Enregistré dans:
Détails bibliographiques
Auteurs principaux: Huang, Tenghao, Qasemi, Ehsan, Li, Bangzheng, Wang, He, Brahman, Faeze, Chen, Muhao, Chaturvedi, Snigdha
Format: Preprint
Publié: 2023
Sujets:
Accès en ligne:https://arxiv.org/abs/2310.15079
Tags: Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
_version_ 1866917628050669568
author Huang, Tenghao
Qasemi, Ehsan
Li, Bangzheng
Wang, He
Brahman, Faeze
Chen, Muhao
Chaturvedi, Snigdha
author_facet Huang, Tenghao
Qasemi, Ehsan
Li, Bangzheng
Wang, He
Brahman, Faeze
Chen, Muhao
Chaturvedi, Snigdha
contents Storytelling's captivating potential makes it a fascinating research area, with implications for entertainment, education, therapy, and cognitive studies. In this paper, we propose Affective Story Generator (AffGen) for generating interesting narratives. AffGen introduces "intriguing twists" in narratives by employing two novel techniques-Dynamic Beam Sizing and Affective Reranking. Dynamic Beam Sizing encourages less predictable, more captivating word choices using a contextual multi-arm bandit model. Affective Reranking prioritizes sentence candidates based on affect intensity. Our empirical evaluations, both automatic and human, demonstrate AffGen's superior performance over existing baselines in generating affectively charged and interesting narratives. Our ablation study and analysis provide insights into the strengths and weaknesses of AffGen.
format Preprint
id arxiv_https___arxiv_org_abs_2310_15079
institution arXiv
publishDate 2023
record_format arxiv
spellingShingle Affective and Dynamic Beam Search for Story Generation
Huang, Tenghao
Qasemi, Ehsan
Li, Bangzheng
Wang, He
Brahman, Faeze
Chen, Muhao
Chaturvedi, Snigdha
Computation and Language
Artificial Intelligence
Machine Learning
Storytelling's captivating potential makes it a fascinating research area, with implications for entertainment, education, therapy, and cognitive studies. In this paper, we propose Affective Story Generator (AffGen) for generating interesting narratives. AffGen introduces "intriguing twists" in narratives by employing two novel techniques-Dynamic Beam Sizing and Affective Reranking. Dynamic Beam Sizing encourages less predictable, more captivating word choices using a contextual multi-arm bandit model. Affective Reranking prioritizes sentence candidates based on affect intensity. Our empirical evaluations, both automatic and human, demonstrate AffGen's superior performance over existing baselines in generating affectively charged and interesting narratives. Our ablation study and analysis provide insights into the strengths and weaknesses of AffGen.
title Affective and Dynamic Beam Search for Story Generation
topic Computation and Language
Artificial Intelligence
Machine Learning
url https://arxiv.org/abs/2310.15079