Meaning Acquisition from Interaction Data with Fisher's Exact Test
-
- OKA Natsuki
- Graduate School of Science and Technology, Kyoto Institute of Technology
-
- MASHIKO Yuya
- Graduate School of Science and Technology, Kyoto Institute of Technology Now at Cosmos Initia
-
- HAYASHIGUCHI Madoka
- Graduate School of Science and Technology, Kyoto Institute of Technology
-
- ITAMI Hideki
- Graduate School of Science and Technology, Kyoto Institute of Technology
-
- KAWAKAMI Shigeo
- School of Engineering and Design, Kyoto Institute of Technology
Bibliographic Information
- Other Title
-
- Fisherの直接法を用いたインタラクションデータからの意味学習
- Fisher ノ チョクセツホウ オ モチイタ インタラクション データ カラノ イミ ガクシュウ
Search this article
Abstract
Proposed is an algorithm that learns the meaning of action instructions and evaluation instructions through interaction with a navigator. The navigator speaks freely, which requires learning from various kinds of few data with biased frequency and error. Utilizing Fisher's exact test, the algorithm finds the pairs of a phrase and a situation which frequently cooccurs. An experiment shows that the learning accuracy improves compared to an earlier study.
Journal
-
- Journal of Japan Society for Fuzzy Theory and Intelligent Informatics
-
Journal of Japan Society for Fuzzy Theory and Intelligent Informatics 20 (4), 461-472, 2008
Japan Society for Fuzzy Theory and Intelligent Informatics
- Tweet
Keywords
Details 詳細情報について
-
- CRID
- 1390282680162942208
-
- NII Article ID
- 110006862946
-
- NII Book ID
- AA1181479X
-
- ISSN
- 18817203
- 13477986
-
- NDL BIB ID
- 9619082
-
- Text Lang
- ja
-
- Data Source
-
- JaLC
- NDL
- Crossref
- CiNii Articles
- KAKEN
-
- Abstract License Flag
- Disallowed