TU Darmstadt / ULB / TUbiblio

Candidate Evaluation Strategies for Improved Difficulty Prediction of Language Tests

Beinborn, Lisa and Zesch, Torsten and Gurevych, Iryna (2015):
Candidate Evaluation Strategies for Improved Difficulty Prediction of Language Tests.
In: Proceedings of the Tenth Workshop on Innovative Use of NLP for Building Educational Applications held in conjunction with NAACL 2015, [Online-Edition: http://aclweb.org/anthology/W15-0601],
[Conference or Workshop Item]

Abstract

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.

Item Type: Conference or Workshop Item
Erschienen: 2015
Creators: Beinborn, Lisa and Zesch, Torsten and Gurevych, Iryna
Title: Candidate Evaluation Strategies for Improved Difficulty Prediction of Language Tests
Language: English
Abstract:

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.

Title of Book: Proceedings of the Tenth Workshop on Innovative Use of NLP for Building Educational Applications held in conjunction with NAACL 2015
Uncontrolled Keywords: Educational Natural Language Processing;UKP_a_WALL;UKP_reviewed;UKP_p_AutoExerGen
Divisions: 20 Department of Computer Science
20 Department of Computer Science > Ubiquitous Knowledge Processing
Date Deposited: 31 Dec 2016 14:29
Official URL: http://aclweb.org/anthology/W15-0601
Identification Number: TUD-CS-2015-0066
Related URLs:
Export:
Suche nach Titel in: TUfind oder in Google

Optionen (nur für Redakteure)

View Item View Item