PEOPLELionel Nicolas

de en it

Lionel Nicolas

Senior Researcher
Institute for Applied Linguistics

T +39 0471 055 123

lionel.nicolas@eurac.edu

download or scan my contact information (vCard Format)

About

The performances of most Natural Language Processing (NLP) tools depend directly or indirectly on the quality of the linguistic resources they rely on. My research focuses on the automatized creation and extension of linguistic resources, especially through the combination of language learning and crowdsourcing. I'm also interested in the automatic processing and use of learner corpora, computer-assisted language learning and many other things.

For more information see:

ORCID, https://orcid.org/0000-0002-7703-9953
Google scholar, https://scholar.google.fr/citations?user=iNuwVa0AAAAJ
Research gate, https://www.researchgate.net/profile/Lionel-Nicolas
CV, https://tinyurl.com/lnicolas-cv

Scientific Publications

Report2025

An overview of Grammatical Error Correction for the twelve MultiGEC-2025 languages

Masciolini A, Caines A, De Clercq O, Kruijsbergen J, Kurfalı M, Muñoz Sánchez R, Volodina E, Östling R,

Lionel Nicolas, Jennifer-Carmen Frey

ISBN: 1401-5919

This overview is complementary to the comprehensive dataset description article for MultiGEC – a dataset for Multilingual Grammatical Error Correction including data for twelve European languages: Czech, English, Estonian, German, Greek, Icelandic, Italian, Latvian, Russian, Slovene, Swedish and Ukrainian. It is well-known that in the field of Natural Language Processing (NLP) most publications tend to focus on the English language. While this is due to historical reasons (ease of publication, greater outreach, increased number of citations, etc.), it does leave other languages at a disadvantage across multiple tasks. The MultiGEC dataset was created as an attempt to counteract this effect. This report provides a historical overview of the evolution of GEC for each of the twelve languages in this dataset and provides a context for the work on the dataset and the related MultiGEC-2025 shared task.

Fonte

Conference proceedings article2025

Towards a new Curation Workflow for the CMC Corpora Resource Family

Stemle EW, Nicolas L, König A

Egon W. Stemle, Lionel Nicolas

Progetto: l'Infrastruttura Comune delle Risorse e delle Tecnologie Linguistiche per l’Italia presso Eurac Research

This paper aims at raising awareness regarding a recently started and ongoing effort of CLARIN ERIC and the CLARIN Knowledge Centre for CMC and Social Media Corpora (CKCMC) to enhance the visibility and accessibility of the CMC community’s datasets through the CLARIN CMC Corpora Resource Family (CMC-RF), which, as of May 2025, the CKCMC officially adopted, that is, it took over responsibility. We offer some possible scenarios regarding how curation (addition, change and deletion of entries) of the CMC-RF could be approached, with the objective to prepare a productive context for a roundtable at the forthcoming 2025 edition of the CMC-Corpora conference. We intend to use the outcomes of this roundtable to devise a grounded and informed first version of Curation Guidelines for the CMC-RF, together with a community-oriented procedure to update it.

DOI Fonte

DOI: 10.15495/EPub_UBT_00008705

Journal article2023

The Kolipsi Corpus Family: Resources for Learner Corpus Research in Italian and German

Glaznieks A, Frey JC, Abel A, Nicolas L, Vettori C

Aivars Glaznieks, Chiara Vettori, Andrea Abel, Lionel Nicolas, Jennifer-Carmen Frey

Progetto: KOLIPSI II: Gli studenti altoatesini e la seconda lingua: indagine linguistica e psicosociale, Infrastruttura per Corpora di Testi di Apprendenti

This article describes the Kolipsi Corpus Family (KCF), a collection of eight related resources for learner corpus research in German and Italian. The KCF supports the study of second language (L2) acquisition of Italian and German in upper secondary schools. It subsumes four L2 corpora with comparable corpus design (with respect to data collection, writing tasks, additional metadata, annotation and processing), portraying two homogeneous learner groups and their learner varieties. The corpora are representative of language learners in the multilingual Italian province of South Tyrol, where both languages are taught daily. The L2 corpora were collected at two different points in time, in 2007 (Kolipsi-1) and 2014 (Kolipsi-2), and all texts were labeled with CEFR levels to allow comparisons of proficiency levels across time. L2 German texts were collected in schools with Italian as the main language of instruction, whereas L2 Italian texts were collected in schools with German as the main language of instruction. Additional resources within the KCF allow researchers to compare the students’ language competences in their L2 with the language competences in their first language (L1) in a different task (Kolipsi-Matura) and with similarly aged L1 writers performing the same task (Kolipsi-1-L1). All texts are freely available to the scientific community. Access to the data is granted via an ANNIS search interface and via the Eurac Research CLARIN Repository, from which corpus data can be downloaded in various formats.

DOI Fonte

DOI: 10.4000/ijcol.1210

journalIssue2022

Crowdsourcing for language learning and linguistic resource creation

Nicolas L, Lyding V

Lionel Nicolas

The current special issue of the journal Slovenščina 2.0 focuses on the newly explored combination of crowdsourcing, language learning and linguistic resource creation. It contains five articles and one project report, providing insightful discussions on several aspects of this combination, as well as results which help us understand its versatile potential and the challenges to address in order to better exploit it.

DOI Fonte

DOI: 10.4312/slo2.0.2022.2

Journal article2022

EnetCollect, European Network for Combining Language Learning with Crowdsourcing Techniques (COST Action CA16105): A review of the project’s vision, organization, progress, and achievements

Nicolas L, Lyding V

Lionel Nicolas

This article reviews the European Network for Combining Language Learning with Crowdsourcing Techniques (enetCollect), an extensive network project created to foster research and innovation (R&I) on the combination of crowdsourcing and language learning. Accordingly, we explain how it began, introduce its overall logic and organization, and discuss its achievements in terms of both (1) creating a new R&I community through a concluded large network project, and (2) fostering R&I on a high-potential and mostly unexplored subject.

We also discuss the challenges involved and lessons learned, whether in orchestrating and leading a new R&I community or the challenges we faced and generally observed in the efforts of enetCollect members, as they explored the many facets of such a versatile enterprise.

DOI Fonte

DOI: 10.4312/slo2.0.2022.2.202-225

Journal article2022

Leonide: A longitudinal trilingual corpus of young learners of Italian, German and English

Glaznieks A, Frey JC, Stopfner M, Zanasi L, Nicolas L

Aivars Glaznieks, Maria Stopfner, Lorenzo Zanasi, Lionel Nicolas, Jennifer-Carmen Frey

Progetto: A lezione con più lingue, Infrastruttura per Corpora di Testi di Apprendenti, A lezione con più lingue 2.0

This article presents the longitudinal trilingual corpus of young learners of Italian, German and English called LEONIDE. The corpus consists of L1, L2 and L3 learner texts. L1 texts were written in two languages of schooling (i.e. Italian and German), L2 texts in two languages learned as second languages (i.e. German and Italian), and L3 texts in an additional foreign language (i.e. English). All texts were collected from a group of lower secondary school pupils from the multilingual Italian province of South Tyrol whose development in all three languages was observed over a period of three years. Each text comes with rich metadata as well as manual and automatic annotations.

DOI Fonte

DOI: 10.1075/ijlcr.21004.gla

Inbook2021

Introducing an implicit crowdsourcing opportunity to teachers

Nicolas L, Ostanina-Olszewska J, Arhar Holdt Š, Borg, C, Čibej J, Lyding V, Barreiro A

Lionel Nicolas

Progetto: Rete Europea per la Combinazione dell'Apprendimento delle Lingue con le Tecniche di Crowdsourcing

This paper aims at attracting attention towards crowdsourcing opportunities for the language teaching community. It presents and discusses a specific crowdsourcing paradigm designed to mass-produce exercise content for different languages by involving their language learners online. The discussion of the implicit crowdsourcing paradigm is framed by a broader look at the current situation regarding crowdsourcing and language learning. Therefore, we first introduce the concept of crowdsourcing, report on the teacher perspective and discuss common objections and practical challenges with regard to the compatibility of the language learning community with crowdsourcing in terms of expertise, motivation and feasibility. The implicit crowdsourcing paradigm we introduce proposes an approach for automatically generating language learning resources and, at the same time, crowdsourcing language-related datasets. It is designed to exploit a synergy between the language learning community and R&I partners working in language-related areas. The proposed approach is one of multiple experimental initiatives, which are being studied and explored within the enetCollect COST Action (European Network for Combining Language Learning with Crowdsourcing Techniques). We conclude the paper with a discussion on our efforts to raise awareness among the varied stakeholders so as to foster the creation of tools implementing the crowdsourcing paradigm.

DOI Fonte

DOI: 10.3726/b18131

Conference proceedings article2020

Substituto - A Synchronous Educational Language Game for Simultaneous Teaching and Crowdsourcing

Araneta MG, Eryigit G, König A, Lee Ji-Ung, Luís AR, Lyding V, Nicolas L, Rodosthenous C,

Lionel Nicolas

Progetto: Rete Europea per la Combinazione dell'Apprendimento delle Lingue con le Tecniche di Crowdsourcing

This paper investigates a general framework for synchronous educational language games that simultaneously allows researchers to crowdsource learner answers in a controlled environment. Our prototype Substituto allows teachers and students to interact in real-time while undergoing language learning exercises; ensuring that the learner's progress is not hurt by the introduction of crowdsourc-ing elements. We evaluate Substituto with a small-scale user study that focuses on training the use of English verb-particle constructions (VPCs), such as break down or take over, and test their use with second language learners of English of different proficiency levels over five pilot sessions. With the study we aim to ensure that our prototypical implementation behaves as expected and to identify any major design flaws that should be addressed. The preliminary results we achieved in order to evaluate the educational value, the user experience and the crowdsourcing capacity of Substituto confirm that it has the potential to become a valuable asset for language learning, a pleasant learning instrument and a crowdsourcing tool for collecting linguistic knowledge.

DOI Fonte

DOI: 10.3384/ecp201759

Edited book2019

Widening the Scope of Learner Corpus Research: Selected Papers from the Fourth Learner Corpus Research Conference

Abel A, Glaznieks A, Lyding V, Nicolas L

Andrea Abel, Aivars Glaznieks, Lionel Nicolas

ISBN: 978-2-87558-868-5

Since its beginnings in the late 1980s, the field of Learner Corpus Research (LCR) has been continuously evolving and thereby widening its scope. LCR is rapidly closing gaps within its original scope by expanding on the languages, language mediums (spoken vs written) and learner types covered, and it is turning its attention to ever-emerging new research questions and phenomena which arise at the crossroads with neighboring disciplines. In fact, by embracing e.g. the latest technical developments in Natural Language Processing and Computer Science as well as by adopting state-of-the-art research methodologies used in Corpus Linguistics which include sophisticated statistical methods of data analysis, LCR is dipping into new interdisciplinary subjects with curiosity and expanding its research scope and methodological repertoire.

This volume combines selected research papers from the 4^th LCR conference hosted by Eurac Research in Bolzano/Bozen (Italy) in October 2017. All contributions in this volume build on the topics of previous LCR conference volumes, and enrich them with their research. The contributions are arranged thematically and refer to the following five LCR topics: (1) analysis of learner data in spoken language, (2) analysis of learner data in corpora of other languages than English, (3) analysis of learner data of younger learners, (4) LCR, language learning and pedagogical applications, and (5) LCR and automatic language modelling. The assembled papers introduce innovative research strands, present original data and research findings, and discuss latest desiderata within the five thematic focal points of the book.

Journal article2018

enetCollect: A New European Network for combining Language Learning with Crowdsourcing Techniques

Agerri R, Maritxalar M, Lyding V, Nicolas L

Lionel Nicolas

Progetto: Rete Europea per la Combinazione dell'Apprendimento delle Lingue con le Tecniche di Crowdsourcing

We present enetCollect, a large European COST action network set upwith the aim of promoting a research trend combining the well-established domain of Language Learning with recent and successful crowdsourcing approaches. More specifically, the challenge of enetCollect is to foster the language skills of all citizens regardless of their backgrounds by enhancing the production of language learning material using Crowdsourcing techniques. In order to do so, the action will create a balanced interdisciplinary community of active stakeholders related to content- creation, content-usage, and Learning/Content Management Systems to create a theoretical framework for achieving a shared understanding of Language Learning and Crowdsourcing. This will allow to unlock the crowdsourcing potential available for language learning and to facilitate the development of prototypical experiments for the production of language learning material, such as lesson or exercise content. These activities would potentially benefit a wide range of users and languages.

DOI Fonte

DOI: 10.26342/2018-61-25

Inbook2018

Introducing the European NETwork for COmbining Language LEarning and Crowdsourcing Techniques (enetCollect)

Lyding V, Nicolas L, Bédi B, Fort K

Lionel Nicolas

Progetto: Rete Europea per la Combinazione dell'Apprendimento delle Lingue con le Tecniche di Crowdsourcing

We present enetCollect, a large European network project funded as a COST Action that sets ground for combining crowdsourcing with IT technologies used in areas such as language learning and Natural Language Processing (NLP). This project tackles a major challenge of bringing together interdisciplinary researchers to foster language learning of all European citizens from diverse socio-demographic, cultural, educational, and linguistic backgrounds. It aims at unlocking a crowdsourcing potential available for all languages, including less widely spoken languages, in order to create language resources and achieve a coverage of material for teaching the languages. It will meet its research and capacity-building goals by creating an international community of researchers that will work on producing a comprehensive theoretical framework and running prototypical experiments to benefit a wide range of users and languages, while considering ethical, legal, and business issues. This article informs about its objectives, expected impact and strategic organisation that contribute to reaching its flexible and sustainable success goals.

DOI Fonte

DOI: 10.14705/rpnet.2018.26.833

Inbook2015

A Generic Data Workflow for Building Annotated Text Corpora

Nicolas L, Stemle EW, Glaznieks A, Abel A

Andrea Abel, Egon W. Stemle, Aivars Glaznieks, Lionel Nicolas

We present an abstract and generic workflow, and detail how it has been implemented to build and annotate learner corpora. This workflow has been developed through an interdisciplinary collaboration between linguists, who annotate and use corpora, and computational linguists and computer scientists, who are responsible for providing technical support and adaptation or implementation of software components.

DOI

DOI: 10.3726/978-3-0351-0736-4

Journal article2023

The Kolipsi Corpus Family: Resources for Learner Corpus Research in Italian and German

Glaznieks A, Frey JC, Abel A, Nicolas L, Vettori C

Aivars Glaznieks, Chiara Vettori, Andrea Abel, Lionel Nicolas, Jennifer-Carmen Frey

Progetto: KOLIPSI II: Gli studenti altoatesini e la seconda lingua: indagine linguistica e psicosociale, Infrastruttura per Corpora di Testi di Apprendenti

DOI Fonte

DOI: 10.4000/ijcol.1210

Service	Disattivo/Attivo	Terms Link
Youtube		https://support.google.com/youtube/answer/7671399?...
Vimeo		https://vimeo.com/terms
Flourish		https://flourish.studio/terms/
Datawrapper		https://www.datawrapper.de/terms
Power BI		https://www.microsoft.com/en/servicesagreement/
Facebook		https://www.facebook.com/policies/cookies/
Instagram		https://help.instagram.com/1896641480634370?ref=ig
X		https://help.twitter.com/en/rules-and-policies/twi...
Google Maps		https://maps.google.com/help/terms_maps/
LinkedIn		https://www.linkedin.com/legal/cookie-policy

Lionel Nicolas

About

Scientific Publications

An overview of Grammatical Error Correction for the twelve MultiGEC-2025 languages

Towards a new Curation Workflow for the CMC Corpora Resource Family

The Kolipsi Corpus Family: Resources for Learner Corpus Research in Italian and German

Crowdsourcing for language learning and linguistic resource creation

EnetCollect, European Network for Combining Language Learning with Crowdsourcing Techniques (COST Action CA16105): A review of the project’s vision, organization, progress, and achievements

Leonide: A longitudinal trilingual corpus of young learners of Italian, German and English

Introducing an implicit crowdsourcing opportunity to teachers

Substituto - A Synchronous Educational Language Game for Simultaneous Teaching and Crowdsourcing

Widening the Scope of Learner Corpus Research: Selected Papers from the Fourth Learner Corpus Research Conference

enetCollect: A New European Network for combining Language Learning with Crowdsourcing Techniques

Introducing the European NETwork for COmbining Language LEarning and Crowdsourcing Techniques (enetCollect)

A Generic Data Workflow for Building Annotated Text Corpora

Science Shots Eurac Research Newsletter

Cosa facciamo

Dove siamo

Istituti & Center

Seguici

Preferenze Cookie

Contenuti esterni

Scientific Publications

An overview of Grammatical Error Correction for the twelve MultiGEC-2025 languages

Towards a new Curation Workflow for the CMC Corpora Resource Family

The Kolipsi Corpus Family: Resources for Learner Corpus Research in Italian and German

Crowdsourcing for language learning and linguistic resource creation

EnetCollect, European Network for Combining Language Learning with Crowdsourcing Techniques (COST Action CA16105): A review of the project’s vision, organization, progress, and achievements

Leonide: A longitudinal trilingual corpus of young learners of Italian, German and English

Introducing an implicit crowdsourcing opportunity to teachers

Substituto - A Synchronous Educational Language Game for Simultaneous Teaching and Crowdsourcing

Widening the Scope of Learner Corpus Research: Selected Papers from the Fourth Learner Corpus Research Conference

enetCollect: A New European Network for combining Language Learning with Crowdsourcing Techniques

Introducing the European NETwork for COmbining Language LEarning and Crowdsourcing Techniques (enetCollect)

A Generic Data Workflow for Building Annotated Text Corpora

Technical
Questi cookie sono necessari per il funzionamento del sito e non possono essere disattivati.