Thomas François’s research while affiliated with Catholic University of Louvain and other places

The current paper addresses the need for language students and teachers to have access to a large number of pedagogically sound contexts for vocabulary acquisition and testing. We investigate the automatic derivation of contexts for a vocabulary list of English for Specific Purposes (ESP). The contexts are generated by contemporary Large Language Models (namely, Mistral-7B-Instruct and Gemini 1.0 Pro) in zero-shot and few-shot settings, or retrieved from a web-crawled repository of domain-relevant websites. The resulting contexts are compared to a professionally crafted reference corpus based on their textual characteristics (length, morphosyntactic, lexico-semantic, and discourse-related). In addition, we annotated the automatically derived contexts regarding their direct applicability, comprehensibility, and domain relevance. The 'Gemini, zero-shot' contexts are rated most highly by human annotators in terms of pedagogical usability, while the 'Mistral, few-shot' contexts are globally closest to the reference based on textual characteristics.

Innovative resources for teaching vocabulary have emerged during the last decades, among which the so-called ‘graded resources’, i.e. lexicons or inventories where linguistic forms have been associated with a difficulty level, having in mind a target reader. The idea of ‘grading’ in Education is not new and has evolved over time: vocabulary or text scales (grades) have been approached as an educational tool with the means available at each period of time. In this survey, our aim is to show how current approaches of graded resources for foreign language learning are rooted in the tradition of building frequency lists for education. We then synthesize the body of work that has been undertaken to design graduated resources, highlighting the different methodologies applied as well as existing resources.

MWE knowledge is key in the process of learning a foreign language, but its teaching remains hindered by the lack of list of expressions connected to pedagogical aims. In this paper, we present an extended version of the PolylexFLE database, containing 4,525 French multiword expressions (MWE) of three types: idioms, collocations or fixed expressions. In order to propose exercises following the difficulty scale of the European Framework of Reference for Languages (CEFR), we used a mixed approach (manual and automatic) to annotate 1,186 expressions according to the CEFR levels. The paper focuses mostly on the automatic procedure that first identifies the expressions from the PolylexFLE database (and their variants) in a corpus of pedagogical texts (with CEFR labels) using a pattern-based system. In a second step, their distribution in this corpus is estimated and transformed into a single CEFR level. The automatic approach proposed is finally evaluated by 52 French as foreign language learners.

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.

Morphological inflection is known to be difficult to master for L2 learners. In this paper, we examine the state of the use of inflection in the verbal tense system among learners of French, and contrast it with the use in FFL textbooks. The objectives of our study are threefold: 1) To establish the distribution of verbal tenses on French textbooks in an automatic way, in order to obtain the first fully empirical and extensive resource on French verbal tenses; 2) To objectively describe the use of verbal tenses by learners of different CEFR levels; 3) To identify the tenses that learners struggle with. Through the description of the use of the tenses in the learners, we found that they had difficulty with the past perfect indicative, even at advanced levels. The proposed Verb Profile summarizes which tenses should be understood at which level, and as such can guide teachers and learners, as well as help pinpoint tenses that learners are underperforming on.

Ever since the publication of Laviosa’s (1998a; 1998b) pioneering work, the study of lexico-syntactic simplification has held centre stage in corpus translation research concerned with the typical features of translated texts. The simplification hypothesis states that translated texts are simpler than non-translated texts. The convergence hypothesis, also discussed by Laviosa (1998a; 1998b), but less so in follow-up studies, is that translated texts are more homogeneous than original texts, that is they display less variance. To date, simplification has mostly been operationalised in CBTS as type-token ratio, lexical density, core vocabulary coverage, list head coverage and average sentence length. Relying on these parameters, previous research has produced mixed results, with simplification varying across translation modalities, language pairs and registers. The present article sets out to revisit the simplification and convergence hypotheses through the lens of NLP-informed readability research. In particular, we rely on a larger set of simplification indicators and make use of multivariate statistical techniques. We present a simplification study of Europarl corpus data in French translated from English and in non-translated French. The results show that translated French is simpler than original French, lexically and syntactically. We also find evidence of convergence that shows that translators smooth out cross-speaker lexical heterogeneity in translated parliamentary proceedings.

Communication between physician and patients can lead to misunderstandings, especially for disabled people. An automatic system that translates natural language into a pictographic language is one of the solutions that could help to overcome this issue. In this preliminary study, we present the French version of a translation system using the Arasaac pictographs and we investigate the strategies used by speech therapists to translate into pictographs. We also evaluate the medical coverage of this tool for translating physician questions and patient instructions.