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

michael ginn@mginn.bsky.social · 4mo ago

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...

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...

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

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

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.

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

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

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

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

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.

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 · 2y ago

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:

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.

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

Yoshitomo Matsubara@yoshitomo-matsubara.net · 2y ago

Here is a list of ML OSS & Open Source / Science enthusiasts I found on Bluesky 🦋 go.bsky.app/8MFcfXd Let me know if you find such people here! I'm still new here and probably the list misses many must-add people, so let's built it together💪

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

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

Arxiv should have a comment section

There! I went for it! (Let me know everyone if you want me to add or remove you) go.bsky.app/CUuio7g

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

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

Attending emnlp virtually and seeing emails about the social event

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 · 2y ago

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!

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

In five minutes, I’ll be presenting (virtually) about teaching LLMs to help with endangered language documentation! aclanthology.org/2024.finding...

Can we teach language models to gloss endangered languages?

Michael Ginn, Mans Hulden, Alexis Palmer. Findings of the Association for Computational Linguistics: EMNLP 2024. 2024.

aclanthology.org

3️⃣ Can we teach language models to gloss endangered languages? Virtual Poster Session 1 - 12 November 2024 at 15:45 ET aclanthology.org/2024.finding... cc @mginn.bsky.social @alexispalmer.bsky.social #EMNLP2024

Can we teach language models to gloss endangered languages?

Michael Ginn, Mans Hulden, Alexis Palmer. Findings of the Association for Computational Linguistics: EMNLP 2024. 2024.

aclanthology.org

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

Lindia Tjuatja@lindiatjuatja.bsky.social · 2y ago

📅 Tues. 2-3:30, Poster Session 3 🗺️GlossLM: A Massively Multilingual Corpus and Pretrained Model for Interlinear Glossed Text [EMNLP Main]

📢 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.🔍

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

Lindia Tjuatja@lindiatjuatja.bsky.social · 2y ago

📅 Tues. 2-3:30, Poster Session 3 🗺️GlossLM: A Massively Multilingual Corpus and Pretrained Model for Interlinear Glossed Text [EMNLP Main]