Wordcraft: a Human-AI Collaborative Editor for Story Writing

By Andy Coenen, Luke Davis, Daphne Ippolito, Emily Reif, Ann Yuan. 2021

94 citations recorded by the source corpus.

As neural language models grow in effectiveness, they are increasingly being applied in real-world settings. However these applications tend to be limited in the modes of interaction they support. In this extended abstract, we propose Wordcraft, an AI-assisted editor for story writing in which a writer and a dialog system collaborate to write a story. Our novel interface uses few-shot learning and the natural affordances of conversation to support a variety of interactions. Our editor provides a sandbox for writers to probe the boundaries of transformer-based language models and paves the way for future human-in-the-loop training pipelines and novel evaluation methods.

Subfields: Artificial Intelligence, Computer Vision and Pattern Recognition, 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

1. Vishakh Padmakumar
2. Vipul Raheja
3. Zae Myung Kim
4. Hengxing He
5. Dongyeop Kang
6. Tuhin Chakrabarty

In Computer Vision and Pattern Recognition

1. Vishakh Padmakumar
2. Hengxing He
3. Dongyeop Kang
4. Tuhin Chakrabarty

Citations in the corpus

• Emergent Abilities of Large Language Models (2022, neutral): “…via prompting to translate natural language instructions into actions executable by robots (Ahn et al., 2022; Huang et al., 2022), interact with users (Coenen et al., 2021; Wu et al., 2021; 2022a; Lee et al., 2022b), and facilitate multi-modal reasoning (Zeng et al., 2022; Alayrac et al., 2022).”
• Help me write a Poem - Instruction Tuning as a Vehicle for Collaborative Poetry Writing (2022, background): “Unlike most of the recent work that prompts large language models to elicit content Coenen et al. (2021) frame collaborative writing as a conversation between a human and a LLM-based dialog system and show how the spontaneous utilities of conversation support a variety of interactions.”
• Read, Revise, Repeat: A System Demonstration for Human-in-the-loop Iterative Text Revision (2022, background): “While some prior works on text revision (Coenen et al., 2021; Padmakumar and He, 2021; Gero et al., 2021; Lee et al., 2022) have proposed humanmachine collaborative writing interfaces, they are”