This thesis, which is organized in two independent parts, presents work on distributional semantics and on variable selection. In the first part, we introduce a new method for learning good word representations using large quantities of unlabeled sentences. The method is based on a probabilistic model of sentence, using a hidden Markov model and a syntactic dependency tree. The latent variables, which correspond to the nodes of the dependency tree, aim at capturing the meanings of the words. We develop an efficient algorithm to perform inference and learning in those models, based on online EM and approximate message passing. We then evaluate our models on intrinsic tasks such as predicting human similarity judgements or word categorization...
Modeling natural language is among fundamental challenges of artificial intelligence and the design ...
In this work, we focus on the design and estimation - from partial observations - of graphical model...
Finite mixture regression models are useful for modeling the relationship between a response andpred...
This thesis, which is organized in two independent parts, presents work on distributional semantics ...
The role of a stochastic language model is to give the best estimation possible of the probability o...
With the increasing availability of large datasets machine learning techniques are becoming an incr...
This thesis deals with the development of estimation algorithms with embedded feature selection the ...
This thesis deals with the problem of modeling and estimation of high-dimensional MoE models, toward...
With the increasing availability of large datasets machine learning techniques are be-coming an incr...
Modeling natural language is among fundamental challenges of artificial intelligence and the design ...
This thesis deals with the problem of modeling and estimation of high-dimensional MoE models, toward...
Learning stochastic models generating sequences has many applications in natural language processing...
This thesis deals with variable selection for clustering. This problem has become all the more chall...
International audienceIn this article, we describe a new approach to distributional semantics. This ...
This thesis presents a detailed study of multinomial regression, with a special focus on its applica...
Modeling natural language is among fundamental challenges of artificial intelligence and the design ...
In this work, we focus on the design and estimation - from partial observations - of graphical model...
Finite mixture regression models are useful for modeling the relationship between a response andpred...
This thesis, which is organized in two independent parts, presents work on distributional semantics ...
The role of a stochastic language model is to give the best estimation possible of the probability o...
With the increasing availability of large datasets machine learning techniques are becoming an incr...
This thesis deals with the development of estimation algorithms with embedded feature selection the ...
This thesis deals with the problem of modeling and estimation of high-dimensional MoE models, toward...
With the increasing availability of large datasets machine learning techniques are be-coming an incr...
Modeling natural language is among fundamental challenges of artificial intelligence and the design ...
This thesis deals with the problem of modeling and estimation of high-dimensional MoE models, toward...
Learning stochastic models generating sequences has many applications in natural language processing...
This thesis deals with variable selection for clustering. This problem has become all the more chall...
International audienceIn this article, we describe a new approach to distributional semantics. This ...
This thesis presents a detailed study of multinomial regression, with a special focus on its applica...
Modeling natural language is among fundamental challenges of artificial intelligence and the design ...
In this work, we focus on the design and estimation - from partial observations - of graphical model...
Finite mixture regression models are useful for modeling the relationship between a response andpred...