We are thrilled to announce our next seminar: @si-wu.bsky.social ( @khourycollege.bsky.social , Northeastern University) "Exploring the Plurality of Language and Interpreting Multilingual Concepts" on Friday 6th November 2026, 11am CET. Details here 👉 almanach.inria.fr/seminars-en....
Si Wu @ EMNLP
@si-wu.bsky.social
PhD candidate working on NLP, computational social science, and digital humanities at Northeastern University. Psycholinguistics, translation, multimodality, art, culture. I don't check here often. Email me!
I’m at #EMNLP2026 until Oct 30, then in Paris until Nov 8! Old friends and new: if you’re in either city, happy to chat about research or just grab coffee/food/drinks/dessert! I’m also on the lookout for postdoc and industry positions, so feel free to reach out about that too!
I’m really happy to see @si-wu.bsky.social ‘s paper out now. Taking advantage of literary works, where we often have multiple very different translations, for both training and evaluation, is very exciting!
Literary works are often translated into the same language multiple times, and each translation interprets the original in its own way. How can we use these different translations to train better literary MT systems? Can synthetic references be as good as human ones?
Literary works are often translated into the same language multiple times, and each translation interprets the original in its own way. How can we use these different translations to train better literary MT systems? Can synthetic references be as good as human ones?
and here's the link to the NLP class David @dasmiq.bsky.social and I co-taught last fall. hopefully it will be helpful to people as well! siwu.io/nlp-class/
CS 6120 Natural Language Processing
siwu.io
now that a substantial proportion of my time is spent teachng, i am so grateful for people who make their lecture slides public so mine will be public too! lucy3.github.io/cs769-fall26...
UCSD Psychology is hiring!! We’re seeking a new assistant professor colleague who studies high-level human cognition, broadly construed. Please share and/or apply! apol-recruit.ucsd.edu/JPF04646
Assistant Professor in High-level Human Cognition
University of California, San Diego is hiring. Apply now!
apol-recruit.ucsd.edu
It's been gratifying to see the response to this project since we officially put it out into the world last week: www.bpl.org/news/boston-... #AI4LAM
Boston Public Library and Harvard IDI Release Open Dataset from 135 Years of Historic Newspapers
Newspapers represent one of the richest available primary sources for historical research — capturing not just major events, but births…
bpl.org
New paper accepted to #EMNLP2026 main conference! We compare worldbuilding strategies in 8,000 stories across four LLMs with a human-authored baseline from Project Gutenberg, in English and German, focusing on setting and narrative space. arxiv.org/abs/2609.02482
How LLMs Build Fictional Worlds: Setting and Narrative Space in AI-Generated Creative Storytelling
In this paper, we analyze how Large Language Models (LLMs) employ worldbuilding strategies, focusing on setting as one measurable dimension of storyworld construction. We compare 1,000 AI-generated st...
arxiv.org
Are open OCR models good enough to unlock historical knowledge? @danielvanstrien.bsky.social and I built a leaderboard using six expert-transcribed volumes from the @biodivlibrary.bsky.social sky.social. Meet FineBooks, from @hf.co and @eleutherai.bsky.social! huggingface.co/blog/fineboo...
FineBooks: are open OCR models good enough to unlock historical knowledge?
A Blog post by FineBooks on Hugging Face
huggingface.co
As an AC, I maintain my not caring that much about a given reviewer's score
"Documents are only partial records of the past" oh i will be thinking about this all day today
Editors’ Choice: The Archive is Not a Toy: The Hidden Problems of a ‘Vintage’ AI
As some may have heard me talk about at #ACL2026, I'm excited to share a new preprint on approaches to validation when using LLMs to measure concepts in social science, led by @madesai.bsky.social and @azjacobs.bsky.social !! Paper: arxiv.org/abs/2607.07915
How do embedding layer representations fare as predictors of reading times against other related predictors such as surprisal? Check out our paper 𝐏𝐫𝐨𝐛𝐢𝐧𝐠 𝐟𝐨𝐫 𝐑𝐞𝐚𝐝𝐢𝐧𝐠 𝐓𝐢𝐦𝐞𝐬 at #ACL2026 📍Oral Session C: Sun July 5, 16:00-17:30, San Diego Preprint: lnkd.in/eNcWZRjC
why did i just discover there are "for you" and "following" tabs on both x. com and bluesky, and "for you" is the source of my misery
At a coffee shop in Memphis: Customer: “What’s shakin’ bacon?” Barista: “well you know, I’m feeling like a small ball in tall grass”. Humans remain undefeated at language 🤩
The MLA AI and Research Working Group's new "AI and the Humanities: A Framework for Language and Literary Scholarship" offers questions and case studies on AI literacy, human-centered expertise, and responsibility and ethics to guide discussion and reflection. mlaai.hcommons.org/ai-and-the-h...
Permanent, full-time Lectureship in Digital Culture and Society at UCL. Closing date 28 June www.ucl.ac.uk/work-at-ucl/...
UCL – University College London
UCL is consistently ranked as one of the top ten universities in the world (QS World University Rankings 2010-2022) and is No.2 in the UK for research power (Research Excellence Framework 2021).
ucl.ac.uk
✨ it's coming ✨ NEMI 2026 will be lit. It will also be the new BU interp supergroup's debut ball. Come meet us!
The 3rd New England Mechanistic Interpretability (NEMI) Workshop
nemiconf.github.io