Proceedings Article10.1145/3293663.3293666
Haiku Generation Using Gap Techniques
Takuya Ito,Jumpei Ono,Takashi Ogata +2 more
- 23 Nov 2018
- pp 93-96
4
TL;DR: From the event with the "surprise" of a haiku, the authors aim to generate a "poetic haiku," that seems at first glance to be disconnected, but has a connection in its background stories.
read more
Abstract: Haiku is the shortest type of formal poem in the world. Haiku includes a set of fragmentary elements; the selection of individual elements plays an important role in their creation. A haiku in which the connections between elements are easily understood tends to be a boring haiku. However, it is difficult to select an element whose connection to other elements is hard to understand, as there is a possibility that the haiku will be interpreted as a combination of simple elements without context. In this thesis, pay attention to the elements of the story that exists in the background of a haiku, and then generate an event from a haiku and a "surprise" for that event. From the event with the "surprise," the authors aim to generate a "poetic haiku," that seems at first glance to be disconnected, but has a connection in its background stories.
read more
Chat with Paper
AI Agents for this Paper
Find similar papers on Google Scholar, PubMed and Arxiv
Write a critical review of this paper
Analyze citations of this paper to find unaddressed research gaps
Citations
Does human-AI collaboration lead to more creative art? Aesthetic evaluation of human-made and AI-generated haiku poetry
TL;DR: In this article , the authors compared human-made and AI-generated haiku poetry, which is composed with 17 syllables and the world's shortest and clearest rules, to examine aesthetic evaluations of AI art and people's beliefs about it.
72
WakaVT: A Sequential Variational Transformer for Waka Generation
TL;DR: WakaVT as mentioned in this paper employs a sequence of latent variables, which effectively captures word-level variability in Waka data, and further proposes the fused multilevel self-attention mechanism, which properly models the hierarchical linguistic structure of Waka.
1
Haiku Generation From Narratological Perspective: A Circulation Between Haikus and Stories
Jumpei Ono,Takashi Ogata +1 more
- 01 Jan 2021
TL;DR: In this paper, the authors implemented a prototype system that has two functions: first, to produce multiple haikus from a single story, and second, to engender multiple stories from haiku.
1
•Posted Content
WakaVT: A Sequential Variational Transformer for Waka Generation.
TL;DR: WakaVT as mentioned in this paper employs a sequence of latent variables, which effectively captures word-level variability in Waka data to improve linguistic quality in terms of fluency, coherence, and meaningfulness.
References
•Book
Computational and Cognitive Approaches to Narratology
Takashi Ogata,Taisuke Akimoto +1 more
- 15 Jul 2016
TL;DR: Computational and Cognitive Approaches to Narratology discusses issues of narrative-related information and communication technologies, cognitive mechanism and analyses, and theoretical perspectives on narratives and the story generation process.
30
Haiku Generation Using Deep Neural Networks
WU Xianchao,Klyen Momo,Ito Kazushige,Chen Zhan +3 more
- 01 Jan 2017
TL;DR: A Haiku poem consists of 17 音 (on, also known as morae though often loosely translated as “syllables”) which are separated into three columns and is frequently written in a right-to-left way.
13
Surprise-Based Narrative Generation in an Automatic Narrative Generation Game
Jumpei Ono,Takashi Ogata +1 more
- 01 Jan 2018
TL;DR: An automatic narrative generation game using the method of tabletalk role playing game (TRPG) that is an analog game based on the interactive process by real humans, where a gap created through the interaction between the GM and the PLs gives various impressive effects for an interesting story or narrative, especially a kind of surprise.
5
Computational and Cognitive Approaches to Narratology from the Perspective of Narrative Generation
Takashi Ogata
- 01 Jan 2016
TL;DR: The authors surveys and discusses interdisciplinary approaches to primarily Artificial Intelligence (AI)based computational narrative or story generation systems by way of introducing cognitive science, and narratology and related literary theories.