While distant reading has taught us a lot about the history of fiction, it hasn’t done much yet to explain why we keep turning pages. “Suspense” is the word we use to explain that impulse. ...
https://tedunderwood.com/2024/01/05/can-language-models-predict-the-next-twist-in-a-story/
If I'm buying a thinking process, I really need to understand what I see when I look under the hood.
Writing is a way of learning. And we can save what matters about it if we're willing to learn something ourselves.
https://tedunderwood.com/2023/07/31/we-can-save-what-matters-about-writing-at-a-price/
Large language models are valuable research assistants, especially when they refuse to follow instructions.
https://tedunderwood.com/2023/03/19/using-gpt-4-to-measure-the-passage-of-time-in-fiction/
To understand why neural language models are dangerous (and fascinating), we need to approach them as models of culture.
https://tedunderwood.com/2021/10/21/latent-spaces-of-culture/
It resembles the Library of Babel more than HAL.
https://tedunderwood.com/2021/02/02/why-sf-hasnt-prepared-us-to-imagine-machine-learning/
This blog post is loosely connected to a talk I’m giving (virtually) at the Workshop on Narrative Understanding, Storylines, and Events at the ACL. It’s an informal talk, exploring some of th...
https://tedunderwood.com/2020/07/05/how-predictable-is-fiction/
This is going to be a short, sweet, slightly-basic blog post, because I just have a simple thing to say. I was originally trained as a scholar of eighteenth- and nineteenth-century British litera...
Neural models have set a new standard for language understanding. Can they also help us reason about history?
Topic models can be valuable tools. But cultural historians should be aware that they are slightly ... curved.
https://tedunderwood.com/2018/07/26/do-topic-models-warp-time/