Nice one Piotr Nawrot! 👏

I can not express how grateful I am for having our paper “ALDi: Quantifying the Arabic Level of Dialectness of Text” accepted to #EMNLP2023! Special thanks to my supervisors (Walid Magdy 🇵🇸 and Sharon Goldwater) at the University of Edinburgh EdinburghNLP UKRI CDT in Natural Language Processing 🧵 (1/6)

😀Happy to share that work done with advisor Mirella Lapata on "Conversational Semantic Parsing using Dynamic Context Graphs" has been accepted at #EMNLP2023 Main conference. Code and updated paper will be released soon. EdinburghNLP UKRI CDT in Natural Language Processing EMNLP 2025

🗣️Well done Laurie Burchell & co whose research is now being used by Wikimedia to improve their language detection: diff.wikimedia.org/2023/10/24/ope… Great outcome! 👏👍 UKRI CDT in Natural Language Processing School of Informatics, The University of Edinburgh

mrinank 🍂 Our paper on the limits of human feedback was accepted too 😁 (arxiv.org/abs/2309.16349…) We should chat in Vienna! (cc Max Bartolo )

Happy to share that our paper won the CogSci Society computational modeling award for perception and action! #CogSci2024 UKRI CDT in Natural Language Processing

The calm before the storm - launch of Joint Conference between UKRI CDTs NLP & CDT in Speech and Language Technologies! Thanks to Coleman Haley , Nick Ferguson + team (NLP & SLT) for organising the two day event - and WELCOME to all SLT students/staff! School of Informatics, The University of Edinburgh

📣 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) 👀 arxiv.org/abs/2403.00435

We propose HIRO - our method learns a discrete hierarchical index over sentences, uses the index to 'retrieve' clusters of sentences containing related and popular opinions, and passes these clusters to an LLM to do the generation work.

This way, we get the best of both worlds! The encoder/indexer can focus on learning a high quality index, and the LLM deals with the generation. HIRO learns a higher quality embedding space than previous work, AND generates higher quality summaries! See paper for lots more exps

🏆 CONGRATULATIONS (🙏🇵🇸) عمرو قلج Amr Keleg et al !! 🙌School of Informatics, The University of Edinburgh

I'm trying to get a feel for what sectors or companies cognitive and computational psych grads work in after PhD. If you are or know someone in that category, please can we have a half hour chat?

If you have an MS or PhD in the #AI field, share your expertise, insights, and guidance with the next generation of AI leaders by volunteering with our Emerging Leaders in AI program! 🔗Register here: forms.gle/fmpfqG1ZcSRXy2… Questions? Email [email protected]

Ready to boost your ML/AI career or share your expertise? Join our Women in Machine Learning Mentoring Program! 🤖✨ Sign up now! Get guidance from experts and advance your career. 👩‍🏫 Mentors: Empower the next generation of ML/AI researchers. 🔗 Apply by Sept 15: Register here

This paper is finally published in TACL! Go check it out: doi.org/10.1162/tacl_a…

🏆🥳🙌Congratulations to (l-r) Dr Burchell Laurie Burchell, Dr Cardenas and Dr Moghe Nikita Moghe on their recent graduation from the UKRI CDT in NLP School of Informatics, The University of Edinburgh ! All the very best in your respective careers! 🌠 🏆

📢 CDTNLP School of Informatics, The University of Edinburgh student Eddie Ungless has created a survey on ethics resources. Anyone in UK who does research with LLMs, in academia or industry, building models or using them as tools, is eligible. Takes <10 mins. Chance to win £100 voucher. Survey: bit.ly/3FjVslT

TLDR; We are kindly inviting you to participate in our survey—running till the 9th of July—related to Arabizi (sometimes referred to as Arabish or Franco-Arabic): edinburghinformatics.eu.qualtrics.com/jfe/form/SV_8p… (🙏🇵🇸) عمرو قلج Amr Keleg Ahmed Amine Taha Yassine Imane Guellil Chadi Helwe 🇱🇧 🇫🇷 Nedjma Ousidhoum نجمة أوسيدهم (1/3) 🧵