Search Results for author: Guillaume Bouchard

Found 20 papers, 3 papers with code

Detecting Abusive Language on Online Platforms: A Critical Analysis

no code implementations27 Feb 2021 Preslav Nakov, Vibha Nayak, Kyle Dent, Ameya Bhatawdekar, Sheikh Muhammad Sarwar, Momchil Hardalov, Yoan Dinkov, Dimitrina Zlatkova, Guillaume Bouchard, Isabelle Augenstein

Abusive language on online platforms is a major societal problem, often leading to important societal problems such as the marginalisation of underrepresented minorities.

Abusive Language Natural Language Processing

Knowledge Graph Completion via Complex Tensor Factorization

2 code implementations22 Feb 2017 Théo Trouillon, Christopher R. Dance, Johannes Welbl, Sebastian Riedel, Éric Gaussier, Guillaume Bouchard

In statistical relational learning, knowledge graph completion deals with automatically understanding the structure of large knowledge graphs---labeled directed graphs---and predicting missing relationships---labeled edges.

Knowledge Graph Completion Link Prediction +1

Complex Embeddings for Simple Link Prediction

9 code implementations20 Jun 2016 Théo Trouillon, Johannes Welbl, Sebastian Riedel, Éric Gaussier, Guillaume Bouchard

In statistical relational learning, the link prediction problem is key to automatically understand the structure of large knowledge bases.

Link Prediction Relational Reasoning

A Factorization Machine Framework for Testing Bigram Embeddings in Knowledgebase Completion

no code implementations WS 2016 Johannes Welbl, Guillaume Bouchard, Sebastian Riedel

Embedding-based Knowledge Base Completion models have so far mostly combined distributed representations of individual entities or relations to compute truth scores of missing links.

Knowledge Base Completion

Online Learning to Sample

no code implementations30 Jun 2015 Guillaume Bouchard, Théo Trouillon, Julien Perez, Adrien Gaidon

Stochastic Gradient Descent (SGD) is one of the most widely used techniques for online optimization in machine learning.

Image Classification online learning

Approximate Inference with the Variational Holder Bound

no code implementations19 Jun 2015 Guillaume Bouchard, Balaji Lakshminarayanan

We introduce the Variational Holder (VH) bound as an alternative to Variational Bayes (VB) for approximate Bayesian inference.

Bayesian Inference Numerical Integration

Overlapping Trace Norms in Multi-View Learning

no code implementations24 Apr 2014 Behrouz Behmardi, Cedric Archambeau, Guillaume Bouchard

Multi-view learning leverages correlations between different sources of data to make predictions in one view based on observations in another view.

Imputation MULTI-VIEW LEARNING

Group-sparse Embeddings in Collective Matrix Factorization

no code implementations20 Dec 2013 Arto Klami, Guillaume Bouchard, Abhishek Tripathi

CMF is a technique for simultaneously learning low-rank representations based on a collection of matrices with shared entities.

MULTI-VIEW LEARNING Recommendation Systems

Variational bounds for mixed-data factor analysis

no code implementations NeurIPS 2010 Mohammad E. Khan, Guillaume Bouchard, Kevin P. Murphy, Benjamin M. Marlin

We show that EM is significantly more robust in the presence of missing data compared to treating the latent factors as parameters, which is the approach used by exponential family PCA and other related matrix-factorization methods.

Asymptotically Optimal Regularization in Smooth Parametric Models

no code implementations NeurIPS 2009 Percy S. Liang, Guillaume Bouchard, Francis R. Bach, Michael. I. Jordan

Many types of regularization schemes have been employed in statistical learning, each one motivated by some assumption about the problem domain.

Multi-Task Learning

Cannot find the paper you are looking for? You can Submit a new open access paper.