The TAL Journal, special issue on “NLP for learning and teaching”

Topic: NLP for learning and teaching

Foreign Language Learning and Teaching is one of the fields where the introduction of information and communication technologies (ICT) has proved particularly fruitful. It is thus no wonder that Computer-Assisted Language Learning (CALL) has been among the first, from the 1960’s, to integrate insights and techniques from Natural Language Processing (NLP) to create intelligent computer-assisted learning environments. Since then, various other fields and disciplines have also incorporated NLP into electronic learning environments to support self-directed learning, blended learning or classroom teaching. NLP has overall contributed to the improvement of learning environments, and to the development of research in the related fields. It has allowed for the improvement of integrated systems, not to say the widening of issues in the related fields.

Today, online learning tools, Massive Open Online Courses (MOOCs), Small Private Online Courses, Computer-Assisted Pronunciation Teaching (CAPT) systems, Computer-Assisted Instruction systems for mathematics, sign language learning applications, or Intelligent Tutoring Systems (ITS), among many others, are heavy “consumers” of NLP, or about to become it.

Integrating NLP into these systems enables to consider, process and reproduce for learning purposes aspects of the content of linguistic data, to create more advanced educational resources, but also to make the communication with the learner more relevant in a teaching context.

The aspects of NLP most frequently involved are analysis of learners’ responses, feedback provision, automated generation of exercises, and the monitoring of learning progress. Other aspects related to learning and teaching also involve NLP, such as plagiarism detection, writing support, use of learner corpora or parallel corpora to detect and resolve errors, or adaptive learning systems integrating ontologies for the associated domains.

The contribution of NLP to these systems is generally regarded as positive. It must be recognized, however, that only a handful of such applications have made it to the general public as a commercial software. In most cases, the systems never left the laboratory and have a limited range of use, sometimes only as a proof of concept. Is this due, as many believe, to the high production cost of NLP resources? Is it because of the current quality of NLP results? Is it a consequence of the integration strategy of NLP into these applications?

The goal of this issue of Traitement Automatique des Langues dedicated to “NLP for learning and teaching” is to summarize the contribution of NLP to instructional systems, both at a theoretical level (opportunities, limitations, integration methods) and at the level of learning systems – or parts of systems – production.

Authors are invited to submit papers on all the aspects of the implementation of NLP into Computer-Assisted Instruction (CAI) systems for a given discipline, as well as useful tools for this task, in particular regarding, but not limited to, the following issues and tasks:

·        Contribution of (written or spoken) NLP to CAI systems.

·        Needs and requirements of NLP techniques and methods for instructional systems design.

·        Instructional design methodology for NLP-based CAI systems.

·        Presentation of systems and learning tools involving NLP.

·        Collection and use of language corpora for pedagogical purposes using NLP.

·        Use of learner corpora and error annotation using NLP.

·        Automated evaluation of learner writing and short answers using NLP.

·        (Semi-)automated diagnostic assessment and remedial help.

·        Design and setting up of activities involving NLP.

·        Language resources for NLP-based instruction and learning.

·        Automated selection of text resources based on pedagogical criteria.

·        Development, presentation and use of linguistic and metalinguistic information for pedagogical purposes.

·        Learner modelling based on his linguistic output.

·        Approaches and methods for plagiarism detection.

Position papers and state of the art papers are also welcome.


Papers can be written in French or in English. Submissions in English will only be accepted if at least one of the authors is not a native speaker of French.

Submission guidelines

Submitted papers should be 20 to 25 pages long. Any dispensation regarding length should be previously discussed with the guest editors.

Authors are invited to submit their paper as a PDF file on , by clicking on “Soumission d’un article”, after having previously registered and logged in on

The TAL Journal follows a double-blind peer-reviewing process. All submissions must be carefully anonymized.

Stylesheets are available online on the journal website: .

Important dates

·        Paper submission deadline: 28 October, 2016

·        Notification to the authors after first review: 17 February, 2017

·        Notification to the authors after second review: 28 April, 2017

·        Publication: September 2017


Traitement Automatique des Langues is an international journal published since 1960 by ATALA (Association pour le traitement automatique des langues) with the support of CNRS. It is now published online, with an immediate open access to published papers, and annual print on demand. This does not change its editorial and reviewing process.

Guest editors

·        Georges Antoniadis, Université Grenoble-Alpes, LIDILEM, France

·        Piet Desmet, KU Leuven, iMinds-ITEC, Belgium

Editorial Board

·        Véronique Aubergé, LIG, Université Grenoble-Alpes, France

·        Yves Bestgen, IPSY, Université Catholique de Louvain, Belgique

·        Eric Bruillard, STEF, ENS Cachan, France

·        Cristelle Cavalla, DILTEC, Université Sorbonne Nouvelle, France

·        Thierry Chanier, LRL, Université Blaise Pascal de Clermont Ferrand, France

·        Françoise Demaizière, Université Paris Diderot, France

·        Philippe Dessus, LSE, Université Grenoble-Alpes, France

·        Sylvain Detey, Waseda University, Japon

·        Walt Detmar Meurers, Universität Tübingen, Allemagne

·        Maxine Eskenazi, Carnegie Mellon University, USA

·        Cédrick Fairon, CENTAL, Université Catholique de Louvain, Belgique

·        Dan Flickinger, LinGO Laboratory, Stanford University, USA

·        Nuria Gala, LIF, Aix-Marseille Université, France

·        Sylviane Granger, CECL, Université Catholique de Louvain, Belgique

·        Nathalie Kübler, CLILLAC, Université Paris Diderot, France

·        Jean-Marc Labat, LIP6, Université Pierre-et-Marie-Curie, France

·        Patrice Pognan, PLIDAM, INALCO, France

·        Mathias Schulze, University of Waterloo, Canada

·        Isabel Trancoso, Instituto Superior Técnico, Portugal

·        Stefan Trausan-Matu, Universitatea Politehnica din Bucuresti, Roumanie

·        Elena Volodina , University of Gothenburg, Suède

·        Virginie Zampa, LIDILEM, Université Grenoble-Alpes, France

·        Michael Zock, LIF, Aix-Marseille Université, France


Accuracy across Proficiency Levels: A Learner Corpus Approach


Accuracy across Proficiency Levels
A Learner Corpus Approach

Presses universitaires de Louvain • Corpora and Language in Use

This volume is a corpus study of the construct of accuracy by learners of English as a Foreign Language based on the International Corpus of Learner English. Accuracy is analysed from a developmental point of view at four consecutive levels of language proficiency (B1, B2, C1, C2), thereby providing insights into areas of progress, stabilisation and regression. Written within a computer-aided error analysis research framework, this volume offers valuable information about the development of more than forty error types in a wide variety of domains such as grammar, lexis, lexico-grammar, spelling and punctuation. It provides important methodological considerations for developmental learner corpus research, presents abundantly illustrated analyses of authentic learner errors as well as suggestions for improving the descriptors of the Common European Framework of Reference for Languages.

Special 20% discount until January 20 : 28.50 €

Investigating segmental, prosodic and fluency features in spoken learner corpora

Call for papers – Special Issue on “Investigating segmental, prosodic and fluency features in spoken learner corpora”

Following an increasing awareness of phonetic learner corpora for phonetic and phonological research and for corpus linguistics, we invite paper submissions for a special issue of the “International Journal of Learner Corpus Research” entitled “Investigating segmental, prosodic and fluency features in spoken learner corpora”.

With this issue we would like to promote research on speech of language learners in large-scale data settings. We would like to invite linguists, phoneticians, speech technologists, second/foreign language researchers as well as scientists from all other fields who share an interest in spoken learner corpora, particularly those with non-scripted L2 speech.

Papers on all topics related to spoken learner corpora are welcome, especially those focusing on the following topics:

  •  (Re-)examinations of theories and models of L2 phonology acquisition
  •  Segmental and prosodic characteristics of non-native speech
  •  Experimental research with data from phonetic learner corpora
  •  Contrastive phonetic studies of L1 and L2 speech based on corpus data
  •  Assessment and annotation of L2 speech
  •  Integration of learner corpora in computer-assisted spoken language training

In accordance with the guidelines of the journal, the length of full papers, i.e. original research papers reporting on completed learner corpus-based research, should be between 7,000 and 10,000 words including references.

Important dates

  •  First call for papers: December 2015
  •  Deadline for submission: 15 April 2016
  •  First review completed: 30 June 2016
  •  Revised manuscripts due: 15 August 2016:
  •  Second review completed: 30 November 2016
  •  Final submission of accepted papers: 15 February 2017

Guest editors:

  •  Jürgen Trouvain (Saarland University, Saarbrücken, Germany)
  •  Frank Zimmerer (Saarland University, Saarbrücken, Germany)
  •  Bernd Möbius (Saarland University, Saarbrücken, Germany)
  •  Mária Gósy (Hungarian Academy of Sciences, Budapest, Hungary)
  •  Anne Bonneau (CNRS/LORIA, Nancy, France)

Submission Guidelines:
The guide for authors can be found on the journal homepage:
<>. All manuscripts should be submitted through Benjamins’ Editorial Manager: <>.
When submitting their manuscript, authors should select ‘Special issue: Phonetic Learner
Corpora’ under ‘Select Section/Category’ in the submission menu.

Corpora in Language Learning and Teaching

CALL FOR PAPERS, LLT Special Issue on: Corpora in Language Learning and Teaching
Special issue editors: Nina Vyatkina and Alex Boulton
Corpora in their many guises have been applied for the purposes of language learning
and language teaching since they emerged in their modern form in the 1960s. Whereas originally, more pedagogical applications were of indirect nature with corpus-based studies informing the contents of textbooks and reference grammars, recent years have seen an exponential growth of more direct applications, also known as Data-Driven Learning (DDL). These developments have been documented in a variety of publications, most notably in the series of edited volumes containing selected papers from the
biannual Teaching and Language Corpora (TaLC) conferences as well as special issues of several major journals. Since the only LLT special issue on this topic was published in 2001, the time has now come to take stock of the new developments in how corpora can be of help to language teachers, learners, and other users.
For this special issue, we seek proposals that present theoretically grounded and methodologically rigorous empirical studies of language learning processes or outcomes in DDL contexts using corpora, broadly defined to include native speaker corpora, second language learner corpora, pedagogical corpora, multimodal corpora, the web-as-corpus, etc. These contexts may include direct explorations of corpora by learners, indirect applications with teacher-prepared corpus-based activities, and any combinations
thereof. We especially welcome proposals that aim to fill existing research gaps by reporting on the use of new DDL technologies (e.g., corpus tools beyond concordancers, corpora in CALL packages), the effectiveness of different DDL types, specific DDL effects beneficial for language learning (e.g., input enrichment and enhancement, learner autonomy, guided induction), integration of DDL instruction modules into regular curricula, as well as languages other than English, instructional contexts other than
university, teachers other than DDL researchers, and comparisons of different learning styles, motivations, levels, or profiles.

Methodologically, we would like to invite more longitudinal and/or mixed-method studies which integrate quantitative and qualitative data. Please note that articles containing only descriptions of corpora, software, or pedagogical procedures without presenting in-depth empirical data will not be considered. Furthermore, we cannot accept studies that analyze or compare linguistic data from learner and native speaker corpora but that do not consider teaching and learning processes and outcomes as the major focus of the paper.
Please consult the LLT website for general guidelines on submission
( and research (
Send a title and 300-word abstract in a word document by February 1, 2016 to
Publication timeline:
February 1, 2016: Submission deadline for abstracts
February 15, 2016: Invitation to authors to submit a manuscript
July 15, 2016: Submission deadline for manuscripts
October 1, 2017: Publication of special issue

International Journal of Learner Corpus Research: call for papers

The International Journal of Learner Corpus Research (IJLCR) is a forum for researchers who collect, annotate, and analyse computer learner corpora and/or use them to investigate topics in Second Language Acquisition and linguistic theory in general, inform foreign language teaching, develop learner-corpus-informed tools (e.g. courseware, proficiency tests, dictionaries and grammars) or conduct natural language processing tasks (e.g. annotation, automatic spell- and grammar-checking , L1 identification). IJLCR aims to highlight the multidisciplinary and broad scope of practice that characterizes the field and publishes original research covering methodological, theoretical and applied work in any area of learner corpus research.

IJLCR features research papers, shorter research notes and reviews of books, corpora and software tools. The language of the journal is English. The journal will also publish special issues. All contributions are peer-reviewed.

IJLCR is now inviting submissions for Vol. 2 No. 1 (to be published in spring 2016).

For more information, visit the official website of the journal:

Best wishes,
Marcus Callies and Magali Paquot
IJLCR General editors

CFP: International Journal of Learner Corpus Research, inaugural issue

Dear colleagues,

We are pleased to announce the launch of a new journal entitled International Journal of Learner Corpus Research (IJLCR) published by John Benjamins Publishing Company and edited by my colleague Marcus Callies and myself (with the help of Sylviane Granger as consulting editor). From 2015, the journal will publish two issues per year and is meant to be a forum for researchers who collect, annotate, and analyze computer learner corpora and/or use them to investigate topics in second language acquisition and linguistic theory in general, inform foreign language teaching, develop learner-corpus-informed tools (e.g. courseware, proficiency tests, dictionaries, and automatic spell- and grammar-checkers), or conduct natural language processing tasks (e.g. automatic spell- and grammar-checking, L1 identification). IJLCR will thus highlight the multidisciplinary and broad scope of practice that characterizes the field and will publish original research covering methodological, theoretical and applied work in any area of learner corpus research.

We would like to invite you to submit a manuscript for IJLCR first issue.

The first issue will be published in the spring of 2015 and feature, among other things, research papers that represent strengths and current developments in the field. Research papers should be between 7,000 and 10,000 words (including references). We are particularly interested in publications that focus on:

– the acquisition of pragmatic, discourse, genre and writing skills in L2
– longitudinal studies of learner language through learner corpora
– learner speech
– strong SLA-informed analyses of learner corpus data
– practical pedagogical applications of learner corpora (i.e. the use of learner corpora in the classroom or in curriculum and materials design)
– NLP-oriented papers (e.g. annotation, error detection and correction)

The (very strict) schedule is as follows:

– Mark of interest by return (to and
30 November: a 500-word abstract including a clear description of data, methodology and results;
Mid December: Formatting guidelines sent to a shortlist of authors (based on the submitted abstract)
30 March 2014 (at the latest, if possible earlier, great!): Full papers
30 May 2014: Comments from reviewers send to authors
30 August 2014: Revised papers

All submitted manuscripts will be peer-reviewed by two members of the editorial board and will only be accepted for the inaugural issue if they are recommended for acceptance with minor revisions. Priority will be given to articles that display a strong theoretical background and solid methodology (including statistics if relevant) and feature one or more of the special areas of interest listed above. Other accepted manuscripts will be published in subsequent issues of IJLCR.

Don’t hesitate to share this with colleagues who may be looking for an outlet for their manuscripts in progress.

Please contact us if you have any queries. We are looking forward to receiving your abstracts.

Thank you for your consideration,

Best wishes,

Marcus Callies and Magali Paquot
General editors of the International Journal of Learner Corpus Research