iiinova — where your digital self keeps evolving

Reposted by michael ginn

Lindia Tjuatja @lindiatjuatja.bsky.social · 06/04/2026

Really excited about this work w/ my long-time collaborators at Boulder! We address limitations in existing morphosyntactic annotation systems for digitally under-resourced languages and show how *jointly* predicting morphological segmentation helps with glossing performance

063

michael ginn @mginn.bsky.social · 06/04/2026

Excited to announce that the PolyGloss paper has been accepted to @aclmeeting.bsky.social! Previously, we trained models to help in endangered language documentation workflows by automatically predicting interlinear glosses. But real-world user studies revealed crucial issues...

153

michael ginn @mginn.bsky.social · 05/06/2025

“Linguistically-motivated” techniques for data augmentation sounds good on paper, but is it worth the cost?

100

Reposted by michael ginn

William B. Fuckley @opinionhaver.bsky.social · 13/01/2025

There’s no conspiracy to make tech products worse by AI in things, AI is just very immediately and clearly productivity enhancing to the people making tech products in a way that it isn’t necessarily to the people using them.

91107

michael ginn @mginn.bsky.social · 08/01/2025

Randomly stumbled on an arxiv paper where im pretty sure the listed affiliations are false, what would you even get out of that?

000

michael ginn @mginn.bsky.social · 08/01/2025

Been reading a lot of old-school finite-state automata papers for a project It is so refreshing to read an interesting, colorfully-written paper that isn’t hyperoptimized for reviewer preferences

010

michael ginn @mginn.bsky.social · 08/01/2025

I have very mixed feelings on the current era in tech—I started a PhD because I thought LLMs were pretty cool, but I absolutely cannot stand the disingenuous hype, insane competitiveness, and slop features that have since come with them

280

Reposted by michael ginn

lecs lab @lecslab.bsky.social · 02/12/2024

Can RAG+LLM systems help boost small models for rare languages? Find out in “Boosting the Capabilities of Compact Models in Low-Data Contexts with Large Language Models and Retrieval-Augmented Generation” by Bhargav Shandilya and @alexispalmer.bsky.social arxiv.org/abs/2410.00387

arxiv.org

Boosting the Capabilities of Compact Models in Low-Data Contexts with Large Language Models and Retrieval-Augmented Generation

The data and compute requirements of current language modeling technology pose challenges for the processing and analysis of low-resource languages. Declarative linguistic knowledge has the potential ...

111

Reposted by michael ginn

Brandon Rohrer @brandonrohrer.com · 23/11/2024

Adding my love letter to arxiv.org/pdf/2304.01315 Empirical Design in Reinforcement Learning by Andrew Patterson, Samuel Neumann, Martha White, Adam White JMLR 25 (2024) 1-63 #ReinforcementLearning These aren’t the heroes we deserve, but they are the heroes we need.

arxiv.org

721347

michael ginn @mginn.bsky.social · 24/11/2024

I’m a big proponent of an accumulating reviewer score (complementary to h-index). I think people would absolutely care about optimizing it even with no concrete incentive.

160

Reposted by michael ginn

Enora @covetedfish.bsky.social · 24/11/2024

I feel like reviewers often expect short papers to be long papers condensed into 4 pages. They should really be a venue to showcase focused and incremental work.

041

michael ginn @mginn.bsky.social · 23/11/2024

Interested in ML open source? There’s a great list for you

030

michael ginn @mginn.bsky.social · 23/11/2024

Python typing is great until you want to use any package ever

000

michael ginn @mginn.bsky.social · 22/11/2024

Just got ICL surgery (implantable lenses) and on one hand, modern medicine is incredible, but on the other hand seeing your eye get sliced open is terrifying

000

michael ginn @mginn.bsky.social · 22/11/2024

Arxiv should have a comment section

3180

michael ginn @mginn.bsky.social · 19/11/2024

Just remade my personal website (michaelginn.com) with pure old-school HTML/CSS, and it’s honestly all you need

1120

michael ginn @mginn.bsky.social · 18/11/2024

If you're an NLP researcher and haven't made it into either Starter Pack yet, please let me know! We're over halfway full at this point 😧 go.bsky.app/JgneRQk

394012

michael ginn @mginn.bsky.social · 13/11/2024

Attending emnlp virtually and seeing emails about the social event

260

michael ginn @mginn.bsky.social · 13/11/2024

Since the original NLP researchers starter pack is full, I've started a second one! Please let me know if you'd like to be added (assuming you're not in the first one). go.bsky.app/JgneRQk

21170

michael ginn @mginn.bsky.social · 12/11/2024

Has anyone made a starter pack for NLP/CL people doing linguistically-motivated research?

010

michael ginn @mginn.bsky.social · 12/11/2024

Don’t forget to come check out the hottest new thing in interlinear glossing @ EMNLP, Tuesday 2-3:30

021

Reposted by michael ginn

Boulder NLP @bouldernlp.bsky.social · 11/11/2024

📢 Check out the lineup of papers our students will be showcasing at #EMNLP2024 in Miami next week! 🌴 We'll be presenting new work on morphology, Q&A, and narratives.🔍

067

michael ginn @mginn.bsky.social · 08/11/2024

Come find Lindia at EMNLP to hear about our work on automated interlinear glossing!

030