IGA: An Intent-Guided Authoring Assistant

Abstract

While large-scale pretrained language models have significantly improved writing assistance functionalities such as autocomplete, more complex and controllable writing assistants have yet to be explored. We leverage advances in language modeling to build an interactive writing assistant that generates and rephrases text according to fine-grained author specifications. Users provide input to our Intent-Guided Assistant (IGA) in the form of text interspersed with tags that correspond to specific rhetorical directives (e.g., adding description or contrast, or rephrasing a particular sentence). We fine-tune a language model on a dataset heuristically-labeled with author intent, which allows IGA to fill in these tags with generated text that users can subsequently edit to their liking. A series of automatic and crowdsourced evaluations confirm the quality of IGA's generated outputs, while a smallscale user study demonstrates author preference for IGA over baseline methods in a creative writing task. We release our dataset, code, and demo to spur further research into AI-assisted writing. * * Most of the work done during an internship at Adobe. 1 As these systems are not open-sourced, it is unclear how exactly they are implemented.

TaleStream: Supporting Story Ideation with Trope Knowledge

“…Such generative tools, however, necessitate the right level of control [24]. While some have proposed to guide the generation with keywords [31,45,70,74], other works have proposed to use natural language prompts directly [27]. General conversational agents like ChatGPT [5] enable users to refine story generation through an iterative process and are now used by a wider audience [37].…”

Fiction-Writing Mode: An Effective Control for Human-Machine Collaborative Writing

“…Our work bears similarity to work on controllable story generation, which aims to control different attributes of stories such as the sentiments (Luo et al, 2019;Kong et al, 2021b), genres (Cho et al, 2022), intention (Sun et al, 2021), and characters (Lee and Jung, 2020;Xu et al, 2020a;Liu et al, 2020b) of stories. However, these attributes are largely unchanging throughout the story, while we focus on writing mode, a more dynamic attribute of text.…”