Creative Writing with a Machine in the Loop: Case Studies on Slogans and Stories

By Elizabeth Clark, A. S. Ross, Chenhao Tan, Yangfeng Ji, Noah A. Smith. 2018

315 citations recorded by the source corpus.

Subfields: Artificial Intelligence, Computer Vision and Pattern Recognition, Information Systems, Natural Language Generation, Human-Computer Interaction

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

In Computer Vision and Pattern Recognition

In Information Systems

In Natural Language Generation

In Human-Computer Interaction

Citations in the corpus

PowerTransformer: Unsupervised Controllable Revision for Biased Language Correction (2020, methodology): “Such controllable revision methods could be used to help reshape how gender roles are portrayed in media (e.g., through machine-in-the-loop writing systems; Clark et al., 2018).”
CoAuthor: Designing a Human-AI Collaborative Writing Dataset for Exploring Language Model Capabilities (2022, background): “The most traditional approach is contextual inquiry, inviting writers to write with an LM and interviewing them afterward [10, 14, 26, 63, 64, 66].”
Comparison of Diverse Decoding Methods from Conditional Language Models (2019, background): “For example, in collaborative story generation, the system makes suggestions to a user for what they should write next (Clark et al., 2018).”
Adhering, Steering, and Queering: Treatment of Gender in Natural Language Generation (2020, background): “For example, research is exploring automatically generated stories (e.g., [15, 33]) and news articles (e.g., [34]).”
Help me write a Poem - Instruction Tuning as a Vehicle for Collaborative Poetry Writing (2022, background): “However, model suggestions of this autocomplete nature were not always helpful, as they often diverged from the user intent (Clark et al., 2018) resulting in only a fraction of generated text being retained (Akoury et al., 2020).”
Does the Whole Exceed its Parts? The Effect of AI Explanations on Complementary Team Performance (2020, background): “ful in many scenarios: communicating model predictions [17, 30, 33, 56], teaching humans tasks like translation [48] or content moderation [28], augmenting human analysis procedure [28] or creativity [14], legal imperatives [51, 64], and others. An assumption underlying all these case is that a huma”
Co-Writing Screenplays and Theatre Scripts with Language Models: Evaluation by Industry Professionals (2022, methodology): “Each question was answered on a 5-point Likert-type scale, using questions adapted from [22, 58, 80, 108, 125].”
Choose Your Own Adventure: Paired Suggestions in Collaborative Writing for Evaluating Story Generation Models (2021, methodology): “To allow the writers control over the story while still encouraging them to use the suggestions, C YO A uses a turn-taking writing process, with writers alternating between writing by themselves and then receiving suggestions to continue the story (Swanson and Gordon, 2012; Clark et al., 2018).”
Wordcraft: Story Writing With Large Language Models (2022, background): “al [12], the authors present a system that generates revisions to users tasked with writing slogans.”
The Principles and Limits of Algorithm-in-the-Loop Decision Making (2019, background): “In the context of algorithm-assisted human decision making, prior research has explored topics such as what interactions can facilitate the development of machine learning models [9, 29, 47], how to improve human performance with an algorithm’s assistance [12, 37, 48], and the ways in which laypeopl”
Towards Facilitating Empathic Conversations in Online Mental Health Support: A Reinforcement Learning Approach (2021, background): “An important way in which the task of empathic rewriting can be used is for providing feedback and training to people through machine-in-the-loop writing systems [9, 58].”
STORIUM: A Dataset and Evaluation Platform for Machine-in-the-Loop Story Generation (2020, background): “This allows story authors to query a machine (Clark et al., 2018) for suggestions during the process of writing their own stories.”
Gender and Representation Bias in GPT-3 Generated Stories (2021, background): “Advances in large language models have allowed new possibilities for their use in storytelling, such as machine-in-the-loop creative writing (Clark et al., 2018; Kreminski et al., 2020; Akoury et al., 2020) and narrative generation for games (Raley and Hua, 2020).”
Human-AI Co-Creation in Songwriting (2020, background): “For example, an AI might add to a user’s drawing [21, 50], alternate writing sentences of a story with a human [14], or auto-complete missing parts of a user’s music composition [4,34,38,45].”
Novice-AI Music Co-Creation via AI-Steering Tools for Deep Generative Models (2020, background): “For example, an AI might ﬂesh out a half-sketched drawing [36], write the next paragraph of a story [7], or add an image to a design mood board [33].”
Teachers’ AI digital competencies and twenty-first century skills in the post-pandemic world (2023, background): “Educators should incorporate learning activities and assessments for students to create content through creative writing (Clark et al., 2018), music composition (Lopez-Rincon et al., 2018) and stylising painting (Hertz-mann, 2018).”
Towards a Science of Human-AI Decision Making: A Survey of Empirical Studies (2021, methodology): “Deep learning models Convolution Neural Networks [3, 27], Recurrent Neural Networks [26, 60], BERT [80], RoBERTa [13], VQA model (hybrid LSTM and CNN) [115], not specified [23, 24, 30, 48, 50, 52, 62, 73, 86, 87, 107, 110, 152]”