Lightnews — Scholar-powered news

michael ginn

@mginn.bsky.social

910 followers 560 following 70 posts

compling phd student @ boulder rare languages, morphology, finite state automata michaelginn.com

Posts Media Videos Starter Packs

Pinned

michael ginn @mginn.bsky.social · Nov 13

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

Maria Antoniak @mariaa.bsky.social · Nov 11

Does someone want to make a Part 2 for this starter pack? I'm out of time/energy to moderate another one but there are definitely more NLP researchers out there!

Maria Antoniak @mariaa.bsky.social · Nov 4

A starter pack for #NLP #NLProc researchers! 🎉

go.bsky.app/SngwGeS

21 17

michael ginn @mginn.bsky.social · Jun 5

Find out in our new paper, which my colleague Ray Groshan will present at ACL!!

arxiv.org/abs/2506.03593

Is linguistically-motivated data augmentation worth it?

Data augmentation, a widely-employed technique for addressing data scarcity, involves generating synthetic data examples which are then used to augment available training data. Researchers have seen s...

arxiv.org

michael ginn @mginn.bsky.social · Jun 5

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

Reposted by michael ginn

Maria Valentini @mvalentini.bsky.social · Jan 16

Excited to be presenting my work with @teaywright.bsky.social at #COLING2025 next week in Abu Dhabi! Find us in poster session 6/E on Jan 22nd (11 AM in the atrium).

Paper: arxiv.org/abs/2412.17427

Measuring Contextual Informativeness in Child-Directed Text

To address an important gap in creating children's stories for vocabulary enrichment, we investigate the automatic evaluation of how well stories convey the semantics of target vocabulary words, a tas...

arxiv.org

1 3 9

michael ginn @mginn.bsky.social · Jan 14

Well isn’t the idea that the entire layer defines a high dimensional space, where each neuron is a dimension?

Reposted by michael ginn

William B. Fuckley @opinionhaver.bsky.social · Jan 13

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.

9 7 110

michael ginn @mginn.bsky.social · Jan 8

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

michael ginn @mginn.bsky.social · Jan 8

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

michael ginn @mginn.bsky.social · Jan 8

Probably doesn’t help that there is effectively an online cult promoting all of this

michael ginn @mginn.bsky.social · Jan 8

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

2 8

michael ginn @mginn.bsky.social · Dec 13

It’s interesting how they describe patches of bytes that are determined by changes in entropy, without making any reference to morphology…Zellig Harris did basically the same thing 50 years ago

Reposted by michael ginn

lecs lab @lecslab.bsky.social · Dec 2

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

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 ...

arxiv.org

1 1 1

michael ginn @mginn.bsky.social · Nov 27

Also shout-out to the morphology reviewers!

Reposted by michael ginn

Brandon Rohrer @brandonrohrer.com · Nov 23

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

7 47 210

michael ginn @mginn.bsky.social · Nov 24

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.

Joe Stacey @joestacey.bsky.social · Nov 24

Okay genius idea to improve quality of #nlp #arr reviews. Literally give gold stars to the best reviewers, visible on open review next to your anonymously ID during review process.

Here’s why it would work, and why would you should RT this fab idea:

1 6

Reposted by michael ginn

Enora @covetedfish.bsky.social · Nov 24

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.

1 4