Logo: Deutsches Institut für Internationale Pädagogische Forschung

Forschung

Publikationendatenbank

Treffer anzeigen

Autor:
Beinborn, Lisa; Zesch, Torsten; Gurevych, Iryna:

Titel:
Candidate evaluation strategies for improved difficulty prediction of language tests

Quelle:
In: Association for Computational Linguistics (Hrsg.): Proceedings of the 10th Workshop on innovative use of NLP for Building Educational Applications held in conjunction with NAACL 2015 Denver, CO : Association for Computational Linguistics (2015) , 1-11

URL des Volltextes:
https://www.ukp.tu-darmstadt.de/fileadmin/user_upload/Group_UKP/CandidateEvaluationStrategies_BEACameraReady.pdf

Sprache:
Englisch

Dokumenttyp:
4. Beiträge in Sammelwerken; Tagungsband/Konferenzbeitrag/Proceedings

Schlagwörter:
Fortschritt, Lernen, Lernerfolg, Prognose, Ranking, Schwierigkeit, Sprachtest, Strategie


Abstract(original):
Language proficiency tests are a useful tool for evaluating learner progress, if the test difficulty fits the level of the learner. In this work, we describe a generalized framework for test difficulty prediction that is applicable to several languages and test types. In addition, we develop two ranking strategies for candidate evaluation inspired by automatic solving methods based on language model probability and semantic relatedness. These ranking strategies lead to significant improvements for the difficulty prediction of cloze tests. (DIPF/Orig.)


DIPF-Abteilung:
Informationszentrum Bildung

Notizen:

zuletzt verändert: 11.11.2016