JSAI2018

Presentation information

Oral presentation

Organized Session » [Organized Session] OS-11

[1B2-OS-11b] [Organized Session] OS-11

Tue. Jun 5, 2018 3:20 PM - 4:40 PM Room B (4F Moon Light)

3:20 PM - 3:40 PM

[1B2-OS-11b-01] Development of Automatic Haiku Generator Using LSTM

〇Koki Yoneda1, Soichiro Yokoyama2, Tomohisa Yamashita2, Hidenori Kawamura2 (1. School of Engineering Hokkaido University, 2. Graduate School of Information Science and Technology, Hokkaido University)

Keywords:AI, Haiku, Deep Learning

The creation of art using deep learning has been paid attention to in recent years.
Also, there is a haiku as an art that has long been popular in Japan.
In this research, we demonstrate the usefulness of deep learning as art creation by making haiku from motifs, which is a general method of creating haikus, using deep learning.
First, we train LSTM based on a large amount of past haiku, let it generate a stringa.
Second, we extract the ones that satisfy the condition as a haiku from the generated character string and calculate
the evaluation value as to whether it fits the motif image or not.
If the evaluation value is high, it is assumed that the generated haiku matches the motif image.
In this process, we conducted an experiment to confirm whether LSTM was able to learn rules as a haiku.