Rémi Lebret

Neural Text Generation from Structured Data with Application to the Biography Domain

2016

This paper introduces a neural model for concept-to-text generation that scales to large, rich domains. It generates biographical sentences from fact tables on a new dataset of biographies from Wikipedia. This set is an order …

Weakly Supervised Active Learning with Cluster Annotation

2018 · arXiv (Cornell University)

In this work, we introduce a novel framework that employs cluster annotation to boost active learning by reducing the number of human interactions required to train deep neural networks. Instead of annotating single samples individually, …

AdaGrid: Adaptive Grid Search for Link Prediction Training Objective

2022 · arXiv (Cornell University)

One of the most important factors that contribute to the success of a machine learning model is a good training objective. Training objective crucially influences the model's performance and generalization capabilities. This paper specifically focuses …