A4 Vertaisarvioitu artikkeli konferenssijulkaisussa

Text-to-Text Automatic Story Generation: A Survey;



Tekijät: Ma, Yuan; Susilo, Richard; Haslum, Patrik; Suominen, Hanna

Toimittaja: Santamaria, Selene Baez; Somayajula, Sai Ashish; Yamaguchi, Atsuki

Konferenssin vakiintunut nimi: European Chapter of the Association for Computational Linguistics

Kustantaja: Association for Computational Linguistics

Julkaisuvuosi: 2026

Kokoomateoksen nimi: Proceedings of the 19th Conference of the European Chapter of the Association for Computational Linguistics : (Volume 4: Student Research Workshop)

Aloitussivu: 514

Lopetussivu: 527

ISBN: 979-8-89176-383-8

DOI: https://doi.org/10.18653/v1/2026.eacl-srw.39

Julkaisun avoimuus kirjaamishetkellä: Avoimesti saatavilla

Julkaisukanavan avoimuus : Kokonaan avoin julkaisukanava

Verkko-osoite: https://doi.org/10.18653/v1/2026.eacl-srw.39

Rinnakkaistallenteen osoite: https://research.utu.fi/converis/portal/detail/Publication/527033444

Rinnakkaistallenteen lisenssi: CC BY

Rinnakkaistallennetun julkaisun versio: Kustantajan versio


Tiivistelmä
Automatic story generation aims to produce coherent, engaging, and contextually consistent narratives with minimal or no human involvement, thereby advancing research in computational creativity and applications in human language technologies. The emergence of large language models has progressed the task, enabling systems to generate multi-thousandword stories under diverse constraints. Despite these advances, maintaining narrative coherence, character consistency, storyline diversity, and plot controllability in generating stories is still challenging. In this survey, we conduct a systematic review of research published over the past four years to examine the major trends and key limitations in story generation methods, model architectures, datasets, and evaluation methodologies. Based on this analysis of 57 included papers, we propose developing new evaluation metrics and creating more suitable datasets, together with ongoing improvement of narrative coherence and consistency, as well as their exploration in practical applications of story generation, as actions to support continued progress in automatic story generation.

Ladattava julkaisu

This is an electronic reprint of the original article.
This reprint may differ from the original in pagination and typographic detail. Please cite the original version.

Julkaisussa olevat rahoitustiedot: 
We thank The Australian National University (ANU) and the ANU School of Computing for supporting the PhD studies of the first two authors.


Last updated on