Presentation 2017-09-23
Comparative study of utilization of non-structured data for automatic generation of sentences
Hiromitsu Ota,
PDF Download Page PDF download Page Link
Abstract(in Japanese) (See Japanese page)
Abstract(in English) Several years have passed since the age of big data arrived, and the development of deep learning in recent years is remarkable. Although image processing and speech recognition benefit from it, it seems that it can not be seen in the field of connection between sentences of natural language processing and sentences. So I would like to compare and examine each method of natural sentence generation that I can pass in practice and want to find a clue to the future. 1) Markov chain, 2) automatic summarization, 3) text generation by deep learning (RNN / LSTM/ GAN).
Keyword(in Japanese) (See Japanese page)
Keyword(in English) big data / deep learning / natural language processing / connection between sentences / Markov chain / automatic summarization / RNN / LSTM
Paper # TL2017-38
Date of Issue 2017-09-16 (TL)

Conference Information
Committee TL
Conference Date 2017/9/23(1days)
Place (in Japanese) (See Japanese page)
Place (in English) Kyoto Institute of Technology
Topics (in Japanese) (See Japanese page)
Topics (in English) Theme1: language and learning, Theme 2: interpretation and translation, Theme 3: thought and language, etc.
Chair Masami Suzuki(KDDI Research)
Vice Chair Tadahisa Kondo(Kogakuin Univ.) / Chiaki Kubomura(Yamano College of Aesthetics)
Secretary Tadahisa Kondo(Kobe Gakuin Univ.) / Chiaki Kubomura(Kyoto Institute of Technology)
Assistant Nobuyuki Jincho(Waseda Univ.) / Noriaki Takada(Ferris Univ.)

Paper Information
Registration To Technical Committee on Thought and Language
Language JPN
Title (in Japanese) (See Japanese page)
Sub Title (in Japanese) (See Japanese page)
Title (in English) Comparative study of utilization of non-structured data for automatic generation of sentences
Sub Title (in English) Connection between sentence and sentence as a subject
Keyword(1) big data
Keyword(2) deep learning
Keyword(3) natural language processing
Keyword(4) connection between sentences
Keyword(5) Markov chain
Keyword(6) automatic summarization
Keyword(7) RNN
Keyword(8) LSTM
1st Author's Name Hiromitsu Ota
1st Author's Affiliation University of Air(Univ. of Air)
Date 2017-09-23
Paper # TL2017-38
Volume (vol) vol.117
Number (no) TL-218
Page pp.pp.1-6(TL),
#Pages 6
Date of Issue 2017-09-16 (TL)