Christophe Gravier
YOU?
Author Swipe
View article: Fair Text Classification via Transferable Representations
Fair Text Classification via Transferable Representations Open
Group fairness is a central research topic in text classification, where reaching fair treatment between sensitive groups (e.g., women and men) remains an open challenge. We propose an approach that extends the use of the Wasserstein Depen…
View article: Histoires Morales: A French Dataset for Assessing Moral Alignment
Histoires Morales: A French Dataset for Assessing Moral Alignment Open
Aligning language models with human values is crucial, especially as they become more integrated into everyday life. While models are often adapted to user preferences, it is equally important to ensure they align with moral norms and beha…
View article: Fair Text Classification with Wasserstein Independence
Fair Text Classification with Wasserstein Independence Open
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 te…
View article: Fine-tuning Strategies for Domain Specific Question Answering under Low Annotation Budget Constraints
Fine-tuning Strategies for Domain Specific Question Answering under Low Annotation Budget Constraints Open
International audience
View article: Proceedings of the ACM Web Conference 2023
Proceedings of the ACM Web Conference 2023 Open
Wikidata has grown to a knowledge graph with an impressive size. To date, it\ncontains more than 17 billion triples collecting information about people,\nplaces, films, stars, publications, proteins, and many more. On the other side,\nmost…
View article: Fair Text Classification with Wasserstein Independence
Fair Text Classification with Wasserstein Independence Open
International audience
View article: QAnswer: Towards Question Answering Search over Websites
QAnswer: Towards Question Answering Search over Websites Open
International audience
View article: ProtAugment: Unsupervised diverse short-texts paraphrasing for intent detection meta-learning
ProtAugment: Unsupervised diverse short-texts paraphrasing for intent detection meta-learning Open
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 …
View article: A Neural Few-Shot Text Classification Reality Check
A Neural Few-Shot Text Classification Reality Check Open
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…
View article: ProtAugment: Intent Detection Meta-Learning through Unsupervised Diverse Paraphrasing
ProtAugment: Intent Detection Meta-Learning through Unsupervised Diverse Paraphrasing Open
International audience
View article: Few-shot Pseudo-Labeling for Intent Detection
Few-shot Pseudo-Labeling for Intent Detection Open
International audience
View article: Learning Joint Job Embeddings Using a Job-Oriented Asymmetrical Pairing System
Learning Joint Job Embeddings Using a Job-Oriented Asymmetrical Pairing System Open
International audience
View article: Readitopics: Make Your Topic Models Readable via Labeling and Browsing
Readitopics: Make Your Topic Models Readable via Labeling and Browsing Open
Readitopics provides a new tool for browsing a textual corpus that showcases several recent work on topic labeling and topic coherence. We demonstrate the potential of these techniques to get a deeper understanding of the topics that struc…
View article: NELL2RDF: Reading the Web, and Publishing it as Linked Data
NELL2RDF: Reading the Web, and Publishing it as Linked Data Open
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 comprise…
View article: Learning to Generate Wikipedia Summaries for Underserved Languages from Wikidata
Learning to Generate Wikipedia Summaries for Underserved Languages from Wikidata Open
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 e…
View article: Learning to Generate Wikipedia Summaries for Underserved Languages from Wikidata
Learning to Generate Wikipedia Summaries for Underserved Languages from Wikidata Open
Lucie-Aimée Kaffee, Hady Elsahar, Pavlos Vougiouklis, Christophe Gravier, Frédérique Laforest, Jonathon Hare, Elena Simperl. Proceedings of the 2018 Conference of the North American Chapter of the Association for Computational Linguistics:…
View article: Real-time, Scalable, Content-based Twitter Users Recommendation
Real-time, Scalable, Content-based Twitter Users Recommendation Open
International audience
View article: Zero-Shot Question Generation from Knowledge Graphs for Unseen Predicates and Entity Types
Zero-Shot Question Generation from Knowledge Graphs for Unseen Predicates and Entity Types Open
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 mo…
View article: Pi-CEP: Predictive Complex Event Processing using Range Queries over Historical Pattern Space
Pi-CEP: Predictive Complex Event Processing using Range Queries over Historical Pattern Space Open
Sera publié à ICDM 2017 au démo track
View article: T-Rex : A Large Scale Alignment of Natural Language with Knowledge Base Triples
T-Rex : A Large Scale Alignment of Natural Language with Knowledge Base Triples Open
Several datasets with alignments between knowledge base triples and free text have been built, for several independent tasks, such as Relation Extraction, Knowledge base population, Relation Discovery…But where the others datasets have a s…
View article: Inferray: fast in-memory RDF inference
Inferray: fast in-memory RDF inference Open
International audience
View article: Multi-agent Systems for Personalized QoE-Management
Multi-agent Systems for Personalized QoE-Management Open
International audience
View article: Nelldb- An Interlinked Ontology
Nelldb- An Interlinked Ontology Open
NellDB is an Interlinked ontology where the widely used DBPedia is married with an emerging ontology called NELL (Never Ending Language Learner). This ontology enables to access NELL from DBPedia and hence it spans the search space by bein…