Hmm, so ChatGPT feels 2 puppies > 1 human life. Good to know I guess...

Excited to be presenting my first paper, co-authored with @ryandcotterell, at ACL 2023 in Toronto this July! We developed a new fast prefix parsing algorithm that can be used for language models. arxiv.org/abs/2306.02303

most recent #nlproc developments #MachineLearning

We summarized the #acl2023nlp Toronto conference for you with some poster recordings and author interviews! 👇 🎬 youtu.be/-Agcr0nawuk Featuring Szymon Tworkowski Jasivan Sivakumar Kundan Krishna (at ACL 2O25) Emanuele Bugliarello Leo Du Florian Mai Franz Nowak Paul Drm Moritz Plenz and Jay Alammar 👏

It's been a long day. Sorry.

How can we faithfully test interpretability methods in an environment that's reflective of natural language? We approach this via large-scale PCFGs from which we sample corpora that provide full control over the source distribution! I'll present this Findings work BlackboxNLP!

He did pull it off!

This guide to picking STEM majors is too good. Especially true about chemistry and feelings on safety haha

I am excited to share our #ACL2024 main paper, "What Languages are Easy to Language-Model? A Perspective from Learning Probabilistic Regular Languages". 📖 Link: arxiv.org/abs/2406.04289

✨How do LMs learn grammatical phenomena? Do they rely on co-occurrence patterns during training, or can they make grammatical judgments based on indirect evidence as well? Through Filtered Corpus Training (FiCT) we are able to answer these questions at scale! 🧵

Check out our #NAACL2024 paper showing how RNN Language Models can simulate Probabilistic Finite State Automata! arxiv.org/abs/2405.19222 With Anej Svete, Anisha Mohamed Sahabdeen, and @ryandcotterell

It was great to talk to Letitia on the AI Coffee Break channel about our research on the expressivity of LLMs. Thanks for having me on the podcast!

What if the way we communicate is shaped by a hidden harmonic rhythm? In our #ACL2025NLP paper, we explore the hypothesis that the components of the information contour of a document vary periodically, with periods that correspond to the boundaries of structural units.