JSAI2021

Presentation information

General Session

General Session » GS-5 Language media processing

[4J4-GS-6g] 言語メディア処理:応用

Fri. Jun 11, 2021 3:40 PM - 5:20 PM Room J (GS room 5)

座長:欅 惇志((株)デンソーアイティーラボラトリ)

4:40 PM - 5:00 PM

[4J4-GS-6g-04] Haiku Generation Method to Inject Sence of Surprise using Adversarial Learning

〇Ryuku Nobusue1, Masanori Akiyoshi2 (1. Keio University, 2. Kanagawa University)

Keywords:GAN, Topic Model, Sense of Surprise

In this study, we propose a Haiku generation method that injects a sense of surprise using adversarial learning.The method incorporates unexpectedness and subject clarity of the Haiku to measure these features with the topicmodel pre-trained from Wiki corpus. These features are used in the generator of GAN, where the discriminatorjudges whether such generated Haikus come from man-made or not. Evaluation is done by several questionnairesthat includes AHP, and experimental results show the proposed method has almost the same sense of surprisecompared to Haikus generated by human.

Authentication for paper PDF access

A password is required to view paper PDFs. If you are a registered participant, please log on the site from Participant Log In.
You could view the PDF with entering the PDF viewing password bellow.

Password