@inProceedings{Pilán-Ildikó2013-188465, title = {Automatic Selection of Suitable Sentences for Language Learning Exercises}, abstract = {In this study we investigated second and foreign language (L2) sentence readability, an area little explored so far in the case of several languages, including Swedish. The outcome of our research consists of two methods for sentence selection from native language corpora based on Natural Language Processing (NLP) and machine learning (ML) techniques. The two approaches have been made available online within Lärka, an Intelligent CALL (ICALL) platform offering activities for language learners and students of linguistics. Such an automatic selection of suitable sentences can be valuable for L2 teachers during the creation of new teaching materials, for L2 students who look for additional self-study exercises as well as for lexicographers in search of example sentences to illustrate the meaning of a vocabulary item. Members from all these potential user groups evaluated our methods and found the majority of the sentences selected suitable for L2 learning purposes.}, booktitle = {20 Years of EUROCALL: Learning from the Past, Looking to the Future. 2013 EUROCALL Conference, 11th to 14th September 2013 Évora, Portugal, Proceedings.}, author = {Pilán, Ildikó and Volodina, Elena and Johansson, Richard}, year = {2013}, ISBN = {978-1-908416-12-4}, pages = {218--225}, } @inProceedings{Pijetlovic-Dijana2013-188543, title = {Developing a Swedish spelling game on an ICALL platform}, abstract = {In this project we developed web services on the ICALL platform Lärka for automatic generation of Swedish spelling exercises using Text-To-Speech (TTS) technology which allows L2 learners to train their spelling and listening individually performance based levels. The embedded avatar pronounces a random item of the desired level, which the user has to spell. Furthermore, the users have the possibility to train their own words for different linguistic levels. A result tracker containing a total and correct answer score keeps track of the language learner’s performance. In order to analyse typical spelling errors and provide better feedback, misspellings are collected in a database. The usability of the spelling exercises, concerning the different linguistic levels and the quality of speech, has been evaluated through a questionnaire with 10 participants.}, booktitle = {20 Years of EUROCALL: Learning from the Past, Looking to the Future. 2013 EUROCALL Conference, Évora, Portugal, Proceedings.}, author = {Pijetlovic, Dijana and Volodina, Elena}, year = {2013}, ISBN = {978-1-908416-12-4}, } @inProceedings{Volodina-Elena2013-188550, title = {Compiling a corpus of CEFR-related texts.}, abstract = {This paper reports on initial efforts to compile a corpus of course book texts used for teaching CEFR-based courses of Swedish to adult immigrants. The research agenda behind compiling such a corpus comprises the study of normative “input” texts that can reveal a number of facts about what is being taught in terms of explicit grammar, receptive vocabulary, text and sentence readability; as well as build insights into linguistic characteristics of normative texts which can help anticipate learner performance in terms of active vocabulary, grammatical competence, etc. in classroom and testing settings. The CEFR “can-do” statements are known to offer flexibility in interpreting them for different languages and target groups. However, they are nonspecific and therefore it is difficult to associate different kinds of competences and levels of accuracy learners need in order to perform the communicative tasks with the different CEFR levels. To address this problem a systematic study needs to be performed for each individual anguage, both for “input” normative texts and “output” learner-produced texts. In this project we take the first step to collect and study normative texts for Swedish. The article describes the process of corpus compilation, annotation scheme of CEFR- relevant parameters, and methods proposed for text analysis, namely statistic and empiric methods, as well as techniques coming from computational linguistics/machine learning. }, booktitle = {Proceedings of the Language Testing and CEFR conference, Antwerpen, Belgium, May 27-29, 2013}, author = {Volodina, Elena and Johansson Kokkinakis, Sofie}, year = {2013}, } @inProceedings{Volodina-Elena2013-188549, title = {Towards a gold standard for Swedish CEFR-based ICALL}, abstract = {In qualitative projects on ICALL (Intelligent Computer-Assisted Language Learning), research and development always go hand in hand: development both depends upon the research results and dictates the research agenda. Likewise, in the development of the Swedish ICALL platform Lärka, the practical issues of development have dictated its research agenda. With NLP approaches, sooner or later, the necessity for reliable training data becomes unavoidable. At the moment Lärka's research agenda cannot be addressed without access to reliable training data, so-called “gold standard”. This paper gives an overview of the current state of the Swedish ICALL platform development and related research agenda, and describes the first attempts to collect the reference corpus (“gold standard”) coming from course books used in CEFR-based language teaching.}, booktitle = {Proceedings of the Second Workshop on NLP for Computer-Assisted Language Learning. NEALT Proceedings Series 17. Nodalida 2013, Oslo, Norway. }, author = {Volodina, Elena and Pijetlovic, Dijana and Pilán, Ildikó and Johansson Kokkinakis, Sofie}, year = {2013}, ISBN = {978-91-7519-588-9}, } @book{Volodina-Elena2013-188675, title = {Proceedings of the second workshop on NLP for computer-assisted language learning at NODALIDA 2013 May 22-24, 2013, Oslo, Norway}, author = {Volodina, Elena and Borin, Lars and Loftsson, Hrafn}, year = {2013}, publisher = {Linköping University Press}, adress = {Linköping, Sweden}, ISBN = {978-91-7519-588-9}, }