| Project/Area Number |
17K13498
|
|---|
| Research Category |
Grant-in-Aid for Young Scientists (B)
|
| Allocation Type | Multi-year Fund |
|---|
| Research Field |
Foreign language education
|
|---|
| Research Institution | Kyoto University |
|---|
Principal Investigator |
|
|---|
| Project Period (FY) |
2017-04-01 – 2024-03-31
|
| Project Status |
Completed (Fiscal Year 2023)
|
| Budget Amount *help |
¥3,900,000 (Direct Cost: ¥3,000,000、Indirect Cost: ¥900,000)
Fiscal Year 2020: ¥1,170,000 (Direct Cost: ¥900,000、Indirect Cost: ¥270,000)
Fiscal Year 2019: ¥780,000 (Direct Cost: ¥600,000、Indirect Cost: ¥180,000)
Fiscal Year 2018: ¥1,040,000 (Direct Cost: ¥800,000、Indirect Cost: ¥240,000)
Fiscal Year 2017: ¥910,000 (Direct Cost: ¥700,000、Indirect Cost: ¥210,000)
|
|---|
| Keywords | 自動評価 / 評価基準 / 生成AI / スピーキング / 発話データ / 評価指標 / 機械学習 / 学習用データ / スコア付き発話データ |
|---|
| Outline of Final Research Achievements |
This research aimed to create evaluation criteria and an annotated speech corpus for automatic evaluation for English speaking. In the first year, existing research was surveyed, and evaluation criteria were organized. In the two to three years, an environment for encoding speech data was prepared, and research on scoring and vectorization was conducted. However, at the stage of collecting speech data, the spread of COVID-19 prevented the collection of actual speech data. Furthermore, with the emergence of generative AI, the significance of the original research objective was greatly diminished. Based on the evaluation criteria research up to that point, the focus shifted to research on English education in the era of generative AI and the neuroscientific study of in-person education. This research achieved certain results through the application of generative AI in English education and presentations at international symposiums.
|
| Academic Significance and Societal Importance of the Research Achievements |
英語スピーキングの評価基準に関する分析に基づき，どのような点を指導，改善すれば英語運用能力の向上させることができるのかについての研究を行ってきた．当初は，自動評価用のシステムの学習に用いる発話データを構築する予定であったが，コロナ禍を挟んで生成AIの急速な発展により，学習用データそのものの必然性が低下した．そこで，評価のあり方を中心とする研究を進めることとなった．その研究の知見を活かし，生成AI時代に必要となる英語教育についての考察を深めることができた．これらの考察は，今後の英語教育に対する指針を示すことができた点で，学術的，社会的に果たした意義は大きいと考えられる．
|
