TaleBrush: Sketching Stories with Generative Pretrained Language Models

被引：78

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

页数：19

共 50 条

[31] Practical Takes on Federated Learning with Pretrained Language Models
Agarwal, Ankur
Rezagholizadeh, Mehdi
Parthasarathi, Prasanna
17TH CONFERENCE OF THE EUROPEAN CHAPTER OF THE ASSOCIATION FOR COMPUTATIONAL LINGUISTICS, EACL 2023, 2023, : 454 - 471
[32] Data Augmentation for Spoken Language Understanding via Pretrained Language Models
Peng, Baolin
Zhu, Chenguang
Zeng, Michael
Gao, Jianfeng
INTERSPEECH 2021, 2021, : 1219 - 1223
[33] Can Pretrained Language Models (Yet) Reason Deductively?
Yuan, Zhangdie
Hu, Songbo
Vulic, Ivan
Korhonen, Anna
Meng, Zaiqiao
17TH CONFERENCE OF THE EUROPEAN CHAPTER OF THE ASSOCIATION FOR COMPUTATIONAL LINGUISTICS, EACL 2023, 2023, : 1447 - 1462
[34] Unlocking Multimedia Capabilities of Gigantic Pretrained Language Models
Li, Boyang
PROCEEDINGS OF THE 1ST WORKSHOP ON LARGE GENERATIVE MODELS MEET MULTIMODAL APPLICATIONS, LGM3A 2023, 2023, : 3 - 4
[35] A Survey of Sentiment Analysis Based on Pretrained Language Models
Sun, Kaili
Luo, Xudong
Luo, Michael Y.
2022 IEEE 34TH INTERNATIONAL CONFERENCE ON TOOLS WITH ARTIFICIAL INTELLIGENCE, ICTAI, 2022, : 1239 - 1244
[36] Large Product Key Memory for Pretrained Language Models
Kim, Gyuwan
Jung, Tae-Hwan
FINDINGS OF THE ASSOCIATION FOR COMPUTATIONAL LINGUISTICS, EMNLP 2020, 2020, : 4060 - 4069
[37] A study of Turkish emotion classification with pretrained language models
Ucan, Alaettin
Dorterler, Murat
Akcapinar Sezer, Ebru
JOURNAL OF INFORMATION SCIENCE, 2022, 48 (06) : 857 - 865
[38] Masking as an Efficient Alternative to Finetuning for Pretrained Language Models
Zhao, Mengjie
Lin, Tao
Mi, Fei
Jaggi, Martin
Schutze, Hinrich
PROCEEDINGS OF THE 2020 CONFERENCE ON EMPIRICAL METHODS IN NATURAL LANGUAGE PROCESSING (EMNLP), 2020, : 2226 - 2241
[39] Probing Pretrained Language Models for Semantic Attributes and their Values
Beloucif, Meriem
Biemann, Chris
FINDINGS OF THE ASSOCIATION FOR COMPUTATIONAL LINGUISTICS, EMNLP 2021, 2021, : 2554 - 2559
[40] Topic Classification for Political Texts with Pretrained Language Models
Wang, Yu
POLITICAL ANALYSIS, 2023, 31 (04) : 662 - 668

← 1 2 3 4 5 →