I'm giving a talk on Stack Attention next Tuesday. If you're in Zurich, come join us! Paper link: arxiv.org/abs/2310.01749

Finally, I’ll be recruiting for Ph.D. positions in the fall 👩‍🎓👨‍🎓👩‍🎓 If you’re interested in using the tools of computer science and information theory to study how people learn and process language, feel free to reach out!

How would you test your BabyLM? We have a new and improved eval pipeline for round 2 of the BabyLM competition, but we're NOT done adding to it. If you have an idea for a new eval, reach out, open a pull request, or even submit a writeup to our new "paper track"!

Had a lot of fun presenting our spotlight paper "Stack Attention" at ICLR 2026 ! That was quite a crowd -- please reach out if we didn't get a chance to chat! openreview.net/forum?id=XVhm3…

Stop by "The Expressive Power of Chain of Thought" poster tomorrow! Wednesday 10:45am #294 iclr.cc/virtual/2024/p…

I’m at #LRECCOLING2024! I’ll have a poster on developing the first ASR dataset and the first ASR model for Kichwa, an endangered language of Ecuador, tomorrow (May 22) at Poster Area I from 5:30-7:10pm. Let’s have a chat! arxiv: arxiv.org/abs/2404.15501

What a great surprise to have found this work by ctaguchi David Chiang on the Kichwa language. As an Ecuadorian 🇪🇨, I feel very happy to see these efforts in the NLP field.

The poster session was full of fun. Thank you everyone for stopping by! I love #lreccoling #lreccoling2024 🫶

People who work on finite automata should call themselves a "no-stack engineer".

Tomorrow I’ll present my (previously published) work to create a new ASR dataset and model for Kichwa, an indigenous language of Ecuador, at AmericasNLP NAACL HLT 2025 from 2:30pm to 3:30pm! If you are still around at the workshops, come and check out my poster 😊

I'm excited to announce my new lab: UCSD's Learning Meaning and Natural Language Lab. a.k.a. LeM🍋N Lab! And 📢WE ARE RECRUITING📢 PhD students to join us in sunny San Diego in either Linguistics OR Data Science. Apply by Dec 4: connect.grad.ucsd.edu/apply/ More about the lab👇

How should computational (psycho)linguists properly apply token-level language models to the field’s inherently character-level problems? We try to bring some clarity in this new EMNLP paper 📣 Spoiler: you can (and should!) convert an LM over tokens into an LM over characters.

To appear at ICLR 2025, "Training Neural Networks as Recognizers of Formal Languages", and new benchmark, 🔥FLaRe🔥, for Formal Language Recognition! With Ghazal Khalighinejad, Anej Svete, Josef Valvoda, Ryan Cotterell, and Brian DuSell. See thread below.

📝 Our #ACL2025 paper is now on arXiv! "Information Locality as an Inductive Bias for Neural Language Models" We quantify how local predictability of a language affects the learnability by neural LMs using our metric, m-local entropy. paper: arxiv.org/abs/2506.05136

Thank you to whichever company's AI web scrapers just wantonly DDoSed my wiki into oblivion