- 121 views
- 215 downloads
Identifying Negative Language Transfer in the English Writing of Chinese and Farsi Native Speakers
-
- Author / Creator
- Karimiabdolmaleki, Mohammad
-
Effective communication in English can facilitate educational and employment opportunities for second-language learners. English as a second or foreign language (ESOL) learners tend to employ rules from their native language while communicating in English, which can lead to Negative Language Transfer (NLT) when the rules transferred from the mother tongue do not match those of English. To assist ESOL learners in writing in English, NLT errors should be identified. However, manually identifying NLT is a difficult task, demanding time and expertise in both languages. Although NLT is a well-researched phenomenon in linguistics, few attempts have been made to automatically identify NLT in learner writing using machine learning techniques. In this work, I have implemented four classification algorithms to automatically identify NLT errors in second-language learner writing. The results show that the models can identify NLT in the English writing of Chinese and Farsi native speakers. This work makes the following contributions: (1) it implements supervised machine learning models and language models to identify NLT in learner writing; (2) it evaluates the models using two different datasets in two languages to investigate the generalizability of the models; and (3) it identifies the most important features for detecting NLT. This work shows
that the implemented models can be used in unstructured domains to identify NLT automatically for speakers of two languages: one is logographic and the other alphabetic. -
- Subjects / Keywords
-
- Graduation date
- Fall 2022
-
- Type of Item
- Thesis
-
- Degree
- Master of Science
-
- License
- This thesis is made available by the University of Alberta Library with permission of the copyright owner solely for non-commercial purposes. This thesis, or any portion thereof, may not otherwise be copied or reproduced without the written consent of the copyright owner, except to the extent permitted by Canadian copyright law.