Detecting Context Dependence in Exercise Item Candidates Selected from Corpora

Pilán, Ildikó

doi:10.18653/v1/w16-0517

Cited by 3 publications

(7 citation statements)

References 15 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Driven by the recent advances in NLP, current ICALL applications which can be used for vocabulary learning purposes are doing more and more credit to the "Intelligent" part of their name. In the category of intelligent corpus consultation applications, the hybrid HitEx system for Swedish (Pilán et al, 2016) is a well-known example: it allows extracting context-independent example sentences of a given proficiency level from corpora by performing fine-grained and customisable queries. To this end, the system relies on computer-readable lexical-semantic resources and POS-tagged, lemmatised and parsed Swedish corpora, to which then a series of rule-based and machine learning-based selection criteria are applied.…”

Section: Wsd In Icallmentioning

confidence: 99%

See 1 more Smart Citation

Proceedings of the 12th Workshop on Natural Language Processing for Computer Assisted Language Learning (NLP4CALL 2023)

2023

Linköping Electronic Conference Proceedings

View full text Add to dashboard Cite

The workshop series on Natural Language Processing (NLP) for Computer-Assisted Language Learning (NLP4CALL) is a meeting place for researchers working on the integration of Natural Language Processing and Speech Technologies in CALL systems and exploring the theoretical and methodological issues arising in this connection. The latter includes, among others, the integration of insights from Second Language Acquisition (SLA) research, and the promotion of "Computational SLA" through setting up Second Language research infrastructures.The intersection of Natural Language Processing (or Language Technology / Computational Linguistics) and Speech Technology with Computer-Assisted Language Learning (CALL) brings "understanding" of language to CALL tools, thus making CALL intelligent. This fact has given the name for this area of research -Intelligent CALL, or for short, ICALL. As the definition suggests, apart from having excellent knowledge of Natural Language Processing and/or Speech Technology, ICALL researchers need good insights into second language acquisition theories and practices, as well as knowledge of second language pedagogy and didactics. This workshop therefore invites a wide range of ICALL-relevant research, including studies where NLP-enriched tools are used for testing SLA and pedagogical theories, and vice versa, where SLA theories, pedagogical practices or empirical data and modelled in ICALL tools. The NLP4CALL workshop series is aimed at bringing together competences from these areas for sharing experiences and brainstorming around the future of the field. We invited submissions:-that describe research directly aimed at ICALL -that demonstrate actual or discuss the potential use of existing Language and Speech Technologies or resources for language learning -that describe the 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. learning material generation, assessment of learner texts and responses, individualized learning solutions, provision of feedback -that discuss challenges and/or research agenda for ICALL -that describe empirical studies on language learner data This year a special focus was given to work done on second language vocabulary and grammar profiling, as well as the use of crowdsourcing for creating, collecting, and curating data in NLP projects. We encouraged paper presentations and software demonstrations describing the above-mentioned themes primarily, but not exclusively, for the Nordic languages.A special feature in this year's workshop is the research notes session. This session included short talks about PhD projects and ongoing unfinished research that collaborating teams were eager to discuss with the community and get feedback. We tested this feature for the second time with an intention to evaluate its impact and utility for future uses. This time around, we circulated a separate call for expression of interest.

show abstract

Section: Wsd In Icallmentioning

confidence: 99%

“…• human expert judgments of exercise quality along different dimensions (e.g., Chinkina and Meurers, 2017;Chinkina et al, 2020;Burstein and Marcu, 2005;Antonsen et al, 2013;Chalvin et al, 2013;Pilán et al, 2017;Pilán, 2016;Slavuj and Prskalo, 2021;Malafeev, 2014;Freitas et al, 2013); and…”

Section: Introductionmentioning

confidence: 99%

Proceedings of the 12th Workshop on Natural Language Processing for Computer Assisted Language Learning (NLP4CALL 2023)

2023

Linköping Electronic Conference Proceedings

View full text Add to dashboard Cite

show abstract

“…the lack of a subject or a finite verb (all verb forms except infinitive, supine and participle) inspired by . The completeness criterion checks the beginning and the end of a sentence for orthographic clues such as capital letters and punctuation, in a similar fashion to Pilán (2016). A large amount of nonlemmatized tokens, i.e.…”

Section: Well-formednessmentioning

confidence: 99%

“…The presence of linguistic elements responsible for connecting sentences at a syntactic or semantic level is therefore suboptimal (Kilgarriff et al, 2008). We incorporate a number of criteria for capturing this aspect which we described also in Pilán (2016).…”

Section: Context Independencementioning

confidence: 99%

Candidate sentence selection for language learning exercises: from a comprehensive framework to an empirical evaluation

Pilán,

Volodina,

Borin

2017

Preprint

Self Cite

View full text Add to dashboard Cite

We present a framework and its implementation relying on Natural Language Processing methods, which aims at the identification of exercise item candidates from corpora. The hybrid system combining heuristics and machine learning methods includes a number of relevant selection criteria. We focus on two fundamental aspects: linguistic complexity and the dependence of the extracted sentences on their original context. Previous work on exercise generation addressed these two criteria only to a limited extent, and a refined overall candidate sentence selection framework appears also to be lacking. In addition to a detailed description of the system, we present the results of an empirical evaluation conducted with language teachers and learners which indicate the usefulness of the system for educational purposes. We have integrated our system into a freely available online learning platform.

show abstract

Section: Introductionmentioning

confidence: 99%

The instructional effectiveness of automatically generated exercises for learning French grammatical gender: preliminary results

Bodnar

2022

Proceedings of the 11th Workshop on Natural Language Processing for Computer-Assisted Language Learning (NLP4CALL 2022)

View full text Add to dashboard Cite

Research into Automatic Exercise Generation (AEG) contributes new tools aimed at reducing the barrier to creating practice material, but few have been deployed in actual instruction with real learners. The present study extends previous work by employing AEG technology in instruction with L2 learners to evaluate its pedagogical effectiveness. Thirty-two second language learners of French were assigned to either a treatment condition, who practised with generated exercises, or a control condition that did no extra work. Both groups completed pre-, post-, and delayed post-tests. Participants in the treatment condition also completed questionnaires that elicited data on their in-practice emotions and the situations in which they arose. Our preliminary results suggest that AEG-based instruction can be pedagogically effective and support positive learning experiences, help to identify aspects of the instruction that could be improved, and suggest that a peer review mechanism could have an important role in future CALL platforms that use generated exercises.

show abstract

Detecting Context Dependence in Exercise Item Candidates Selected from Corpora

Cited by 3 publications

References 15 publications

Proceedings of the 12th Workshop on Natural Language Processing for Computer Assisted Language Learning (NLP4CALL 2023)

Proceedings of the 12th Workshop on Natural Language Processing for Computer Assisted Language Learning (NLP4CALL 2023)

Candidate sentence selection for language learning exercises: from a comprehensive framework to an empirical evaluation

The instructional effectiveness of automatically generated exercises for learning French grammatical gender: preliminary results

Contact Info

Product

Resources

About