Manipulating the difficulty of C-Tests

Thumbnail
Count of file(s): 5
data.zip (13.80KB)
DifficultyPrediction.jar (Difficulty Prediction model (using all features)) (99.87MB)
model_inc (SVM model (pickle file) to measure the relative change in difficulty when increasing the gap size.) (261.5KB)
model_dec (SVM model (pickle file) to measure the relative change in difficulty when decreasing the gap size.) (163.5KB)
wp_eng_lem_nc_c.zip (Semantic analysis calculated on the Wikipedia corpus) (845.5MB)
Date
Author
Type
Dataset
Metadata
Show full item record
Export
Text
BibTex
DataCite XML
JSON

Description

We propose two novel manipulation strategies for increasing and decreasing the difficulty of C-tests automatically. This is a crucial step towards generating learner-adaptive exercises for self-directed language learning and preparing language assessment tests. To reach the desired difficulty level, we manipulate the size and the distribution of gaps based on absolute and relative gap difficulty predictions. We evaluate our approach in corpus-based experiments and in a user study with 60 participants. We find that both strategies are able to generate C-tests with the desired difficulty level.

DFG subject classification

4.43-06 Datenmanagement, datenintensive Systeme, Informatik-Methoden in der Wirtschaftsinformatik

URI

Related third party funded projects

HA(Hessen Agentur) | 521/17-03 | a! automated languag
DFG | GRK1994 | TPGurevychGRK1994

Related Resources

Collections

The following license files are associated with this item:

Creative Commons Attribution 4.0
Except where otherwise noted, this item's license is described as Creative Commons Attribution 4.0