Zobrazeno 1 - 10
of 124
pro vyhledávání: '"Gravier, Christophe"'
Publikováno v:
21st International Symposium on Intelligent Data Analysis, IDA 2023
In recent years, large Transformer-based Pre-trained Language Models (PLM) have changed the Natural Language Processing (NLP) landscape, by pushing the performance boundaries of the state-of-the-art on a wide variety of tasks. However, this performan
Externí odkaz:
http://arxiv.org/abs/2401.06495
Group fairness is a central research topic in text classification, where reaching fair treatment between sensitive groups (e.g. women vs. men) remains an open challenge. This paper presents a novel method for mitigating biases in neural text classifi
Externí odkaz:
http://arxiv.org/abs/2311.12689
Recent research considers few-shot intent detection as a meta-learning problem: the model is learning to learn from a consecutive set of small tasks named episodes. In this work, we propose ProtAugment, a meta-learning algorithm for short texts class
Externí odkaz:
http://arxiv.org/abs/2105.12995
Modern classification models tend to struggle when the amount of annotated data is scarce. To overcome this issue, several neural few-shot classification models have emerged, yielding significant progress over time, both in Computer Vision and Natura
Externí odkaz:
http://arxiv.org/abs/2101.12073
Autor:
Giménez-García, José M., Duarte, Maísa, Zimmermann, Antoine, Gravier, Christophe, Hruschke Jr., Estevam R., Maret, Pierre
NELL is a system that continuously reads the Web to extract knowledge in form of entities and relations between them. It has been running since January 2010 and extracted over 50,000,000 candidate statements. NELL's generated data comprises all the c
Externí odkaz:
http://arxiv.org/abs/1804.05639
Word embeddings are commonly used as a starting point in many NLP models to achieve state-of-the-art performances. However, with a large vocabulary and many dimensions, these floating-point representations are expensive both in terms of memory and ca
Externí odkaz:
http://arxiv.org/abs/1803.09065
Autor:
Kaffee, Lucie-Aimée, Elsahar, Hady, Vougiouklis, Pavlos, Gravier, Christophe, Laforest, Frédérique, Hare, Jonathon, Simperl, Elena
While Wikipedia exists in 287 languages, its content is unevenly distributed among them. In this work, we investigate the generation of open domain Wikipedia summaries in underserved languages using structured data from Wikidata. To this end, we prop
Externí odkaz:
http://arxiv.org/abs/1803.07116
We present a neural model for question generation from knowledge base triples in a "Zero-Shot" setup, that is generating questions for triples containing predicates, subject types or object types that were not seen at training time. Our model leverag
Externí odkaz:
http://arxiv.org/abs/1802.06842
We explore methods to extract relations between named entities from free text in an unsupervised setting. In addition to standard feature extraction, we develop a novel method to re-weight word embeddings. We alleviate the problem of features sparsit
Externí odkaz:
http://arxiv.org/abs/1801.07174
Autor:
Gravier, Christophe
Présentation de travaux sur la création d'environnements collaboratifs synchrones réutilisables pour télé-TPs.