Little Red Riding Hood Goes Around the Globe:Crosslingual Story Planning and Generation with Large Language Models

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Razumovskaia, Evgeniia, Maynez, Joshua, Louis, Annie, Lapata, Mirella, Narayan, Shashi
Format: Preprint
Published: 2022
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866916173737623552
author Razumovskaia, Evgeniia
Maynez, Joshua
Louis, Annie
Lapata, Mirella
Narayan, Shashi
author_facet Razumovskaia, Evgeniia
Maynez, Joshua
Louis, Annie
Lapata, Mirella
Narayan, Shashi
contents Previous work has demonstrated the effectiveness of planning for story generation exclusively in a monolingual setting focusing primarily on English. We consider whether planning brings advantages to automatic story generation across languages. We propose a new task of cross-lingual story generation with planning and present a new dataset for this task. We conduct a comprehensive study of different plans and generate stories in several languages, by leveraging the creative and reasoning capabilities of large pre-trained language models. Our results demonstrate that plans which structure stories into three acts lead to more coherent and interesting narratives, while allowing to explicitly control their content and structure.
format Preprint
id arxiv_https___arxiv_org_abs_2212_10471
institution arXiv
publishDate 2022
record_format arxiv
spellingShingle Little Red Riding Hood Goes Around the Globe:Crosslingual Story Planning and Generation with Large Language Models
Razumovskaia, Evgeniia
Maynez, Joshua
Louis, Annie
Lapata, Mirella
Narayan, Shashi
Computation and Language
Previous work has demonstrated the effectiveness of planning for story generation exclusively in a monolingual setting focusing primarily on English. We consider whether planning brings advantages to automatic story generation across languages. We propose a new task of cross-lingual story generation with planning and present a new dataset for this task. We conduct a comprehensive study of different plans and generate stories in several languages, by leveraging the creative and reasoning capabilities of large pre-trained language models. Our results demonstrate that plans which structure stories into three acts lead to more coherent and interesting narratives, while allowing to explicitly control their content and structure.
title Little Red Riding Hood Goes Around the Globe:Crosslingual Story Planning and Generation with Large Language Models
topic Computation and Language
url https://arxiv.org/abs/2212.10471