no code implementations • ACL (CODI, CRAC) 2021 • Joseph Renner, Priyansh Trivedi, Gaurav Maheshwari, Rémi Gilleron, Pascal Denis
We demonstrate the performance of an end-to-end transformer-based higher-order coreference model finetuned for the task of full bridging.
no code implementations • COLING (CRAC) 2020 • Onkar Pandit, Pascal Denis, Liva Ralaivola
Specifically, we convert the external knowledge source (in this case, WordNet) into a graph, and learn embeddings of the graph nodes of low dimension to capture the crucial features of the graph topology and, at the same time, rich semantic information.
no code implementations • COLING (TextGraphs) 2020 • Mariana Vargas-Vieyra, Aurélien Bellet, Pascal Denis
Graph-based semi-supervised learning is appealing when labels are scarce but large amounts of unlabeled data are available.
no code implementations • 30 May 2023 • Bastien Liétard, Mikaela Keller, Pascal Denis
Another related question is whether and how lexical relations over pairs of words, such as synonymy, change over time.
no code implementations • 21 May 2023 • Gaurav Maheshwari, Aurélien Bellet, Pascal Denis, Mikaela Keller
In this work, we consider the problem of intersectional group fairness in the classification setting, where the objective is to learn discrimination-free models in the presence of several intersecting sensitive groups.
no code implementations • 14 Feb 2023 • Joseph Renner, Pascal Denis, Rémi Gilleron, Angèle Brunellière
Recent work on predicting category structure with distributional models, using either static word embeddings (Heyman and Heyman, 2019) or contextualized language models (CLMs) (Misra et al., 2021), report low correlations with human ratings, thus calling into question their plausibility as models of human semantic memory.
1 code implementation • 12 May 2022 • Gaurav Maheshwari, Pascal Denis, Mikaela Keller, Aurélien Bellet
Encoded text representations often capture sensitive attributes about individuals (e. g., race or gender), which raise privacy concerns and can make downstream models unfair to certain groups.
no code implementations • NAACL 2019 • Mathieu Dehouck, Pascal Denis
Languages evolve and diverge over time.
no code implementations • EMNLP 2018 • Mathieu Dehouck, Pascal Denis
This paper presents a simple framework for characterizing morphological complexity and how it encodes syntactic information.
no code implementations • EMNLP 2018 • Melissa Ailem, Bo-Wen Zhang, Aurelien Bellet, Pascal Denis, Fei Sha
Our approach learns textual and visual representations jointly: latent visual factors couple together a skip-gram model for co-occurrence in linguistic data and a generative latent variable model for visual data.
no code implementations • EACL 2017 • Mathieu Dehouck, Pascal Denis
This paper presents a new approach to the problem of cross-lingual dependency parsing, aiming at leveraging training data from different source languages to learn a parser in a target language.
no code implementations • EACL 2017 • Pascal Denis, Liva Ralaivola
This paper presents a new, efficient method for learning task-specific word vectors using a variant of the Passive-Aggressive algorithm.
no code implementations • JEPTALNRECITAL 2013 • Chlo{\'e} Braud, Pascal Denis
no code implementations • Proceedings of the 49th Annual Meeting of the Association for Computational Linguistics: Human Language Technologies 2011 • André Bittar, Pascal Amsili, Pascal Denis, Laurence Danlos
This article presents the main points in the creation of the French TimeBank (Bittar, 2010), a reference corpus annotated according to the ISO-TimeML standard for temporal annotation.