How much Chinese linguistic knowledge do large pretrained language models encode? SLING (to appear at #EMNLP2022) investigates this question and presents a high-quality dataset with 38K minimal pairs covering 9 Chinese linguistic phenomena. (1/6) 📄Paper: arxiv.org/abs/2210.11689

A new paper just came out in Cognition! It has been an incredibly amazing experience working with Rachel Ryskin and Ted Gibson, Language Lab MIT. We provide a noisy-channel explanation for the age-old linguistic illusion called “depth-charge” sentences. Check it out! 🧵1/n sciencedirect.com/science/articl…

I'm thrilled to share some good news! In Fall 2023, I'll be joining Colgate University as an Assistant Professor of Computer Science! I feel immense gratitude for everyone who has provided mentorship, friendship, and support through this process and the many that came before!

In addition to the stochastic parrots paper, what paper should someone read at the intersection of AI and bias/ethics? (Hoping for something closer to a position paper than a more technical paper documenting particular bias in models)

Hi there, does anyone know any female researcher going to EMNLP this year? I am looking for a roommate and I would really appreciate getting introduced to some potential friends! Thanks! 😊

Trying to figure out Singapore visa stuff for my students and me #EMNLP and as always it is a nightmare. Would anyone who has/ is going through this process be willing to talk through this?

Our lab will have our final external speaker for the semester on Wednesday, Nov 15, 12:30-2:00 EST. We will have Forrest Davis, presenting the talk entitled 'Neural Language Models are not Modeling Human Linguistic Behavior' -- a very compelling and evocative title! Link below!

I'm attending CoNLL and EMNLP! Looking forward to catching up with old friends and making some new ones. Happy to chat about the intersection of NLP and linguistics. Reach out if you'd like to grab coffee! #EMNLP2023 #CoNLL2023

My two awesome undergrad research students Aryaman and @anzi_wang will also be here presenting our BabyLM work at CoNLL’s poster session 1 at their first ever NLP conference! (details below) Pls stop by to say hi to them!

When humans make errors in processing certain sentences, would LLMs imitate by making similar errors or surpass humans and circumvent these errors? We take language illusions as a testing ground. See you at #CoNLL 12/06 at 11am (location: West 1)! #EMNLP2023 #EMNLP23 #emnlp 1/n

I'm at LSA. Always interested in making new friends and catching up with old ones. Happy to chat about the intersection of linguistics and NLP and/or cats. Also, presenting work on adjective acquisition and language models with Dr. Meg Gotowski on Jan 6! #LSA2024

Thank you to everyone who came to my joint talk with Forrest Davis on adjective learning. We are always happy to discuss acquisition and language models so hit us up if you want to chat #LSA2024

Would like to disseminate our new paper at #CogSci2024 with Titus von der Malsburg (Titus von der Malsburg) titled "Work Smarter...Not Harder: Efficient Minimization of Dependency Length in SOV Languages". CogSci Society Link: arxiv.org/pdf/2404.18684 A quick walk-through: 🧵 (1/n)

So thrilled to announce I got fifty (50) papers accepted to #ACL2024 like and subscribe below. Actually 0 for 1 🎉

Looking forward to #LSA2025 ! I will be there presenting work with Forrest Davis on word learning and LLMs, and work with Galia Bar-Sever and one of my students on adjective stacking and subjectivity. Woohoo! Hope to see lots of linguist friends there :)

Work with Language Processing Lab @ UChicago on processing appositive (ARCs) vs. restrictive relative clauses (RRCs) is out: doi.org/10.1111/cogs.1… ARCs typically contain side-commentary info; does a distractor in an ARC lead to an absence of agreement attraction effect? (1/8)

🚨 I am on the faculty job market this year 🚨 I will be presenting at #NeurIPS2024 and am happy to chat in-person or digitally! I work on developing AI agents that can collaborate and communicate robustly with us and each other. My work covers 3 key problems👇 1⃣ Multi-agent +

New study on LMs and discourse sensitivity! We evaluate 25 LMs on their ability to prioritize discourse-relevant info, and find that (1) smaller & dialogue-trained models align closer to human patterns, while (2) larger/instruction models overuse structural or discourse cues.