研究課題/領域番号 |
22K00792
|
研究種目 |
基盤研究(C)
|
配分区分 | 基金 |
応募区分 | 一般 |
審査区分 |
小区分02100:外国語教育関連
|
研究機関 | 会津大学 |
研究代表者 |
BLAKE John 会津大学, コンピュータ理工学部, 上級准教授 (80635954)
|
研究分担者 |
Pyshkin Evgeny 会津大学, コンピュータ理工学部, 上級准教授 (50794088)
|
研究期間 (年度) |
2022-04-01 – 2025-03-31
|
研究課題ステータス |
交付 (2022年度)
|
配分額 *注記 |
3,770千円 (直接経費: 2,900千円、間接経費: 870千円)
2024年度: 1,300千円 (直接経費: 1,000千円、間接経費: 300千円)
2023年度: 1,170千円 (直接経費: 900千円、間接経費: 270千円)
2022年度: 1,300千円 (直接経費: 1,000千円、間接経費: 300千円)
|
キーワード | NLG / trend descriptions / describing graphs / intelligent CALL / data series description / NLP / language generation |
研究開始時の研究の概要 |
This interactive online tool provides unlimited practice opportunities to describe graphs and charts. Students can practice at three levels: word, clause or sentence using generated practice texts. Students either fill in the gaps, complete sentence stems or draft the whole text. On completion of their practice task, they compare their answers with an automatically generated plain or colorized exemplar text. This helps learners notice patterns, which is said to be a precursor to learning.
|
研究実績の概要 |
A corpus of trend descriptions was compiled and manually analyzed to identify rhetorical patterns. The initial codebase of the description generator was created. We are still working on enabling examplars and practice descriptions to be generated at three different difficulty levels. An automated workflow incorporating AI-generated video explanations that are moderated by language experts has been trialled. A preliminary set of explanation videos has been created for piloting purposes.
|
現在までの達成度 (区分) |
現在までの達成度 (区分)
2: おおむね順調に進展している
理由
We have been able to follow our timeline set at the outset. The codebase will continue to be improved throughout the project, but the fundamental design and the core functions has been completed.
|
今後の研究の推進方策 |
A more sophisticated combination of rule-based and probabilistic parsing will be used to create a powerful NLG pipeline. This pipeline will draw on published research to provide users with access to cutting-edge research in NLG. At the end of this year, we expect to deploy an online version for testing purposes.
|