29 citations
- Université Paris NanterreFR5 papers
- Langues, Textes, Traitements Informatiques, CognitionFR3 papers
- University at Buffalo, State University of New YorkUS2 papers
- Aix-Marseille UniversitéFR1 paper
- Brigham Young UniversityUS1 paper
- Canada Research ChairsCA1 paper
- Carnegie Mellon UniversityUS1 paper
- Centre de physique des particules de MarseilleFR1 paper
- Centre National de la Recherche ScientifiqueFR1 paper
- Charles UniversityCZ1 paper
- Comenius University BratislavaSK1 paper
- Czech Technical University in PragueCZ1 paper
4 papers · 1 filter
Large-scale cloze evaluation reveals that token prediction tasks are neither lexically nor semantically aligned
Cassandra L. Jacobs, Loïc Grobol, Alvin Tsang
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…
Kreyòl-MT: Building MT for Latin American, Caribbean and Colonial African Creole Languages
Nathaniel R. Robinson, Raj Dabre, Ammon Shurtz +14
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 l…
UCxn: Typologically Informed Annotation of Constructions Atop Universal Dependencies
Leonie Weissweiler, Nina Böbel, Kirian Guiller +11
The Universal Dependencies (UD) project has created an invaluable collection of treebanks with contributions in over 140 languages. However, the UD annotations do not tell the full…
Sparse Logistic Regression with High-order Features for Automatic Grammar Rule Extraction from Treebanks
Santiago Herrera, Caio Corro, Sylvain Kahane
Descriptive grammars are highly valuable, but writing them is time-consuming and difficult. Furthermore, while linguists typically use corpora to create them, grammar descriptions…