Juan-Manuel Torres-Moreno

A Turing Test to Evaluate a Complex Summarization Task

This paper deals with a new strategy to evaluate a Natural Language Processing NLP complex task using the Turing test. Automatic summarization based on sentence compression requires to asses informativeness and modify inner sentence structures. This is much more intrinsically related with real rephrasing than plain sentence extraction and ranking paradigm so new evaluation methods are needed. We propose a novel imitation game to evaluate Automatic Summarization by Compression ASC. Rationale of this Turing-like evaluation could be applied to many other NLP complex tasks like Machine translation or Text Generation. We show that a state of the art ASC system can pass such a test and simulate a human summary in 60% of the cases.

Automatic specialized vs. non-specialized sentence differentiation

Compilation of Languages for Specific Purposes (LSP) corpora is a task which is fraught with several difficulties (mainly time and human effort), because it is not easy to discern between specialized and non-specialized text. The aim of this work is to study automatic specialized vs. non-specialized sentence differentiation. The experiments are carried out on two corpora of sentences extracted from specialized and non-specialized texts. One in economics (academic publications and news from newspapers), another about sexuality (academic publications and texts from forums and blogs). First we show the feasibility of the task using a statistical n-gram classifier. Then we show that grammatical features can also be used to classify sentences from the first corpus. For such purpose we use association rule mining.

Predicting Personalized Academic and Career Roads: First Steps Toward Multi-Uses Recommender Systems

Nobody knows what ones do in the future and everyone will have had a different answer to the question: how do you see yourself in 5 years after your current job/diploma? We introduce concepts, large categories of fields of studies or job domains to represent the vision of the future of the users trajectory. Then, we show how they can influence the prediction when proposing him a set of next steps to take.

A First Summarization System of a Video in a Target Language

In this paper, we present the first results of the project AMIS (Access Multilingual Information opinionS) funded by Chist-Era. The main goal of this project is to understand the content of a video in a foreign language. In this work, we consider the understanding process, such as the aptitude to capture the most important ideas contained in a media expressed in a foreign language. In other words, the understanding will be approached by the global meaning of the content of a support and not by the meaning of each fragment of a video.

E-Gen : traitement automatique d'informations de ressources humaines

L’internet est au cœur du marche du travail et son utilisation s’etend a mesure qu’augmente le nombre d’internautes. La recherche d’emploi au travers des « bourses a l’emploi electroniques » et l’e-recrutement se sont banalises. Cette explosion d’informations pose divers problemes pour leur traitement rapide et efficace. Nous presentons le projet EGen, qui permet d’analyser les offres d’emploi de maniere automatique ou assistee. Base sur des classifieurs pilotes par un automate de Markov, le systeme obtient de tres bons resultats. Nous proposons egalement une strategie afin d’assister les recruteurs dans la tâche – difficile et d’une grande subjectivite – de classement de candidatures. Nous evaluons differentes mesures de similarite afin d’effectuer un classement pertinent des candidatures. L’utilisation d’un modele de relevance feedback a permis de surpasser nos resultats.