NotesFAQContact Us
Collection
Advanced
Search Tips
Peer reviewed Peer reviewed
PDF on ERIC Download full text
ERIC Number: EJ1131310
Record Type: Journal
Publication Date: 2010
Pages: 16
Abstractor: As Provided
Reference Count: 14
ISBN: N/A
ISSN: EISSN-1792-8788
Second Language Writing Classification System Based on Word-Alignment Distribution
Kotani, Katsunori; Yoshimi, Takehiko
Themes in Science and Technology Education, v3 n1-2 p223-238 2010
The present paper introduces an automatic classification system for assisting second language (L2) writing evaluation. This system, which classifies sentences written by L2 learners as either native speaker-like or learner-like sentences, is constructed by machine learning algorithms using word-alignment distributions as classification features for detecting word-by-word translated expressions. The experimental results demonstrated that our classification system provided adequate classification results with respect to (i) high classification accuracy, (ii) classification results reflecting the properties of L2 learner sentences, and (iii) identification of learner-like expressions. These results suggest that our classification system can be used to evaluate L2 learner sentences.
Themes in Science and Technology Education. The Educational Approaches to Virtual Reality Technologies Laboratory, University of Ioannina, Ioannina, GR 45110, Greece. Tel: +30-2651005697; Fax: +30-2651005854; Web site: http://earthlab.uoi.gr/theste
Publication Type: Journal Articles; Reports - Research
Education Level: N/A
Audience: N/A
Language: English
Sponsor: N/A
Authoring Institution: N/A