Using Google Translate for Academic English Writing Instruction
| Project/Area Number |
18K00656
|
|---|
| Research Category |
Grant-in-Aid for Scientific Research (C)
|
| Allocation Type | Multi-year Fund |
|---|
| Section | 一般 |
|---|
| Review Section |
Basic Section 02080:English linguistics-related
|
|---|
| Research Institution | The University of Aizu |
|---|
Principal Investigator |
Heo Younghyon 会津大学, コンピュータ理工学部, 上級准教授 (10631476)
|
|---|
| Co-Investigator(Kenkyū-buntansha) |
Perkins Jeremy 会津大学, コンピュータ理工学部, 上級准教授 (30725635)
Paik Incheon 会津大学, コンピュータ理工学部, 教授 (70336478)
|
|---|
| Project Period (FY) |
2018-04-01 – 2023-03-31
|
| Project Status |
Completed (Fiscal Year 2022)
|
| Budget Amount *help |
¥2,860,000 (Direct Cost: ¥2,200,000、Indirect Cost: ¥660,000)
Fiscal Year 2020: ¥910,000 (Direct Cost: ¥700,000、Indirect Cost: ¥210,000)
Fiscal Year 2019: ¥910,000 (Direct Cost: ¥700,000、Indirect Cost: ¥210,000)
Fiscal Year 2018: ¥1,040,000 (Direct Cost: ¥800,000、Indirect Cost: ¥240,000)
|
|---|
| Keywords | L2 writing / Machine translation / academic writing / Academic writing / Machine Translation / Machine-translated text / machine-translated text / keyword analysis / Google Translate / Academic English / Machine Learning |
|---|
| Outline of Final Research Achievements |
There were three goals in this project. First, we investigated how well human readers can detect machine-translated text. We also performed a word analysis (n-gram analysis). Regarding the first goal, we found that the machine-translated text using Neural Machine Translation was so natural that human raters could not successfully detect them (51% accuracy). The results of the n-gram analysis showed that the top 50 most frequently used words were different between human-written and machine-translated texts, indicating some unique traits of each. Our second goal was to test whether machine learning can detect machine-translated texts. It was found that machine learning could detect machine-translated texts with high accuracy (accuracy rate 89% to 99%). The third goal was to create educational materials, and we were able to create materials teaching effective and appropriate use of Google Translate based on the results of our survey conducted on English instructors and our word analysis.
|
| Academic Significance and Societal Importance of the Research Achievements |
Based on the result of our research (machine-translated writing being identifiable) and other studies, a system can be further developed and used to detect machine-translated writings (for L2 teaching). Also, we could instruct students how to use a machine translation tool to learn L2 writing.
|
Report
(6 results)
Research Products
(4 results)
