Candidate evaluation strategies for improved difficulty prediction of language tests
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.
Vorschau
Zitieren
Zitierform:
Zitierform konnte nicht geladen werden.
Rechte
Nutzung und Vervielfältigung:
Dieses Werk kann unter einerCreative Commons Namensnennung - Nicht-kommerziell - Weitergabe unter gleichen Bedingungen 3.0 Lizenz (CC BY-NC-SA 3.0)
genutzt werden.