Ethan Gotlieb Wilcox
@weGotlieb
Followers
1K
Following
516
Media
40
Statuses
229
Asst. Prof. of Computational Linguistics @Georgetown. Formerly Postdoc @ETH, PhD @Harvard Ling, MIT Brain & Cog Sci. Language, Computers, Cognition.
Joined June 2012
Delighted Sasha's work using mech interp to study complex syntax constructions won an Outstanding Paper Award at EMNLP! And delighted the ACL community continues to recognize unabashedly linguistic topics like filler-gaps, and the huge potential for LMs to inform such topics!
A key hypothesis in the history of linguistics is that different constructions share underlying structure. We take advantage of recent advances in mechanistic interpretability to test this hypothesis in Language Models. New work with @kmahowald and @ChrisGPotts! 🧵👇
1
22
81
👀Ever wondered how visual information quality affects reading and language processing? Our new #EMNLP2025 paper, “Modeling Bottom-up Information Quality during Language Processing”, bridges psycholinguistics and multimodal LLMs. 🧠💡👇 https://t.co/9z7nbo8UWZ
1
3
15
Georgetown Linguistics has a dedicated Computational Linguistics PhD track, and a lively CL community on campus ( https://t.co/jAg5qLEGbc), including my faculty colleagues @complingy and Amir Zeldes
0
0
2
PICoL stands for “Psycholinguistics, Information, and Computational Linguistics,” and I encourage applications from anyone whose research interests connect with these topics!
1
0
0
I will be recruiting PhD students via Georgetown Linguistics this application cycle! Come join us in the PICoL (pronounced “pickle”) lab. We focus on psycholinguistics and cognitive modeling using LLMs. See the linked flyer for more details: https://t.co/BVHklkWcd4
1
7
31
Soon, I can already see the head Papers on pretraining, small models, cognitive modelling etc. are all welcome in the BabyLM workshop Submissions are due in the 15th of Aug direct from ARR or full papers Submission links: https://t.co/P1QuAbSdNt
1
4
12
Honored to have received a Senior Area Chair award at #ACL2025 for our Prosodic Typology paper. Huge shout out to the whole team: @CuiDing_CL, @tpimentelms, @a_stadt, @tamaregev!
4
5
57
It has also been nominated for best paper (title) based on a musical or song, although I hear competition is steep this year 🎵
1
0
3
Check out Xiulin's paper at #ACL2025 for new results on LMs learning "impossible" and typologically unattested languages!
🥳Thrilled to present our #ACL2025 paper with @t_aoyam, @yuekun_yao, and @weGotlieb on language modeling! Can LMs’ learning dynamics distinguish typologically attested from unattested and from truly impossible languages? We test this across 12 languages and find: yes, but…👀
1
0
11
To be presented at #ACL2025NLP on Wednesday, 30/7 at 11am! See Mario's great thread for more details on the paper.
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.
0
0
10
🌟🌟This paper will appear at @aclmeeting 2025! New updated version is on arXiv: https://t.co/uCYGu74nus 🌟🌟
⭐🗣️New preprint out: 🗣️⭐ “Using Information Theory to Characterize Prosodic Typology: The Case of Tone, Pitch-Accent and Stress-Accent” with @CuiDing_CL, Giovanni Acampa, @tpimentelms, @a_stadt, @tamaregev: https://t.co/uCYGu74nus
0
1
26
This project connects to some other recent papers seeking to cast typological variation in information-theoretic terms, with shout-outs to @MichaelaSocolof @postylem, @rljfutrell ( https://t.co/U2rmCNw37G) and @Julius_Steuer ( https://t.co/jfAiIjvHmA)
aclanthology.org
Julius Steuer, Johann-Mattis List, Badr M. Abdullah, Dietrich Klakow. Proceedings of the 5th Workshop on Research in Computational Linguistic Typology and Multilingual NLP. 2023.
0
0
3
⭐ ⭐This paper also makes several technical contributions to the mixed-pair mutual information estimation pipeline of Wolf et al., ( https://t.co/GMQ42JHRM8). Shout out to @CuiDing_CL for all her hard work on this aspect of the paper! ⭐⭐
aclanthology.org
Lukas Wolf, Tiago Pimentel, Evelina Fedorenko, Ryan Cotterell, Alex Warstadt, Ethan Wilcox, Tamar Regev. Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing. 2023.
1
0
3
✅In line with our prediction, we find that mutual information is higher in tonal languages than in non-tonal languages. BUT, the way one represents context is important. When full sentential context is taken into account (mBERT and mGPT), the distinction collapses.
1
0
2
🌏🌍We test this prediction by estimating mutual information in an audio dataset of 10 different languages across 6 language families. 🌏🌍
1
0
1
We propose a way to do so using …📡information theory.📡 In tonal languages, pitch reduces uncertainty about lexical identity, therefore, the mutual information between pitch contours and words should be higher.
1
0
1
🌐But there are intermediate languages, which have lexically contrastive tone, but only sporadically, making some linguists doubt the tonal/non-tonal dichotomy. So, how can we measure how “tonal” a language is? 🧐🧐
1
0
1
🌏 Different languages use pitch in different ways. 🌏 Tonal languages, like Cantonese, use it to make lexical distinctions. 📖 While others, like English, use it for other functions, like marking whether or not a sentence is a question. ❓
1
0
2
⭐🗣️New preprint out: 🗣️⭐ “Using Information Theory to Characterize Prosodic Typology: The Case of Tone, Pitch-Accent and Stress-Accent” with @CuiDing_CL, Giovanni Acampa, @tpimentelms, @a_stadt, @tamaregev: https://t.co/uCYGu74nus
2
11
46
I’ll also use this as a way to plug human-scale language modeling in the wild: This year’s BabyLM eval pipeline was just released last week at https://t.co/iuZyPt77he. For more info on BabyLM, head to
github.com
Contribute to babylm/evaluation-pipeline-2025 development by creating an account on GitHub.
0
0
3