🚨 NLP4DH 2026 deadline has been extended to March 13! Submission link here: openreview.net/group?id=NLP...

A photo of the city Albuquerque in the distance.

Bye, Albuquerque! Attending NAACL was a blast & releasing 71k literary social networks with @rmmhicke.bsky.social, @dmimno.bsky.social, and @mattwilkens.bsky.social at NLP4DH was well received. Excited to see folks use it!

Data → github.com/srhm-ca/pgn
Paper → aclanthology.org/2025.nlp4dh-...

Happy 2024! I wrote a retrospective on early AI research to finish off 2023: srhm.ca/revisiting_t... — writing it brought me to archive.org/details/bits... which is a treasure trove of early documents on AI research at MIT. Worth checking!

Cool! I've seen things like this before and think it's very promising. I wonder if there's value in some utility to make sure changes are under some information threshold—to make sure it can only adjust so many characters, etc.

A few weeks back I put together a small website for embedding and ranking documents in-browser. Svelte is pretty nice! srhm-ca.github.io/docplot/

Using cross-entropy loss to measure the space of narrative entropy is neat. Another good article to throw on to the pile is arxiv.org/pdf/2103.128... from the EleutherAI folk

Hey! Glad to see @dbamman.bsky.social using semantic tags for annotation. I've been using them as well. They're especially nice when you constrain output with a CFG: github.com/ggerganov/ll...