no code implementations • 17 Jan 2024 • Kunpeng Guo, Dennis Diefenbach, Antoine Gourru, Christophe Gravier
In this work, we demonstrate that this strategy is sub-optimal for fine-tuning QA models, especially under a low QA annotation budget, which is a usual setting in practice due to the extractive QA labeling cost.
no code implementations • 17 Jan 2024 • Kunpeng Guo, Clement Defretiere, Dennis Diefenbach, Christophe Gravier, Antoine Gourru
Question Answering (QA) is increasingly used by search engines to provide results to their end-users, yet very few websites currently use QA technologies for their search functionality.
no code implementations • 15 Jan 2024 • Kunpeng Guo, Dennis Diefenbach, Antoine Gourru, Christophe Gravier
On the other side, most of the information on the Web is not published in highly structured data repositories like Wikidata, but rather as unstructured and semi-structured content, more concretely in HTML pages containing text and tables.
no code implementations • 12 Jan 2024 • Thibaud Leteno, Antoine Gourru, Charlotte Laclau, Christophe Gravier
In this paper, we propose an empirical exploration of this problem by formalizing two questions: (1) Can we identify the neural mechanism(s) responsible for gender bias in BERT (and by extension DistilBERT)?
1 code implementation • 21 Nov 2023 • Thibaud Leteno, Antoine Gourru, Charlotte Laclau, Rémi Emonet, Christophe Gravier
This is more suitable for real-life scenarios compared to existing methods that require annotations of sensitive attributes at train time.
1 code implementation • ACL 2021 • Thomas Dopierre, Christophe Gravier, Wilfried Logerais
It relies on diverse paraphrasing: a conditional language model is first fine-tuned for paraphrasing, and diversity is later introduced at the decoding stage at each meta-learning episode.
1 code implementation • 27 May 2021 • Thomas Dopierre, Christophe Gravier, Wilfried Logerais
It relies on diverse paraphrasing: a conditional language model is first fine-tuned for paraphrasing, and diversity is later introduced at the decoding stage at each meta-learning episode.
1 code implementation • EACL 2021 • Thomas Dopierre, Christophe Gravier, Wilfried Logerais
Additionally, some models used in Computer Vision are yet to be tested in NLP applications.
1 code implementation • COLING 2020 • Thomas Dopierre, Christophe Gravier, Julien Subercaze, Wilfried Logerais
This performance is achieved on multiple intent detection datasets, even in more challenging situations where the number of classes is large or when the dataset is highly imbalanced.
1 code implementation • 24 Mar 2018 • Julien Tissier, Christophe Gravier, Amaury Habrard
Word embeddings are commonly used as a starting point in many NLP models to achieve state-of-the-art performances.
1 code implementation • NAACL 2018 • Lucie-Aimée Kaffee, Hady Elsahar, Pavlos Vougiouklis, Christophe Gravier, Frédérique Laforest, Jonathon Hare, Elena Simperl
While Wikipedia exists in 287 languages, its content is unevenly distributed among them.
1 code implementation • NAACL 2018 • Hady Elsahar, Christophe Gravier, Frederique Laforest
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.
Ranked #14 on Zero-shot Text Search on BEIR
1 code implementation • 22 Jan 2018 • Hady Elsahar, Elena Demidova, Simon Gottschalk, Christophe Gravier, Frederique Laforest
We explore methods to extract relations between named entities from free text in an unsupervised setting.
no code implementations • IJCNLP 2017 • Hady Elsahar, Christophe Gravier, Frederique Laforest
Relation Discovery discovers predicates (relation types) from a text corpus relying on the co-occurrence of two named entities in the same sentence.
1 code implementation • EMNLP 2017 • Julien Tissier, Christophe Gravier, Amaury Habrard
Learning word embeddings on large unlabeled corpus has been shown to be successful in improving many natural language tasks.