Presentation 2016-01-18
Extraction of Locative Words in Novels using NGD
Igarashi Hiakru, Kamioka Eiji,
PDF Download Page PDF download Page Link
Abstract(in Japanese) (See Japanese page)
Abstract(in English) When reading a novel, sometimes it is difficult to comprehend a scene because the expression is complicated. In such a case, illustrations as seen in juvenile novels help the readers to understand the scene. This study pays attention to the background image of an illustration since it directly shows the novel scene to the readers, and then proposes a method to automatically extract location words such as school, station and so on from tons of words used in the novel. In this paper, three methods to extract the location words using NGD, Word2Vec and the hit number of searches will be explained. Furthermore, the accuracy of the extraction and the validation of the categorization will be discussed.
Keyword(in Japanese) (See Japanese page)
Keyword(in English) NGD / Word2Vec / MeCab / Morphological Analysis
Paper # EMM2015-67
Date of Issue 2016-01-11 (EMM)

Conference Information
Committee EMM
Conference Date 2016/1/18(2days)
Place (in Japanese) (See Japanese page)
Place (in English) Katahira Campus, Tohoku University
Topics (in Japanese) (See Japanese page)
Topics (in English) Sense of Presence, Universal Media, Digital Entertainment, etc.
Chair Akinori Ito(Tohoku Univ.)
Vice Chair Masashi Unoki(JAIST) / Masaki Kawamura(Yamaguchi Univ.)
Secretary Masashi Unoki(Univ. of Electro-Comm.) / Masaki Kawamura(Nagasaki Univ.)
Assistant Motoi Iwata(Osaka Pref. Univ.) / Kazuhiro Kohno(Kansai Univ.)

Paper Information
Registration To Technical Committee on Enriched MultiMedia
Language JPN
Title (in Japanese) (See Japanese page)
Sub Title (in Japanese) (See Japanese page)
Title (in English) Extraction of Locative Words in Novels using NGD
Sub Title (in English)
Keyword(1) NGD
Keyword(2) Word2Vec
Keyword(3) MeCab
Keyword(4) Morphological Analysis
1st Author's Name Igarashi Hiakru
1st Author's Affiliation Shibaura Institute Of Technology(SIT)
2nd Author's Name Kamioka Eiji
2nd Author's Affiliation Shibaura Institute Of Technology(SIT)
Date 2016-01-18
Paper # EMM2015-67
Volume (vol) vol.115
Number (no) EMM-397
Page pp.pp.37-42(EMM),
#Pages 6
Date of Issue 2016-01-11 (EMM)