Recent developments in natural language generation (NLG) using neural language models have brought us closer than ever to the goal of building AI-powered creative writing tools. However, most prior work on human-AI collaboration in the creative writing domain has evaluated new systems with amateur writers, typically in contrived user studies of limited scope. In this work, we commissioned 13 professional, published writers from a diverse set of creative writing backgrounds to craft stories using Wordcraft, a text editor with built-in AI-powered writing assistance tools. Using interviews and participant journals, we discuss the potential of NLG to have significant impact in the creative writing domain--especially with respect to brainstorming, generation of story details, world-building, and research assistance. Experienced writers, more so than amateurs, typically have well-developed systems and methodologies for writing, as well as distinctive voices and target audiences. Our work highlights the challenges in building for these writers; NLG technologies struggle to preserve style and authorial voice, and they lack deep understanding of story contents. In order for AI-powered writing assistants to realize their full potential, it is essential that they take into account the diverse goals and expertise of human writers.
Can we use generative NLP to suggest alternative framings of gender-based violence that make the perpetrator more visible? If you're at #ACL2023NLP in Toronto, come meet @HuiyuanLai and me at the WOAH poster session from 10:15-11:45
www.workshopononlineabuse.com
When @aaronlolo326 first got in touch to discuss collaboration, I have to admit I was alarmed by some of his suggestions. I thought, *You can't just get rid of the world model!* But I was curious to see where his ideas might lead...
I'm very excited to announce our paper on "Functional Distributional Semantics at Scale", presented today at #StarSEM2023.
If you've ever wondered how truth-conditional semantics can really work when training on a large corpus, have a look!