Aurélien Bossard

Learn More
The Text Analysis Conferences (TAC) offer a unique occasion to show innovative approaches to text summarization. As a first incursion into this new research area, LIPN participated in the following tasks of TAC 2008: the Update Summarization task and the Opinion Summarization task. LIPN systems obtained good results for Opinion Summarization; however, we(More)
In this paper, we present a novel approach for automatic summarization. Our system, called CBSEAS, integrates a new method to detect redundancy at its very core, and produce more expressive summaries than previous approaches. Moreover, we show that our system is versatile enough to integrate opinion mining techniques, so that it is capable of producing(More)
In this paper, we present a novel approach for automatic summarization. We believe redundancy is the most important factor in building a summary automatically. We want to detect it automatically with an unsupervized method that could apply to any multi-document summarization task. CBSEAS, the system implementing our approach integrates a new method to(More)
In this paper, we present a novel approach for automatic summarization. CBSEAS, the system implementing this approach, integrates a method to detect redundancy at its very core, in order to produce more expressive summaries than previous approaches. The evaluation of our system during TAC 2008 —the Text Analysis Conference— revealed that, even if our system(More)
We present PathSum, a high-performing hierarchical-topic based singleand multi-document automatic text summarization framework. This approach leverages Bayesian nonparametric methods to model sentences as paths through a tree and create a hierarchy of topics from the input in an unsupervised setting. We describe the generative model used to learn a topic(More)
The Text Analysis Conferences (TAC) offer a unique occasion to show innovative approaches to text summarization. As a first incursion into this new research area, LIPN participated in the Update Summarization task of TAC 2008. The LIPN wanted to improve the results obtained during TAC 2008 and to confirm that the changes made to its summarization system(More)
RÉSUMÉ. Dans cet article, nous comparons les résultats produits par différentes approches de résumé multi-documents. Nous opposons deux approches classiques à la nôtre qui place la modélisation de la diversité informationnelle du corpus au centre du processus. Nous évaluons également l’impact de différentes mesures de similarité entre phrases. Les(More)