This applies to science and scientific writing. No amount of experiments will make up for a bad story. Don't go do all the work and then try to tell a mediocre story with the results. Michal Irani once told me that she writes the introductions to her papers long before she has

The School of Informatics @InfAtEd at the University of Edinburgh @EdinburghUni is hiring a lecturer or reader in embodied natural language processing. Apply by 31 Jan 2025 at https://t.co/caiETxTUfL

I'm looking for a PhD research intern focused on Speech/NLP to join Apple Machine Learning Research in Copenhagen, Denmark! You can apply via : https://t.co/M5Qs1fR6bK Please share with anyone who might be interested

📣 New paper! 📣 Hierarchical Indexing for Retrieval-Augmented Opinion Summarization (to appear in TACL) Discrete latent variable models are scalable and attributable, but LLMs are wayyy more fluent/coherent. Can we get the best of both worlds? (yes) 👀 https://t.co/kK5OhqTwlw

Happy to share that our paper won the @cogsci_soc computational modeling award for perception and action! #CogSci2024 @Edin_CDT_NLP

Paper with @larryniven4, Naomi Feldman, and Sharon Goldwater to appear in CogSci 2024: "A predictive learning model can simulate temporal dynamics and context effects found in neural representations of continuous speech" https://t.co/Nz4y1Rhrsh (1/7)

HRQ-VAE is now available in Pythae! Hierarchical Residual Quantization learns a recursive clustering of a dense vector space, end-to-end. And it learns more meaningful clusters than doing quantization post-hoc. 📝 Paper: https://t.co/3tu9cLBY1V 🤖 Code:

🚨New TACL paper 🚨 Can we use explicit latent variable alignment for cross-lingual transfer? Minotaur uses optimal transport for explicit alignment across languages. w/ @tomhosking, Mirella Lapata. To be presented @emnlpmeeting + @mrl2023 in-person 🇸🇬 https://t.co/PdoDPEIP97

"InDI" is our new supervised image restoration method that's (a) user-friendly (alternative) way to explain diffusion & improve it; and (b) an effective way to avoid a common pitfall of one-step inference used in non-diffusion restoration methods. https://t.co/h1smVnyGDV 1/8

Calling all Machine Learning researchers on the academic job market for 2024. 📢📢📢 Applications are invited for a full time academic position in Machine Learning in the School of Informatics at the University of Edinburgh.

@kennysmithed and I are looking for a postdoc for our ESRC project titled "Language learning, communication and the emergence of phonotactic constraints" (32 months; see link for details). Come work with us!

Tomorrow at Language Lunch @InfAtEd and in December at @emnlpmeeting: my EMNLP findings short paper with Chris Lucas on non-compositionality in sentiment! Sentiment computations largely adhere to the principle of compositionality, but ... (1/3)

My student sent me this list saying they have to improve themselves in many areas. Such a list can do more harm than good. While I appreciate author's intention to motivate one for greatness, I don't think it can be planned. But you can plan to be a "good researcher."

My son has just started calculus, and I asked him what the relationship was between the gradients of the tangent and the normal to a curve at a given point. His first reply was, "They are perpendicular." I've noticed many times that something one gains with experience ... 1/7

🚨 New paper 🚨 I’m excited to share the findings from my internship at @cohere with @max_nlp tl;dr Human feedback under-represents the factuality of LLM output, and annotators are less likely to spot factual errors in more assertive outputs! https://t.co/vGETMkW4NU

🚨 new paper 🚨 Can we train for flat minima with less catastrophic forgetting? We propose Trust Region Aware Minimization for smoothness in parameter+representations. TL;DR representations matter as much as parameters! https://t.co/SNCaglqioE w/@nsaphra @pdasigi @haopeng_nlp

In honor of TTIC's 20th anniversary, we wanted to share our story and highlight the outstanding accomplishments of our faculty, staff, and students. View a 20-year timeline of the history of TTIC: https://t.co/sxCWBCF43o

Materials for my three-hour workshop "Quantitative analysis for corpus phonetics and phonology" given last week are online. Thanks to all who attended and to @LabPhon for sponsoring! #RStats #labphon https://t.co/QdsEyJxmKg

“Make yourself be lucky!”- Alyosha Efros

We’re hiring at Linguistics and English Language @SchoolofPPLS Extra time for research in the first three years. Dream job! Especially interested in corpus/computational linguists or expertise in endangered languages, but honestly open to any area. Pls RT!