Hoppa till huvudinnehåll

3rd workshop on NLP for computer-assisted language learning, SLTC, Uppsala, Sweden

SLTC workshop, November, 13, 2014, Uppsala, Sweden

Thank you for your participation in the workshop!

Workshop proceedings are now available online: http://www.ep.liu.se/ecp_home/index.en.aspx?issue=107

ACL anthology link to proceedings is here and in ACL beta-version here

We encourage you to join the nlp-call mailing list to get news and updates from the ICALL community. This mailing list is a united list for ICALL SIGs (Special Interest Groups) at EuroCALL, CALICO and Nodalida. To join the list, contact Mat Schulze, mschulze@uwaterloo.ca. These mails usually arrive with the [ICALL] prefix in front of the messages. In case you would like to ask some question to the community or advertise some event/resource/tool, mail to nlpcall@artsservices.uwaterloo.ca.


View the results of the Terminology mess... hmm... message questionnaire here

If you haven't yet filled in the questionnaire, you still can do it below

 

Some workshop pictures


Workshop venue

Campus Blåsenhus , Uppsala University. Address: von Kraemers Allé 1A, 752 37 Uppsala. Room 13:028

Further practical information is provided at the conference website


NOTE!

Don't forget, that you are required to submit to us the Copyright Agreement with your final submission. Please download the form from the provided URL: http://spraakbanken.gu.se/sites/spraakbanken.gu.se/files/NLP4CALL_2014_…, fill it in, sign (by all the authors; or by the corresponding author if the others do not object), scan it and attach to the mail.

You need to register to attend.


Workshop schedule

9.00-9.05 Introduction [pdf; slides]

9.05-10.00 Short paper presentations

  • 9.05-9.10 Tobias Horsmann and Torsten Zesch Towards Automatic Scoring of Cloze Items by Selecting Low-Ambiguity Contexts [pdf; slides]
  • 9.10-9.15 Nikolina Koleva, Andrea Horbach, Alexis Palmer, Manfred Pinkal and Simon Ostermann Paraphrase Detection for Short Answer Scoring [pdf; slides]
  • 9.15-9.20 Roberto Carlini, Joan Codina-Filba and Leo Wanner Improving Collocation Correction by Ranking Suggestions Using Linguistic Knowledge [pdf; slides]
  • 9.20-9.25 Levi King and Markus Dickinson Leveraging Known Semantics for Spelling Correction [pdf; slides]
  • 9.25-9.30 Christos Koniaris An approach to measure pronunciation similarity in second language learning using radial basis function kernel [pdf; slides]
  • 9.30-9.35 Robert Reynolds, Eduard Schaf and Detmar Meurers A VIEW of Russian: Visual Input Enhancement for a morphologically rich language [pdf; slides]
  • 9.35-9.40 Elizaveta Kuzmenko and Andrey Kutuzov Russian Error-Annotated Learner English Corpus: a Tool for Computer-Assisted Language Learning [pdf; slides]
  • 9.40-9.45 Sowmya Vajjala and Kaidi Lõo Experiments with Modeling the CEFR Level Prediction for Estonian Learner Text [pdf; slides]
  • 9.45-9.50 Elena Volodina, Ildikó Pilán, Stian Rødven Eide and Hannes Heidarsson You get what you annotate: a pedagogically annotated corpus of coursebooks for Swedish as a Second Language [pdf; slides]
  • 9.50-9.55 Thomas Francois An analysis of a French as a Foreign language corpus for readability assessment [pdf; slides]

10.00-10.15 Coffee break

10.15-10.45 Poster session 1

  • Tobias Horsmann and Torsten Zesch Towards Automatic Scoring of Cloze Items by Selecting Low-Ambiguity Contexts
  • Roberto Carlini, Joan Codina-Filba and Leo Wanner Improving Collocation Correction by Ranking Suggestions Using Linguistic Knowledge
  • Christos Koniaris An approach to measure pronunciation similarity in second language learning using radial basis function kernel
  • Elizaveta Kuzmenko and Andrey Kutuzov Russian Error-Annotated Learner English Corpus: a Tool for Computer-Assisted Language Learning
  • Elena Volodina, Ildikó Pilán, Stian Rødven Eide and Hannes Heidarsson You get what you annotate: a pedagogically annotated corpus of coursebooks for Swedish as a Second Language

10.45-11.15 Poster session 2

  • Nikolina Koleva, Andrea Horbach, Alexis Palmer, Manfred Pinkal and Simon Ostermann Paraphrase Detection for Short Answer Scoring
  • Levi King and Markus Dickinson Leveraging Known Semantics for Spelling Correction
  • Robert Reynolds, Eduard Schaf and Detmar Meurers A VIEW of Russian: Visual Input Enhancement for a morphologically rich language
  • Sowmya Vajjala and Kaidi Lõo Experiments with Modeling the CEFR Level Prediction for Estonian Learner Text
  • Thomas Francois An analysis of a French as a Foreign language corpus for readability assessment

11.15-11.50 Detmar Meurers A roadmap connecting NLP research and language learning (Invited talk) [handout]

11.50-12.00 Final discussion


Call for papers

Intelligent Computer-Assisted Language Learning (ICALL), i.e., the integration of Natural Language Processing (NLP) and Speech Technologies (ST) in language learning applications, is a rapidly developing area which has started to attract increased attention from the Language Technology (LT) community. ICALL research has generated a number of successful applications for alleviating a variety of (mechanical) tasks that teachers face daily in their work, for example grammar or spelling error marking, essay grading, preparation of text questions for reading activities, creating tests and exercises, etc.

However, reusing NLP/ST methods or tools (developed for other than pedagogical purposes) in pedagogical applications is not always pedagogically justifiable since they need to be adapted to the educational tasks, e.g. readability measures for legal texts adapted to the second language learning context. Thus, LT researchers who intend to re-use their algorithms and techniques in CALL applications need new datasets, specifically designed corpora, databases, etc. to fine-tune their tools for new target groups – the design and compilation of which are both critical for achieving good results and time-consuming.

There are other challenges that the area of NLP-based CALL faces: re-use and sharing of existing NLP/ST components, copyright issues, standardization of pedagogical framework, lack of collaboration with end-users – to name just a few. Probably the most significant challenge is to make sure that the research results reach actual end-users in the form of tools which can become a part of the educational process, and which are both easy of use and have a pedagogically sound basis.

This workshop aims to bring together (computational) linguists involved in research aiming at integrating NLP/ST in CALL systems and exploring the theoretical and methodological issues arising in this connection, with the purpose to share experiences, achievements and setbacks, and to discuss potential ways of addressing the challenges that need to be overcome.

This year we welcome papers

  • that describe research directly aimed at ICALL
  • that demonstrate actual or discuss potential use of existing NLP/ST tools or resources for language learning
  • that describe ongoing development of resources and tools with potential usage in ICALL, either directly in interactive applications, or indirectly in materials, application or curriculum development, e.g. collecting and annotating learner corpora; developing tools and algorithms for readability analysis, selecting optimal corpus examples, etc.
  • that discuss challenges and/or research agendas for ICALL
  • we are also interested in software demonstrations

We especially invite submissions describing the above-mentioned themes for the Nordic languages.


Submission information

We are using Nodalida 2013 template for the workshop this year. Authors are invited to submit papers between 7 and 14 pages of content, excluding title, abstract, references and author affiliations. Only pdf files will be accepted. Submissions will be managed through the electronic conference management system EasyChair. Final camera-ready versions of accepted papers will be given an additional page to address reviewer comments.

Papers should describe original unpublished work or work-in-progress. Every paper will be reviewed by at least 2 members of the program committee. As reviewing will be blind, please ensure that papers are anonymous. Self-references that reveal the author's identity, e.g., "We previously showed (Smith, 1991) ...", should be avoided. Instead, use citations such as "Smith previously showed (Smith, 1991) ...". Submissions will be judged on appropriateness, clarity, originality/innovativeness, correctness/soundness, meaningful comparison, significance and impact of ideas or results. Accepted papers will be published in a NEALT Proceeding Series and, additionally, made available through ACL anthology.

Please note that NoDaLiDa 2013 format adopts a single-column, smaller page format, optimized for on-screen reading. In terms of actual word counts, the above page numbers correspond to approximately 4-8 pages, in a ‘classic’, two-column conference proceedings layout.


Important dates:

  • June, 16: first call for papers
  • August, 8: EasyChair opens for submissions
  • August, 14: second call for papers
  • September, 14: final call for papers
  • September, 25 --> October, 2: paper submission deadline, via EasyChair
  • October, 16: notification of acceptance
  • October, 30: camera-ready papers for publication. You are also required to submit the NEALT transfer of copyright agreement (signed at least by the corresponding author and scanned) with your final submission.
  • November, 13, 9.00-12.00: workshop date


Invited speaker

We are happy to announce that our invited speaker will be

Prof. Detmar Meurers, University of Tübingen, Germany


Program committee:

  • Lars Ahrenberg, Linköping University, Sweden
  • Lars Borin, University of Gothenburg, Sweden
  • Antonio Branco, University of Lisboa, Portugal
  • Simon Dobnik, University of Gothenburg, Sweden
  • Robert Eklund, Linköping University, Sweden
  • Katarina Heimann Mühlenbock, DART, Sahlgrenska Universitetssjukhuset, Göteborg, Sweden
  • Thomas Francois, UCLouvain, Belgium
  • Arne Jönsson, Linköping University, Sweden
  • Sofie Johansson Kokkinakis, University of Gothenburg, Sweden
  • Chris Koniaris, University of Gothenburg, Sweden
  • Peter Ljunglöf, University of Gothenburg, Sweden
  • Hrafn Loftsson, Reykjavik University, Iceland
  • Montse Maritxalar, University of the Basque country, Spain
  • Detmar Meurers, University of Tübingen, Germany
  • Martí Quixal, University of Tübingen, Germany
  • Mathias Schulze, University of Waterloo, Canada
  • Joel Tetreault, Yahoo! Labs, US
  • Trond Trosterud, Universitetet i Tromsø, Norway
  • Cornelia Tschichold, Swansea University, UK
  • Francis Tyers, The Arctic University of Norway, Norway
  • Elena Volodina, University of Gothenburg, Sweden


Workshop organizers

  • Elena Volodina, Språkbanken, Department of Swedish, University of Gothenburg; elena dot volodina at svenska dot gu dot se (Organizing chair)
  • Lars Borin, Språkbanken, Department of Swedish, University of Gothenburg; lars dot borin at svenska dot gu dot se
  • Ildikó Pilán, Språkbanken, Department of Swedish, University of Gothenburg; ildiko dot pilan at svenska dot gu dot se


Related links

Other upcoming conferences/events in ICALL

Past events in ICALL

For all inquiries, please email Elena Volodina <elena dot volodina at svenska dot gu dot se>