| Presentation | 2016-09-08 Discrimination of Manyo-shu and Kokin-Waka-shu and Dating of Poets using Machine Learning Kazuhisa Noguchi, Akira Aiba, Sachio Hirokawa, |
|---|---|
| PDF Download Page |  PDF download Page Link |
| Abstract(in Japanese) | (See Japanese page) |
| Abstract(in English) | Manyo-Shu and Kokinwaka-Shu are famous anthologies of Japanese poetry (Waka-Shu). They have different background and different compilation history. It is well known that they have many different features such as contents and rhetoric. This paper consider the discrimination of the two Waka-Shu by applying machine learning method SVM (support vector machine). Moreover, this paper proposes to use the predicted score (SVM score) of poetry for dating a poet. We confirmed that 60 feature words are enough to gain 86% prediction performance. We obtained a regression formula y = -2.37477 * x + 805.6495 to guess the year y of a poet whose SVM score is x. |
| Keyword(in Japanese) | (See Japanese page) |
| Keyword(in English) | Machine Learning / SVM / Feature Selection / WAKA / Mannyo-shu / Kokin-shu / Dating |
| Paper # | NLC2016-14 |
| Date of Issue | 2016-09-01 (NLC) |
| Conference Information | |
| Committee | NLC |
|---|---|
| Conference Date | 2016/9/8(2days) |
| Place (in Japanese) | (See Japanese page) |
| Place (in English) | Convention Room AP Shibuya-Dogenzaka (Tokyo) |
| Topics (in Japanese) | (See Japanese page) |
| Topics (in English) | The Ninth Text Mining Symposium |
| Chair | Hiroshi Kanayama(IBM) |
| Vice Chair | Makoto Ichise(NTT DoCoMo) / Takeshi Sakaki(Univ. of Tokyo/Hottolink) |
| Secretary | Makoto Ichise(Ryukoku Univ.) / Takeshi Sakaki(Kyushu Inst. of Tech.) |
| Assistant | Ryuichiro Higashinaka(NTT) / Mitsuo Yoshida(Toyohashi Univ. of Tech.) |
| Paper Information | |
| Registration To | Technical Committee on Natural Language Understanding and Models of Communication |
|---|---|
| Language | JPN |
| Title (in Japanese) | (See Japanese page) |
| Sub Title (in Japanese) | (See Japanese page) |
| Title (in English) | Discrimination of Manyo-shu and Kokin-Waka-shu and Dating of Poets using Machine Learning |
| Sub Title (in English) | |
| Keyword(1) | Machine Learning |
| Keyword(2) | SVM |
| Keyword(3) | Feature Selection |
| Keyword(4) | WAKA |
| Keyword(5) | Mannyo-shu |
| Keyword(6) | Kokin-shu |
| Keyword(7) | Dating |
| 1st Author's Name | Kazuhisa Noguchi |
| 1st Author's Affiliation | Kyushu University(Kyushu Univ.) |
| 2nd Author's Name | Akira Aiba |
| 2nd Author's Affiliation | Shibaura Institute of Technology(Shibaura Inst. of Tech.) |
| 3rd Author's Name | Sachio Hirokawa |
| 3rd Author's Affiliation | Kyushu University(Kyushu Univ.) |
| Date | 2016-09-08 |
| Paper # | NLC2016-14 |
| Volume (vol) | vol.116 |
| Number (no) | NLC-213 |
| Page | pp.pp.7-11(NLC), |
| #Pages | 5 |
| Date of Issue | 2016-09-01 (NLC) |