TaleBrush: Sketching Stories with Generative Pretrained Language Models

被引：57
|
作者：
Chung, John Joon Young [1 ]
Kim, Wooseok [2 ]
Yoo, Kang Min [3 ]
Lee, Hwaran [3 ]
Adar, Eytan [1 ]
Chang, Minsuk [3 ]
机构：
[1] Univ Michigan, Ann Arbor, MI 48109 USA
[2] Korea Adv Inst Sci & Technol, Daejeon, South Korea
[3] Naver AI LAB, Seongnam, South Korea
来源：
PROCEEDINGS OF THE 2022 CHI CONFERENCE ON HUMAN FACTORS IN COMPUTING SYSTEMS (CHI' 22) | 2022年
关键词：
story writing; sketching; creativity support tool; story generation; controlled generation; PLOT;
D O I：
10.1145/3491102.3501819
中图分类号：
TP [自动化技术、计算机技术];
学科分类号：
0812 ;
摘要：
While advanced text generation algorithms (e.g., GPT-3) have enabled writers to co-create stories with an AI, guiding the narrative remains a challenge. Existing systems often leverage simple turn-taking between the writer and the AI in story development. However, writers remain unsupported in intuitively understanding the AI's actions or steering the iterative generation. We introduce TaleBrush, a generative story ideation tool that uses line sketching interactions with a GPT-based language model for control and sensemaking of a protagonist's fortune in co-created stories. Our empirical evaluation found our pipeline reliably controls story generation while maintaining the novelty of generated sentences. In a user study with 14 participants with diverse writing experiences, we found participants successfully leveraged sketching to iteratively explore and write stories according to their intentions about the character's fortune while taking inspiration from generated stories. We conclude with a reflection on how sketching interactions can facilitate the iterative human-AI co-creation process.
引用
下载
收藏
页数：19
相关论文
共 50 条
  • [41] Efficient Hierarchical Domain Adaptation for Pretrained Language Models
    Chronopoulou, Alexandra
    Peters, Matthew E.
    Dodge, Jesse
    NAACL 2022: THE 2022 CONFERENCE OF THE NORTH AMERICAN CHAPTER OF THE ASSOCIATION FOR COMPUTATIONAL LINGUISTICS: HUMAN LANGUAGE TECHNOLOGIES, 2022, : 1336 - 1351
  • [42] Progressive Generation of Long Text with Pretrained Language Models
    Tan, Bowen
    Yang, Zichao
    Al-Shedivat, Maruan
    Xing, Eric P.
    Hu, Zhiting
    2021 CONFERENCE OF THE NORTH AMERICAN CHAPTER OF THE ASSOCIATION FOR COMPUTATIONAL LINGUISTICS: HUMAN LANGUAGE TECHNOLOGIES (NAACL-HLT 2021), 2021, : 4313 - 4324
  • [43] A Language for Counterfactual Generative Models
    Tavares, Zenna
    Koppel, James
    Zhang, Xin
    Das, Ria
    Solar-Lezama, Armando
    INTERNATIONAL CONFERENCE ON MACHINE LEARNING, VOL 139, 2021, 139 : 7180 - 7191
  • [44] Probing for Predicate Argument Structures in Pretrained Language Models
    Conia, Simone
    Navigli, Roberto
    PROCEEDINGS OF THE 60TH ANNUAL MEETING OF THE ASSOCIATION FOR COMPUTATIONAL LINGUISTICS (ACL 2022), VOL 1: (LONG PAPERS), 2022, : 4622 - 4632
  • [45] A Survey on Model Compression and Acceleration for Pretrained Language Models
    Xu, Canwen
    McAuley, Julian
    THIRTY-SEVENTH AAAI CONFERENCE ON ARTIFICIAL INTELLIGENCE, VOL 37 NO 9, 2023, : 10566 - 10575
  • [46] medigan: a Python']Python library of pretrained generative models for medical image synthesis
    Osuala, Richard
    Skorupko, Grzegorz
    Lazrak, Noussair
    Garrucho, Lidia
    Garcia, Eloy
    Joshi, Smriti
    Jouide, Socayna
    Rutherford, Michael
    Prior, Fred
    Kushibar, Kaisar
    Diaz, Oliver
    Lekadir, Karim
    JOURNAL OF MEDICAL IMAGING, 2023, 10 (06)
  • [47] ElitePLM: An Empirical Study on General Language Ability Evaluation of Pretrained Language Models
    Li, Junyi
    Tang, Tianyi
    Gong, Zheng
    Yang, Lixin
    Yu, Zhuohao
    Chen, Zhipeng
    Wang, Jingyuan
    Zhao, Wayne Xin
    Wen, Ji-Rong
    NAACL 2022: THE 2022 CONFERENCE OF THE NORTH AMERICAN CHAPTER OF THE ASSOCIATION FOR COMPUTATIONAL LINGUISTICS: HUMAN LANGUAGE TECHNOLOGIES, 2022, : 3519 - 3539
  • [48] Leveraging Frozen Pretrained Written Language Models for Neural Sign Language Translation
    De Coster, Mathieu
    Dambre, Joni
    INFORMATION, 2022, 13 (05)
  • [49] MeLM, a generative pretrained language modeling framework that solves forward and inverse mechanics problems
    Buehler, Markus J.
    JOURNAL OF THE MECHANICS AND PHYSICS OF SOLIDS, 2023, 181
  • [50] Application of Pretrained Large Language Models in Embodied Artificial Intelligence
    A. K. Kovalev
    A. I. Panov
    Doklady Mathematics, 2022, 106 : S85 - S90
12345