Back to Search
Start Over
Predicting CEFR levels in learners of English: The use of microsystem criterial features in a machine learning approach
- Source :
- ReCALL, ReCALL, Cambridge University Press (CUP), 2021, pp.1-17. ⟨10.1017/S095834402100029X⟩
- Publication Year :
- 2021
- Publisher :
- Cambridge University Press (CUP), 2021.
-
Abstract
- This paper focuses on automatically assessing language proficiency levels according to linguistic complexity in learner English. We implement a supervised learning approach as part of an automatic essay scoring system. The objective is to uncover Common European Framework of Reference for Languages (CEFR) criterial features in writings by learners of English as a foreign language. Our method relies on the concept of microsystems with features related to learner-specific linguistic systems in which several forms operate paradigmatically. Results on internal data show that different microsystems help classify writings from A1 to C2 levels (82% balanced accuracy). Overall results on external data show that a combination of lexical, syntactic, cohesive and accuracy features yields the most efficient classification across several corpora (59.2% balanced accuracy).
- Subjects :
- language functions
Linguistics and Language
Computer science
criterial features
computer.software_genre
supervised learning
[INFO.INFO-CL]Computer Science [cs]/Computation and Language [cs.CL]
Language and Linguistics
Education
linguistic complexity
[INFO.INFO-LG]Computer Science [cs]/Machine Learning [cs.LG]
Microsystem
060201 languages & linguistics
business.industry
4. Education
05 social sciences
microsystem
050301 education
06 humanities and the arts
[SCCO.LING]Cognitive science/Linguistics
Computer Science Applications
Automatic Essay Scoring
0602 languages and literature
Artificial intelligence
business
0503 education
computer
Natural language processing
Subjects
Details
- ISSN :
- 14740109 and 09583440
- Volume :
- 34
- Database :
- OpenAIRE
- Journal :
- ReCALL
- Accession number :
- edsair.doi.dedup.....52e72c1a8290c49b765b26a393d38cfc