Skip to Main content Skip to Navigation

A Supervised Learning Model for the Automatic Assessment of Language Levels Based on Learner Errors

Abstract : This paper focuses on the use of technology in language learning. Language training requires the need to group learners homogeneously and to provide them with instant feedback on their productions such as errors [8, 15, 17] or proficiency levels. A possible approach is to assess writings from students and assign them with a level. This paper analyses the possibility of automatically predicting Common European Framework of Reference (CEFR) language levels on the basis of manually annotated errors in a written learner corpus [9, 11]. The research question is to evaluate the predictive power of errors in terms of levels and to identify which error types appear to be criterial features in determining interlanguage stages. Results show that specific errors such as punctuation, spelling and verb tense are significant at specific CEFR levels.
Complete list of metadatas

Cited literature [28 references]  Display  Hide  Download

https://hal.univ-rennes2.fr/hal-02496688
Contributor : Thomas Gaillat <>
Submitted on : Tuesday, March 3, 2020 - 11:12:53 AM
Last modification on : Friday, March 27, 2020 - 3:20:36 AM

File

EC_TEL_2019_A_supervised_model...
Files produced by the author(s)

Identifiers

  • HAL Id : hal-02496688, version 1

Citation

Nicolas Ballier, Thomas Gaillat, Andrew Simpkin, Bernardo Stearns, Manon Bouyé, et al.. A Supervised Learning Model for the Automatic Assessment of Language Levels Based on Learner Errors. EC-TEL 2019, EATEL, Sep 2019, Delft, Netherlands. pp.308-320. ⟨hal-02496688⟩

Share

Metrics

Record views

17

Files downloads

26