8 citations · 15 across the 10 of their papers we have counts for
10 papers
Diffusion-MF: Approximate Structured Diffusion for Sequence Labelling
Nicolas Floquet, Joseph Le Roux, Nadi Tomeh
We introduce Diffusion-MF, a discrete diffu- sion sequence labeller that places a linear-chain conditional random field (LCRF) inside the denoising loop. Unlike prior diffusion lab…
A Voronoi Cell Formulation for Principled Token Pruning in Late-Interaction Retrieval Models
Yash Kankanampati, Yuxuan Zong, Nadi Tomeh +2
Late-interaction models such as ColBERT offer competitive performance across various retrieval tasks but require storing a dense embedding for each document token, leading to a sub…
Bregman Conditional Random Fields: Sequence Labeling with Parallelizable Inference Algorithms
Caio Corro, Mathieu Lacroix, Joseph Le Roux
We propose a novel discriminative model for sequence labeling called Bregman conditional random fields (BCRF). Contrary to standard linear-chain conditional random fields, BCRF all…
Scaling Graph-Based Dependency Parsing with Arc Vectorization and Attention-Based Refinement
Nicolas Floquet, Joseph Le Roux, Nadi Tomeh +1
We propose a novel architecture for graph-based dependency parsing that explicitly constructs vectors, from which both arcs and labels are scored. Our method addresses key limitati…
Predicting Accurate Lagrangian Multipliers for Mixed Integer Linear Programs
Francesco Demelas, Joseph Le Roux, Mathieu Lacroix +1
Lagrangian relaxation stands among the most efficient approaches for solving a Mixed Integer Linear Programs (MILP) with difficult constraints. Given any duals for these constraint…
Towards Unsupervised Content Disentanglement in Sentence Representations via Syntactic Roles
Ghazi Felhi, Joseph Le Roux, Djamé Seddah
Linking neural representations to linguistic factors is crucial in order to build and analyze NLP models interpretable by humans. Among these factors, syntactic roles (e.g. subject…
Exploiting Inductive Bias in Transformers for Unsupervised Disentanglement of Syntax and Semantics with VAEs
Ghazi Felhi, Joseph Le Roux, Djamé Seddah
We propose a generative model for text generation, which exhibits disentangled latent representations of syntax and semantics. Contrary to previous work, this model does not need s…
AraBART: a Pretrained Arabic Sequence-to-Sequence Model for Abstractive Summarization
Moussa Kamal Eddine, Nadi Tomeh, Nizar Habash +2
Like most natural language understanding and generation tasks, state-of-the-art models for summarization are transformer-based sequence-to-sequence architectures that are pretraine…
Challenging the Semi-Supervised VAE Framework for Text Classification
Ghazi Felhi, Joseph Le Roux, Djamé Seddah
Semi-Supervised Variational Autoencoders (SSVAEs) are widely used models for data efficient learning. In this paper, we question the adequacy of the standard design of sequence SSV…
Feature Unification in TAG Derivation Trees
Sylvain Schmitz, Joseph Le Roux
The derivation trees of a tree adjoining grammar provide a first insight into the sentence semantics, and are thus prime targets for generation systems. We define a formalism, feat…