✨ Do current neural speech models show human-like linguistic biases in speech perception? We took inspiration from classic phonetic categorization experiments to explore whether & where sensitivity to phonotactic context emerges in Wav2Vec2 models 🔍 📑 arxiv.org/abs/2407.03005

The Open Encyclopedia of Cognitive Science is now live! oecs.mit.edu OECS an online, open resource about the nature of minds—what they are, how they grow, how they interact, and how they differ from one another. At #CogSci2024? Come along to Penn II, 12.15 The MIT Press @mitpress.bsky.social

Working on #bias & #discrimination in #NLP? Passionate about integrating insights from other disciplines? Want to discuss current limitations of #LLM bias mitigation? 👋Join the workshop New Perspectives on Bias and Discrimination in Language Technology; 4&5 Nov in #Amsterdam!

So much new and exciting work -- from LLMs to VSAs -- reshapes the science of concepts. See our new Trends in Cognitive Sciences review on why vector-based models might just be what we need, and why a successful theory of human concepts no longer seems out of reach. sciencedirect.com/science/articl…

I will be presenting this work tomorrow (Thursday) at #INTERSPEECH2024, 10.00-10.40 in the Acesso room! Looking forward to discuss how we can learn from human speech science to interpret end-to-end neural speech models 💡 The paper is here: isca-archive.org/interspeech_20…

🚨 Publication Alert! #PLOSCompBio: Cracking the neural code for word recognition in convolutional neural networks dx.plos.org/10.1371/journa… We (Stanislas Dehaene @standehaene.bsky.social) have uncovered how convolutional neural networks recognize words, and the results are fascinating.

NEW PAPER! We (Najoung Kim 🫠 and I) find that training on mapping from form to meaning leads to improved hierarchical generalization.

🤖🧠NOW OUT IN PNAS🧠🤖 Language models show many surprising behaviors. E.g., they can count 30 items more easily than 29 In Embers of Autoregression, we explain such effects by analyzing what LMs are trained to do pnas.org/doi/10.1073/pn… Major updates since the preprint! 1/n

New paper out 🎉 !! Masoud and I wrote a perspective on how modern LMs and AI models can be useful for studying language acquisition in kids. Check out the open source paper in Language and Linguistics Compass: dx.doi.org/10.1111/lnc3.7… and this original thread: