaluation on three sequence labelling tasks yields resu…
View article: Neural Coreference Resolution with Limited Lexical Context and Explicit Mention Detection for Oral French
Neural Coreference Resolution with Limited Lexical Context and Explicit Mention Detection for Oral French Open
International audience
View article: Seq2Biseq: Bidirectional Output-wise Recurrent Neural Networks for\n Sequence Modelling
Seq2Biseq: Bidirectional Output-wise Recurrent Neural Networks for\n Sequence Modelling Open
During the last couple of years, Recurrent Neural Networks (RNN) have reached\nstate-of-the-art performances on most of the sequence modelling problems. In\nparticular, the "sequence to sequence" model and the neural CRF have proved to\nbe…
View article: Seq2Biseq: Bidirectional Output-wise Recurrent Neural Networks for Sequence Modelling
Seq2Biseq: Bidirectional Output-wise Recurrent Neural Networks for Sequence Modelling Open
During the last couple of years, Recurrent Neural Networks (RNN) have reached state-of-the-art performances on most of the sequence modelling problems. In particular, the "sequence to sequence" model and the neural CRF have proved to be ve…
View article: Neural Coreference Resolution with Limited Lexical Context and Explicit Mention Detection for Oral
Neural Coreference Resolution with Limited Lexical Context and Explicit Mention Detection for Oral Open
We propose an end-to-end coreference resolution system obtained by adapting neural models that have recently improved the state-of-the-art on the OntoNotes benchmark to make them applicable to other paradigms for this task. We report the p…
View article: XML-TEI-URS: using a TEI format for annotated linguistic resources
XML-TEI-URS: using a TEI format for annotated linguistic resources Open
International audience
View article: ANCOR-AS: Enriching the ANCOR Corpus with Syntactic Annotations
ANCOR-AS: Enriching the ANCOR Corpus with Syntactic Annotations Open
International audience
View article: Interoperable annotation of (co)references in the Democrat project
Interoperable annotation of (co)references in the Democrat project Open
International audience