| Project/Area Number |
15K00382
|
|---|
| Research Category |
Grant-in-Aid for Scientific Research (C)
|
| Allocation Type | Multi-year Fund |
|---|
| Section | 一般 |
|---|
| Research Field |
Kansei informatics
|
|---|
| Research Institution | Meiji University |
|---|
Principal Investigator |
|
|---|
| Project Period (FY) |
2015-04-01 – 2019-03-31
|
| Project Status |
Completed (Fiscal Year 2018)
|
| Budget Amount *help |
¥4,550,000 (Direct Cost: ¥3,500,000、Indirect Cost: ¥1,050,000)
Fiscal Year 2017: ¥910,000 (Direct Cost: ¥700,000、Indirect Cost: ¥210,000)
Fiscal Year 2016: ¥780,000 (Direct Cost: ¥600,000、Indirect Cost: ¥180,000)
Fiscal Year 2015: ¥2,860,000 (Direct Cost: ¥2,200,000、Indirect Cost: ¥660,000)
|
|---|
| Keywords | 機械学習 / データマイニング / 感性工学 / 意思決定支援システム / 自然言語処理 / 対話システム / ディープラーニング / 行動予測 / 情報検索 |
|---|
| Outline of Final Research Achievements |
The purpose of this research is to develop a Web intelligent agent that understands the user's situation and intention as if there is a smart secretary in the machine and provides the information necessary for decision making. In order to realize this, it is important to establish an inference algorithm that estimates the user's intention. In this research, we focused on application and evaluation of agent systems using information filtering technology by natural language processing based on speech and text information, and user situation estimation technology. More specifically, research on a counseling agent who interacts based on the user's purpose comprehension and their information towards understanding the intention and understanding of intention and context based on text information, natural language using deep learning Research on processing was advanced.
|
| Academic Significance and Societal Importance of the Research Achievements |
近年ディープラーニングの発展により、画像処理や自然言語処理の研究が進んでいる。画像処理については人間を凌駕する高い性能を記録した半面、自然言語処理、とりわけ意味の理解についてはまだ課題が多い。本研究の成果である自然言語処理による意図の推定は、非常に難しい課題であるが、精度を高めていくことにより多様な応用分野での活用が期待される。
|
