A4LL logo designed by Sidonie Tosser – Licence: CC-BY-NC 4.0
Why does my English teacher only ever underline the mistakes in my essays? Why does it take so long to correct my essay?
Description
The A4LL project will develop an innovative language-learning analytics system designed to assist teachers and learners with objective reports linking proficiency with linguistic features. Thomas Gaillat, the coordinator, proposes an approach relying on textual measures operationalising global and structure complexity, phraseology, discourse cohesion, and fluency. These measures will support the automatic creation of graphic reports used by teachers to diagnose their learners’ productions. A4LL’s ambition is to create the first fully automated L2 (Second language) analysis system serving learners, teachers, and researchers at university via an integrated data workflow from ingestion to analytics.
Research questions
The A4LL project will deliver an L2 analytics system for learners and teachers of English at university level. The project will address 3 main research questions aiming to uncover some of the features of Interlanguage, i.e the unstable linguistic system demonstrated by learners of a second language: i) what are the language features that are related to specific proficiency levels? ii) how can these features be measured automatically? iii) how can measures be converted into meaningful analytics for descriptive feedback and teaching decisions?
Interlanguage can be seen as a complex multifactorial system which makes the identification of criterial proficiency features difficult. Over time and practice, the system gradually stabilises. However, it is not clear which factors are at play at a given point. To cast a light on how interlanguage develops, current research shows that approaches combining linguistic measurements and statistics within computer models help to highlight some features of interlanguage (Ballier et al., 2020; Yannakoudakis et al., 2018). However, current state-of-the-art metrics lack linguistic meaningfulness and so impair interpretability.
Objective
The objective is to develop a computer system that automatically generates linguistic diagnostics of learner writings. These diagnostics will therefore be visualised by teachers through MOODLE, one of the main open-source LMS in France and in the world. These diagnostics will help teachers formulate advice for their students and adapt their teaching objectives in relation to their groups’ profiles. Developing the system will imply research work to identify correlations between linguistic features and metadata including task types, proficiency, learning habits and writing ability.
The system will collect, automatically analyse and provide specific linguistic feedback for writings submitted in MOODLE (see Figure 1). By exploiting lexical, syntactic and semantic metrics, the system will point out the dimensions that require attention in each writing. Graphical visualisations will show which linguistic areas to improve for a targeted proficiency level. The system will rely on a supervised learning approach with learner data collected in the two Language Centres (in charge of 20,000 students learning English for Specific Purposes) of the two universities of Rennes. It will be modular to allow subsequent integration of other languages.
A4LL intends to leverage the strength of two previously developed prototypes in which the coordinator participated. The first prototype, developed in 2019 (Gaillat, Simpkin, et al., 2021), provides automatic classification of learner writings according to the levels of the CEFR. The second prototype, called VizLing (Gaillat, Knefati, et al., 2021), and developed in 2019, focused on the automatic generation of graphs to visualize linguistic complexity in writings. A4LL will expand in the same avenue, but it will rely on a selection of significant and linguistically descriptive metrics for second language analysis. A4LL will unify the Natural Language Processing tasks under a single framework producing visualisations in MOODLE. It will rely on learner metadata in order to allow teachers to profile their learners and personalise feedback.
The purpose of A4LL is thus i) to offer the language teaching community data analytics tools that help position learners according to proficiency and aspects of their language. ii) to model learner language to map linguistic features with proficiency and, ultimately, interlanguage stages. A4LL intends to provide a solution for university language centres, in France and abroad, that are in charge of millions of students studying languages for professional purposes.
Partners
| Institution | Last Name | First Name | Role |
|---|---|---|---|
| Rennes 2 University | GAILLAT | Thomas | PI & Associate Professor |
| Rennes 2 university | MALLART | Cyriel | Research Engineer |
| Rennes 2 University | LI | Jen-Yu | Ph.D. candidate |
| Rennes 2 University | FAUGERE | Anatole | Research Assistant and Computer programmer |
| University of Paris Cité | BALLIER | Nicolas | Professor of Linguistics |
| University of Paris Cité |
LISSON | Paula | Research Engineer |
| University of Galway | SIMPKIN | Andrew | Associate professors in Statistics |
| University of Galway | STEARNS | Bernardo | Research Associate |
| Le Mans University | VENANT | Rémi | Associate Professor |
| IRISA / INSA Rennes | SÉBILLOT | Pascale | Professor of Computer Science |
| IRISA / CNRS | GRAVIER | Guillaume | Senior Research Scientist |
Partner project
Deep Learning for Language Assessment (DLLA)
Expert annotators
CEFR Annotation
| Institution | Expert | Role | Structure |
|---|---|---|---|
| Rennes 2 University | Joanne Ward-Henry | English teacher | Centre de Langues Rennes 2 |
| Rennes 2 University | Francoise Le Roux | English teacher | Centre de Langues Rennes 2 |
| University of Rennes | Benedicte Dumont | English teacher | SCELVA, Univ de Rennes |
| University of Rennes | Pascale Janvier | English teacher | SCELVA, Univ de Rennes |
Linguistic Annotation
- Team members: Paula, Nicolas and Thomas
- Université Paris Cité - CLILLAC-ARP: Jessica Tayeh
Conferences & publications
2025
Conference papers
- titre
- Actionability in CALL: linking proficiency prediction models to interpretable indicators
- auteur
- Thomas Gaillat, Cyrielle Mallart, Andrew Simpkin, Rémi Venant, Nicolas Ballier, Bernardo Stearns, Jen-Yu Li, Paula Lissón
- article
- International Workshop on Foreign language learning and proficiency-rated reading materials: SLA research and AI methods supporting analysis and effective didactics in real-life education, Universität Tübingen, Mar 2025, Tübingen, Allemagne, Germany
- Accès au bibtex
-
- titre
- L'usage des collocations en anglais d'apprenants : une analyse croisée des L1 et des niveaux de compétence
- auteur
- Jen-Yu Li
- article
- Approches interdisciplinaires des unités phraséologiques (UP) dans les langues du monde : Linguistique - TAL & IA - Traduction - Littérature, Mar 2025, Paris, France
- Accès au bibtex
-
Other publications
- titre
- Annotated English Verb Noun collocation dataset
- auteur
- Jen-Yu Li
- article
- 2025
- Accès au bibtex
-
- titre
- CELVA.Sp processed with A4LL metrics pipeline
- auteur
- Thomas Gaillat, Cyriel Mallart, Andrew J. Simpkin
- article
- 2025, ⟨10.34847/nkl.3aba968r⟩
- Accès au bibtex
-
Reports
- titre
- Analytics for Language Learning Data Management Plan
- auteur
- Thomas Gaillat, Nicolas Ballier, Cyrielle Mallart
- article
- Opidor. 2025, https://dmp.opidor.fr/plans/13498
- Accès au bibtex
-
Preprints, Working Papers, ...
- titre
- Assessing the validity of new paradigmatic complexity measures as criterial features for proficiency in L2 writings in English
- auteur
- Cyriel Mallart, Andrew Simpkin, Nicolas Ballier, Paula Lissón, Rémi Venant, Jen-Yu Li, Bernardo Stearns, Thomas Gaillat
- article
- 2025
- Accès au texte intégral et bibtex
-
2024
Conference papers
- titre
- La linguistique de corpus à l'heure du code ouvert
- auteur
- Cyrielle Mallart, Thomas Gaillat, Rémi Venant, Nicolas Ballier, Jen-Yu Li, Bernardo Stearns
- article
- Deuxième journée d'étude ARDoISE, INRIA, Dec 2024, Rennes, France
- Accès au bibtex
-
- titre
- Evaluating the Generalisation of an Artificial Learner
- auteur
- Bernardo Stearns, Nicolas Ballier, Thomas Gaillat, Andrew J. Simpkin, John P. Mc Crae
- article
- NLP4CALL2024 : Natural Language Processing for Computer-assisted Language Learning, Université Rennes 2, France; University of Gothenburg, Sweden; Linköping University, Sweden, Oct 2024, Rennes, France
- Accès au texte intégral et bibtex
-
- titre
- Overview of the linguistic features: creating measures – Joint presentation
- auteur
- Nicolas Ballier, Bernardo Stearns, Jen-Yu Li
- article
- pre-conference workshop to NLP4CALL 2024, Oct 2024, Rennes, France
- Accès au bibtex
-
- titre
- Exploring learner knowledge with Large Language Models fine-tuned with the EFCAMDAT
- auteur
- Nicolas Ballier, Bernardo Stearns
- article
- LCR2024 Learner Corpus Research conference, University of Tartu; Learner Corpus Association, Sep 2024, Tartu (Estonie), Estonia
- Accès au texte intégral et bibtex
-
- titre
- Assessing the validity of new structural complexity measures as features of proficiency in L2 English
- auteur
- Thomas Gaillat, Cyriel Mallart, Nicolas Ballier, Andrew Simpkin, Rémi Venant, Bernardo Stearns, Paula Lissón, Jen-Yu Li
- article
- Learner Corpus Research Conference, University of Tartu, Sep 2024, Tartu (Estonie), Estonia
- Accès au bibtex
-
- titre
- Linguistic interoperability within a unified architecture
- auteur
- Thomas Gaillat, Cyrielle Mallart, Andrew J. Simpkin, Rémi Venant, Nicolas Ballier, Jen-Yu Li, Bernardo Stearns
- article
- Langues & Langage à la croisée des Disciplines - 1ère Rencontre annuelle LLcD, Sorbonne Université; cnrs, Sep 2024, Paris, France
- Accès au texte intégral et bibtex
-
- titre
- Analytics for Language Learning. Linguistic interoperability within a unified architecture
- auteur
- Cyriel Mallart, Andrew Simpkin, Rémi Venant, Nicolas Ballier, Bernardo Stearns, Jen-Yu Li, Thomas Gaillat
- article
- Langues & Langage à la croisée des Disciplines 1ère Rencontre annuelle LLcD, Sep 2024, Paris, France
- Accès au bibtex
-
Other publications
- titre
- Understanding Large Language Models
- auteur
- Cyriel Mallart
- article
- 2024
- Accès au bibtex
-
- titre
- Dictionary of Bigram-Score extracted from BNC with all association meausres by NLTK
- auteur
- Jen-Yu Li
- article
- 2024
- Accès au bibtex
-
Proceedings
- titre
- Proceedings of the 13th Workshop on Natural Language Processing for Computer Assisted Language Learning
- auteur
- Thomas Gaillat, Cyriel Mallart, Fabienne Moreau, Griselda Drouet, Jen-Yu Li, David Alfter, Elena Volodina, Arne Jönsson
- article
- The 13th Workshop on Natural Language Processing for Computer Assisted Language Learning, Oct 2024, Rennes, France. LiU Electronic Press, 2024, Linköping electronic conference proceedings
- Accès au texte intégral et bibtex
-
2023
Scientific blog post
- titre
- CELVA.sp: A new learner language data set for the study of English for Specific Purposes at university level
- auteur
- Thomas Gaillat, Cyrielle Mallart, Rémi Venant, Nicolas Ballier, Jen-Yu Li, Bernardo Stearns, Andrew Simpkin
- article
- 2023
- Accès au bibtex
-
Conference papers
- titre
- L'interopérabilité des corpus pour la modélisation des dynamiques d'acquisition de langue seconde
- auteur
- Thomas Gaillat, Cyrielle Mallart, Nicolas Ballier, Andrew Simpkin, Rémi Venant, Anatole Faugère, Bernardo Stearns, Jen-Yu Li, Paula Lissón
- article
- Journée d'étude : « Corpus d’apprenants / corpus d’experts : Quels enseignements pour la caractérisation du discours scientifique ? », UR 3967 - CLILLAC-ARP : Centre de Linguistique Inter-langues, de Lexicologie, de Linguistique Anglaise et de Corpus - Atelier de Recherche sur la Parole; UFR EILA - Etudes Interculturelles de Langues Appliquées, Faculté Sociétés et Humanités d’Université Paris Cité, Dec 2023, Paris, France
- Accès au bibtex
-
- titre
- Analytics for Language Learning: Interfacing MOODLE with A4LL via LTI
- auteur
- Thomas Gaillat, Cyrielle Mallart, Nicolas Ballier, Andrew Simpkin, Rémi Venant, Bernardo Stearns, Jen-Yu Li, Paula Lissón, Anatole Faugère
- article
- Deep learning for language assessment closing event (DLLA Closing event 2023), UR 3967 - CLILLAC-ARP : Centre de Linguistique Inter-langues, de Lexicologie, de Linguistique Anglaise et de Corpus-Atelier de Recherche sur la Parole; UFR EILA de l’Université Paris Cité, Nov 2023, Paris, France
- Accès au bibtex
-
- titre
- Exploring a New Grammatico-functional Type of Measure as Part of a Language Learning Expert System
- auteur
- Cyriel Mallart, Andrew Simpkin, Rémi Venant, Nicolas Ballier, Bernardo Stearns, Jen-Yu Li, Thomas Gaillat
- article
- Proceedings of the 18th Workshop on Innovative Use of NLP for Building Educational Applications (BEA 2023), Jul 2023, Toronto, Canada. pp.466-476, ⟨10.18653/v1/2023.bea-1.39⟩
- Accès au texte intégral et bibtex
-
- titre
- Analytics for Language Learning : Transmettre aux enseignants les profils linguistiques de leurs apprenants
- auteur
- Thomas Gaillat, Cyrielle Mallart, Anatole Faugère, Andrew Simpkin, Bernardo Stearns, Paula Lissón, Jen-Yu Li, Nicolas Ballier, Rémi Venant
- article
- Atelier GERAS @ 62e Congrès annuel de la SAES 2023, Université Rennes 2; SAES La Sorbonne Nouvelle; GERAS (Groupe d'Etude et de Recherche en Anglais de Spécialité), Jun 2023, Rennes, France
- Accès au bibtex
-
- titre
- Grammatical profiling with UD annotation (WiP)
- auteur
- Nicolas Ballier, Cyrielle Mallart, Thomas Gaillat
- article
- Workshop on Profiling second language vocabulary and grammar, University of Gothenburg, Humanisten., Apr 2023, Gothenburg, Sweden
- Accès au bibtex
-
Poster communications
- titre
- Exploring Verb-Noun collocations in learner English
- auteur
- Jen-Yu Li, Cyriel Mallart, Thomas Gaillat, Elisabeth Richard
- article
- Deep learning for language assessment (DLLA) closing event, Nov 2023, Paris, France
- Accès au texte intégral et bibtex
-
- titre
- Vers une grammaire probabiliste de microsystèmes fonctionnels en L2
- auteur
- Cyrielle Mallart, Andrew Simpkin, Rémi Venant, Nicolas Ballier, Bernardo Stearns, Jen-Yu Li, Thomas Gaillat
- article
- RéAL2: Grammaire(s) et acquisition des L2: Approches, trajectoires, interfaces,, Oct 2023, Grenoble, France
- Accès au texte intégral et bibtex
-
2022
Conference papers
- titre
- Language learning analytics : designing and testing new functional complexity measures in L2 writings
- auteur
- Thomas Gaillat
- article
- 11th Workshop on Natural Language Processing for Computer-Assisted Language Learning (NLP4CALL 2022), Dec 2022, Louvain la Neuve, Belgium. pp.55-60, ⟨10.3384/ecp190006⟩
- Accès au texte intégral et bibtex
-
2018
Software
- titre
- CELVA.Sp corpus User Interface
- auteur
- Thomas Gaillat, Rémi Venant, Cyriel Mallart, Taylor Arnold, Anatole Fougère
- article
- 2018, ⟨swh:1:dir:7405005eae86eb3f53662e5649f10f5c4f92e11a;origin=https://gitlab.huma-num.fr/lidile/celva.sp-ui;visit=swh:1:snp:198c7b3333fa18b5a721d36e06e8a5a0648600e3;anchor=swh:1:rev:95c370947852a8fe6ef9254069ca7812fd901188⟩
- Accès au bibtex
-
Deliverables
Software
- A Tool for learner corpus collection: The CELVA.SP User Interface for MOODLE
- The Google Colab for the Workshop « Enrichissement linguistique des données textuelles« , an Introduction to Python for Humanities Experts.
Supported by Rennes Métropole & ANR
Datasets & corpora
Learner corpus of language for Specific Purposes Three datasets on Nakala:
- One with Dialang CEFR annotation
- Two batches with human expert CEFR annotation: 2018-2022 and 2023-2024
