Document Type
Honors Thesis
Abstract
Korean is a particularly challenging language for English speakers due to its typological distance from English, and as such, learning Korean typically requires hundreds or thousands of additional hours of instruction to reach intermediate and advanced levels. One solution that this study analyzes is the use of a rapidly improving technology: machine translation (MT). Participants were tasked with producing a short composition in Korean and then trained to use MT-based strategies to improve their writing; they also completed pre- and post-surveys to gauge their attitudes toward machine translation. Results showed improvement in vocabulary choice and grammar as well as case/locative markers with minimal improvements in other categories. Post-survey results showed participant beliefs that MT strategies allowed for better expression of ideas and were reliable for grammar and word order corrections. They also expressed that information provided about the issues of machine translation was beneficial. Feedback from a Korean language educator stated that MT improved writing overall by correcting grammar and sentence structure, but levels of proficiency play an important role in effectiveness. This work extends existing research internationally in MT-based L2 learner strategies, in addition to confirming machine translation as a form of AI with strong potential in language education.
Publication Date
12-1-2022
Language
English
License
This work is licensed under a Creative Commons Attribution-NonCommercial-Share Alike 4.0 International License.
Recommended Citation
Khandekar, Manali, "PEDAGOGICAL USES FOR MACHINE TRANSLATION: KOREAN L2 WRITING" (2022). 2022 Fall Honors Capstone Projects. 5.
https://mavmatrix.uta.edu/honors_fall2022/5