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