[Apologies for cross-posting]
10th Workshop on NLP4CALL, NoDaLiDa 2021
31 May, 2021
09:00 - 17:30 CEST/UTC+2
Online-only event
**The program has been updated. The final program can be found at the end of this email and on the webpage.**
**Please note that the registration deadline is May 21, 2021. Registration is free of charge.**
Dear all,
we would like to invite you to participate in our 10th workshop on Natural Language Processing for Computer-Assisted Language Learning NLP4CALL.
Registration to the workshop is free and is done via the following link:
https://nodalida2021.github.io/registration.html
Please note that the workshop will take place via Zoom. The link to the workshop will be sent out to registered participants, so please register if you want to participate.
*Registration deadline is May 21, 2021.*
This year we will have a research notes session for the second time. This session includes short talks about PhD projects and ongoing unfinished research that collaborating teams were eager to discuss with the community and get feedback. This year, we have the following topics:
Automatic generation of vocabulary and grammar exercises for Finnish and Hungarian. Zsanett Ferenczi (PhD student).
BNP readability formulas for Algerian middle school EFL learners. Younes Behira (PhD student).
Automatically individualised reading assistance for second language learning through modelling learner vocabulary. Frankie Robertson (PhD student).
Suggestion for a Shared task at the next NLP4CALL. Elena Volodina.
Swedish Profile – research and L2 teaching potential. Therese Lindström Tiedemann, Elena Volodina, Yousuf Mohammed.
This year, we have two keynote speeches: Mark Brenchley and Kevin Cheung from Cambridge Assessment English, and Johanna Monti from the University of Naples.
Keynote 1 by Mark Brenchley and Kevin Cheung
Title: What is an NLP NLP? Considerations from an L2 Assessment Perspective
Recent years have witnessed what feels like an exponential development in the scope and performance of NLP-approaches to human language. This is no less the case regarding the field of second language assessment, where NLP techniques seem likely to become ever more essential to, and integrated with, the assessment process. Indeed, surveying the recent progress of NLP, it seems hard to think of an assessment area where such techniques would not have genuine practical value. From an NLP-perspective, in other words, the future of NLP-informed assessment looks extremely bright.
At the same time, it remains important to keep taking stock, especially where there is always a chance that techniques and applications will advance at a faster rate than our ability to properly conceptualise them. With that in mind, this talk offers a more philosophical perspective on the role of NLP in second language assessment, focusing on the question of what it might actually mean for something to be an "NLP NLP"; that is, a natural language processed, natural language profile. In general, it will explore the relationship between NLP and L2 profiles with regard to the wider notion of validity as a key assessment concept (Messick, 1989; Bachman & Palmer, 1996; Weir, 2005; Kane, 2006); In particular, it will do so with regard to the specific validation framework utilised at Cambridge English (e.g. Shaw & Weir, 2007), and with reference to some of our current principles and practice.
Keynote 2 by Johanna Monti
Title: Challenges of Gamified Crowdsourcing for language learning applications
Gamification is defined (Deterding et al., 2011) as "the use of game design elements in non-game contexts" and it has been employed variously in the field of language learning. Gamified crowdsourcing is an increasing practice, and researchers explore creative methods of use in different domains (Morschheuser et al. 2017; Morschheuser and Hamari 2019; Murillo Zamorano et al. 2020) also with respect to the collection of language resources for language learning applications (Fort et al. 2018; Nicolas et al. 2020; Eryiğit, et al. 2021 among others).
In this talk, I will present an overview of different types of gamified crowdsourcing and discuss the emerging opportunities and challenges of using it for language learning applications.
Program
The schedule for the workshop is as follows:
09:00 - 09:10 Opening session
09:10 - 10:00 Invited talk 1
What is an NLP NLP? Considerations from an L2 Assessment Perspective.
Mark Brenchley, Kevin Cheung
Chair: Elena Volodina
10:00 - 10:20 Coffee break
Session 1
Chair: Elena Volodina
10:20 - 10:50 Automatic annotation of curricular language targets to enrich activity models and support both pedagogy and adaptive systems.
Martí Quixal, Björn Rudzewitz, Elizabeth Bear and Detmar Meurers
10:50 - 11:20 Using Broad Linguistic Complexity Modeling for Cross-Lingual Readability Assessment.
Zarah Weiss, Xiaobin Chen and Detmar Meurers
11:20 - 11:30 Coffee break
Session 2
Chair: David Alfter
11:30 - 12:00 An Experiment on Implicitly Crowdsourcing Expert Knowledge about Romanian Synonyms from Language Learners.
Lionel Nicolas, Lavinia Nicoleta Aparaschivei, Verena Lyding, Christos Rodosthenous, Federico Sangati, Alexander König and Corina Forascu
12:00 - 13:00 Lunch
13:00 - 13:50 Invited talk 2
Challenges of Gamified Crowdsourcing for language learning applications.
Johanna Monti
Chair: Johannes Graën
13:50 - 14:00 Coffee break
Research notes session 1 *
Chair: David Alfter
Discussion leaders: Ildikó Pilán, Torsten Zesch, Gerold Schneider
14:00 - 14:10 Automatic generation of vocabulary and grammar exercises for Finnish and Hungarian.
Zsanett Ferenczi
14:10 - 14:20 BNP readability formulas for Algerian middle school EFL learners.
Younes Behira
14:20 - 14:30 Automatically individualised reading assistance for second language learning through modelling learner vocabulary.
Frankie Robertson
14:30 - 15:00 Research notes discussion
15:00 - 15:20 Coffee break
Session 3
Chair: Johannes Graën
15:20 - 15:40 Leveraging Task Information in Grammatical Error Correction for Short Answer Assessment through Context-based Reranking.
Ramon Ziai and Anna Karnysheva
15:40 - 16:00 Developing Flashcards for Learning Icelandic.
Xindan Xu and Anton Karl Ingason
16:00 - 16:20 DaLAJ - a dataset for linguistic acceptability judgments for Swedish.
Elena Volodina, Yousuf Ali Mohammed and Julia Klezl
16:20 - 16:40 Coffee break + best presentation voting
Research notes session 2 *
Chair: Ildikó Pilán
Discussion leaders: Lionel Nicolas, TBD
16:40 - 16:50 Suggestion for a Shared task at the next NLP4CALL.
Elena Volodina
16:50 - 17:00 Swedish Profile - research and L2 teaching potential.
Therese Lindström Tiedemann, Elena Volodina, Yousuf Mohammed
17:00 - 17:20 Research notes discussion
17:20 - 17:30 Closing session + best paper and presentation awards
* Note: For research notes sessions, questions/discussion will be at the end of the session, not after each presentation.
More information on the workshop can be found on the workshop webpage:
https://spraakbanken.gu.se/forskning/teman/icall/nlp4call-workshop-serie...
Best regards,
the NLP4CALL organizing committee