X575: writing rengas with web services

TL;DR

This paper presents a software system that uses NLP web services to simulate the Japanese poetry form renga, highlighting partial success and exploring related research for future improvements.

Contribution

It introduces a novel system integrating NLP web services to generate renga, a traditional Japanese poetic form, and discusses challenges and future directions.

Findings

Partial success in satisfying classical constraints

Web services enable flexible NLP integration

Insights from related research inform future work

Abstract

Our software system simulates the classical collaborative Japanese poetry form, renga, made of linked haikus. We used NLP methods wrapped up as web services. Our experiments were only a partial success, since results fail to satisfy classical constraints. To gather ideas for future work, we examine related research in semiotics, linguistics, and computing.