Call from the past: This week I was contacted about k-delayed tree-local MCTAGs, a formalism I proposed with David Chiang in 2008
Sadly, both I and the field at large have moved on, but it is so nice to see that someone still gets value out of this
https://aclanthology.org/W08-2303/
#sigh #TAG #nlproc #academicChatter

Hello! My husband @trurl has been using Mastodon for a while, and I finally decided to make an account as well.

About me:

* Software engineer in #NLProc / #MachineLearning space
* #BikeCommuting (#ebike , to be exact)
* interested in local issues for #SomervilleMA and #Boston area
* I also enjoy #knitting as well as building and painting #gunpla figures

We've got a new article out

*Angst M, Müller NN, Walker V. Automated extraction of discourse networks from large volumes of media data* (open access)

https://doi.org/10.1017/nws.2025.4

As part of our sustainability.discourses project, we developed an automated method to gather and track discourse networks around urban sustainable mobility, based on media data.

The article describes the approach in detail and reports an evaluation of the internal validity (do we measure what we ourselves think we measure) of the pipeline.

tl;dnr: Automating discourse network data gathering can work well to capture broader tendencies. In many cases, it is likely not worth investing in automating data gathering to understand discourse however.

Want to see the daily updated pipeline in action? Check out the web apps and resources here: https://sustainability.discourses.ch/en/

Mobile email UIs added AI replies "on top". These popups hide draft & email, so users need to remember all info from the email while prompting & checking AI results. We've redesigned this with local responses, resulting in flexible workflows - both with & without AI. #CHI2025 #HCI #NLP #NLProc #AI

We’ve redesigned mobile email replies - with & without AI. Tap sentences while reading to enter local responses (or get suggestions). Then connect them on a usual draft screen (or let AI do just that). Result: Flexible workflows with varying speed and control. #CHI2025 preprint in comments.

Look you may say that I can’t do interesting research because it’s not tied to some specific business milestone, but I’m going to still sneak it in anyway…
And if it’s esoteric enough that my slow side-project pace won’t be scooped by some other lab with more flexibility, so much the better!
#AcademicInIndustry #AIML #NLProc #IndustryResearcher

I'm looking for the current best Vision & Language models that can be run on a modern laptop, ideally through LMStudio.

I currently have Qwen2.5-VL 7B and LLaVA 1.5 7B. Any others I should consider?

Moved all my stuff out of Dropbox (didn’t have much there), Google drive is next (but it’s a bit more messy and complicated).
I have a colleague who years back was concerned about keeping work stuff (eg paper drafts, grant proposals) on Google -we’re in #nlproc, kind of the same area as they are-, and I thought he was a bit paranoid. Now I think it’s probably best to keep our stuff closer to home instead of on US clouds. #academicChatter #europe #warOnScience