Predicting the Difficulty of Language Proficiency Tests (bibtex)
by Lisa Beinborn, Torsten Zesch and Iryna Gurevych
Abstract:
Language proficiency tests are used to evaluate and compare the progress of language learners. We present an approach for automatic difficulty prediction of C-tests that performs on par with human experts. On the basis of detailed analysis of newly collected data, we develop a model for C-test difficulty introducing four dimensions: solution difficulty, candidate ambiguity, inter-gap dependency, and paragraph difficulty. We show that cues from all four dimensions contribute to C-test difficulty.
Reference:
Predicting the Difficulty of Language Proficiency Tests Lisa Beinborn, Torsten Zesch and Iryna Gurevych, In Transactions of the Association for Computational Linguistics, volume 2, 2014.
Bibtex Entry:
@article{TACL414b,
abstract = {Language proficiency tests are used to evaluate and compare the progress of language learners. We present an approach for automatic difficulty prediction of C-tests that performs on par with human experts. On the basis of detailed analysis of newly collected data, we develop a model for C-test difficulty introducing four dimensions: solution difficulty, candidate ambiguity, inter-gap dependency, and paragraph difficulty. We show that cues from all four dimensions contribute to C-test difficulty.},
author = {Beinborn, Lisa and Zesch, Torsten and Gurevych, Iryna},
issn = {2307-387X},
journal = {Transactions of the Association for Computational Linguistics},
pages = {517--529},
title = {{Predicting the Difficulty of Language Proficiency Tests}},
url = {http://www.aclweb.org/anthology/Q14-1040},
volume = {2},
year = {2014}
}