activity
20192023
most citedDisentangling semantics in language through VAEs and a certain architectural choice

1 citations · 2 across the 5 of their papers we have counts for

collaborators

8 papers

cs.CL2023

Interpretable Sentence Representation with Variational Autoencoders and Attention

Ghazi Felhi

In this thesis, we develop methods to enhance the interpretability of recent representation learning techniques in natural language processing (NLP) while accounting for the unavai…

cs.CL2022★ 1 cited

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…

cs.CL2022

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…

cs.CL2021

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…

cs.CL2020★ 1 cited

Disentangling semantics in language through VAEs and a certain architectural choice

Ghazi Felhi, Joseph Le Roux, Djamé Seddah

We present an unsupervised method to obtain disentangled representations of sentences that single out semantic content. Using modified Transformers as building blocks, we train a V…

cs.LG2020

Controlling the Interaction Between Generation and Inference in Semi-Supervised Variational Autoencoders Using Importance Weighting

Ghazi Felhi, Joseph Leroux, Djamé Seddah

Even though Variational Autoencoders (VAEs) are widely used for semi-supervised learning, the reason why they work remains unclear. In fact, the addition of the unsupervised object…