La correction automatisée de textes (CAT) vise à évaluer automatiquement la qualité de textes écrits. L’automatisation permet une évaluation à grande échelle ainsi qu’une amélioration de la cohérence, de la fiabilité et de la normalisation du processus. Ces caractéristiques sont particulièrement importantes dans le contexte des examens de certification linguistique. Cependant, un goulot d’étranglement majeur dans le développement des systèmes CAT est la disponibilité des corpus. Dans cet article, nous visons à encourager le développement de systèmes de correction automatique en fournissant le corpus TCFLE-8, un corpus de 6~569 essais collectés dans le contexte de l’examen de certification Test de Connaissance du Français (TCF). Nous décrivons la procédure d’évaluation stricte qui a conduit à la notation de chaque essai par au moins deux évaluateurs selon l’échelle du Cadre européen commun de référence pour les langues (CECR) et à la création d’un corpus équilibré. Nous faisons également progresser les performances de l’état de l’art pour la tâche de CAT en français en expérimentant deux solides modèles de référence.

Les architectures d’apprentissage automatique reposant sur la définition de traits linguistiques ont connu un succès important dans le domaine de l’évaluation automatique de la lisibilité des textes (ARA) et ont permis de faire se rencontrer informatique et théorie psycholinguistique. Toutefois, les récents développements se sont tournés vers l’apprentissage profond et les réseaux de neurones. Dans cet article, nous cherchons à réconcilier les deux approches. Nous présentons une comparaison systématique de 6 architectures hybrides (appliquées à plusieurs langues et publics) que nous comparons à ces deux approches concurrentes. Les diverses expériences réalisées ont clairement mis en évidence deux méthodes d’hybridation : Soft-Labeling et concaténation simple. Ces deux architectures sont également plus efficaces lorsque les données d’entraînement sont réduites. Cette étude est la première à comparer systématiquement différentes architectures hybrides et à étudier leurs performances dans plusieurs tâches de lisibilité.

Linguistic features have a strong contribution in the context of the automatic assessment of text readability (ARA). They have been one of the anchors between the computational and theoretical models. With the development in the ARA field, the research moved to Deep Learning (DL). In an attempt to reconcile the mixed results reported in this context, we present a systematic comparison of 6 hybrid approaches along with standard Machine Learning and DL approaches, on 4 corpora (different languages and target audiences). The various experiments clearly highlighted two rather simple hybridization methods (soft label and simple concatenation). They also appear to be the most robust on smaller datasets and across various tasks and languages. This study stands out as the first to systematically compare different architectures and approaches to feature hybridization in DL, as well as comparing performance in terms of two languages and two target audiences of the text, which leads to a clearer pattern of results.

Automated Essay Scoring (AES) aims to automatically assess the quality of essays. Automation enables large-scale assessment, improvements in consistency, reliability, and standardization. Those characteristics are of particular relevance in the context of language certification exams. However, a major bottleneck in the development of AES systems is the availability of corpora, which, unfortunately, are scarce, especially for languages other than English. In this paper, we aim to foster the development of AES for French by providing the TCFLE-8 corpus, a corpus of 6.5k essays collected in the context of the Test de Connaissance du Français (TCF - French Knowledge Test) certification exam. We report the strict quality procedure that led to the scoring of each essay by at least two raters according to the CEFR levels and to the creation of a balanced corpus. In addition, we describe how linguistic properties of the essays relate to the learners’ proficiency in TCFLE-8. We also advance the state-of-the-art performance for the AES task in French by experimenting with two strong baselines (i.e. RoBERTa and feature-based). Finally, we discuss the challenges of AES using TCFLE-8.

In this paper, we present the FABRA: readability toolkit based on the aggregation of a large number of readability predictor variables. The toolkit is implemented as a service-oriented architecture, which obviates the need for installation, and simplifies its integration into other projects. We also perform a set of experiments to show which features are most predictive on two different corpora, and how the use of aggregators improves performance over standard feature-based readability prediction. Our experiments show that, for the explored corpora, the most important predictors for native texts are measures of lexical diversity, dependency counts and text coherence, while the most important predictors for foreign texts are syntactic variables illustrating language development, as well as features linked to lexical sophistication. FABRA: have the potential to support new research on readability assessment for French.

Traditional approaches to set goals in second language (L2) vocabulary acquisition relied either on word lists that were obtained from large L1 corpora or on collective knowledge and experience of L2 experts, teachers, and examiners. Both approaches are known to offer some advantages, but also to have some limitations. In this paper, we try to combine both sources of information, namely the official reference level description for French language and the FLElex lexical database. Our aim is to train a statistical model on the French RLD that would be able to turn the distributional information from FLElex into one of the six levels of the Common European Framework of Reference for languages (CEFR). We show that such approach yields a gain of 29% in accuracy compared to the method currently used in the CEFRLex project. Besides, our experiments also offer deeper insights into the advantages and shortcomings of the two traditional sources of information (frequency vs. expert knowledge).