| Budget Amount *help |
¥17,160,000 (Direct Cost: ¥13,200,000、Indirect Cost: ¥3,960,000)
Fiscal Year 2017: ¥3,900,000 (Direct Cost: ¥3,000,000、Indirect Cost: ¥900,000)
Fiscal Year 2016: ¥4,420,000 (Direct Cost: ¥3,400,000、Indirect Cost: ¥1,020,000)
Fiscal Year 2015: ¥4,160,000 (Direct Cost: ¥3,200,000、Indirect Cost: ¥960,000)
Fiscal Year 2014: ¥4,680,000 (Direct Cost: ¥3,600,000、Indirect Cost: ¥1,080,000)
|
|---|
| Outline of Final Research Achievements |
The purpose of this research is to analyze diversity of millions of cooking recipes that are reachable on the Web. In this study, we developed a method to extract the procedural structure from the recipe procedural description by natural language processing technology and analyze the diversity of recipe collection. We annotated Japanese and English recipes for 400 each and constructed Japanese and English recipe corpora. The recognition accuracies of recipe named entity reached 92.6% of F0 in Japanese and 87.2% of F0 in English. Moreover, the estimation accuracy of dependencies between recipe named entities achieved 79.7% of F0 in Japanese and 76.2% of F0 in English. These tools are available online and are used by many research institutes.
|
