BibTeX

@inProceedings{falkenjack-heimannmuhlenbock-2012-using-178259,
	title        = {Using the probability of readability to order Swedish texts},
	abstract     = {In this study we present a new approach to rank readability in Swedish texts based on lexical, morpho-syntactic and syntactic analysis of text as well as machine learning. The basic premise and theory is presented as well as a small experiment testing the feasibility, but not actual performance, of the approach. The experiment shows that it is possible to implement a system based on the approach, however, the actual performance of such a system has not been evaluated as the necessary resources for such an evaluation does not yet exist for Swedish. The experiment also shows that a classifier based on the aforementioned linguistic analysis, on our limited test set, outperforms classifiers based on established metrics used to assess readability such as LIX, OVIX and Nominal Ratio.},
	booktitle    = {Proceedings of the Fourth Swedish Language Technology Conference},
	author       = {Falkenjack, Johan and Heimann Mühlenbock, Katarina},
	year         = {2012},
	pages        = {27--28},
}

@inProceedings{heimannmuhlenbock-johanssonkokkinakis-2012-swevoc-178263,
	title        = {SweVoc - A Swedish vocabulary resource for CALL},
	abstract     = {The core in language teaching and learning is vocabulary, and access to a delimited set of words for basic communication is central for most CALL applications. Vocabulary characteristics also play a fundamental role for matching texts to specific readers. For English, the task of grading texts into different levels of difficulty has long been facilitated by the existence of word lists serving as guides for vocabulary selection. For Swedish, the situation is with a few exceptions less fortunate, in that no base vocabulary organized according to aspects of usage has existed. The Swedish base vocabulary – SweVoc – is an attempt to remediate this. It is a comprehensive resource, aimed at differentiating vocabulary items into categories of usage and frequency. As we are of the opinion that no corpus of written text can do fully justice of general language use, we have utilized materials from a second language as reference for delimiting the category of core words. Another belief is that the task of defining a base vocabulary can not be fully automatic, and that a considerable amount of manual, traditional lexicographic work has to be invested. Hence, the present approach is not an innovative, but a methodological approach to word list generation for a specific purpose, much like LSP.We anticipate SweVoc to be integrated in CALL applications for vocabulary assessment, language teaching and students’ practice.},
	booktitle    = {Proceedings of the SLTC 2012 workshop on NLP for CALL, Lund, 25th October, 2012},
	author       = {Heimann Mühlenbock, Katarina and Johansson Kokkinakis, Sofie},
	year         = {2012},
	pages        = {28--34},
}