michael ginn
@mginn.bsky.social
compling phd student @ boulder
rare languages, morphology, finite state automata
michaelginn.com
rare languages, morphology, finite state automata
michaelginn.com
Pinned
michael ginn
@mginn.bsky.social
· Nov 13
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!
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
go.bsky.app/JgneRQk
“Linguistically-motivated” techniques for data augmentation sounds good on paper, but is it worth the cost?
June 5, 2025 at 6:53 AM
“Linguistically-motivated” techniques for data augmentation sounds good on paper, but is it worth the cost?
Reposted by michael ginn
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
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
January 16, 2025 at 11:16 PM
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
Paper: arxiv.org/abs/2412.17427
Reposted by michael ginn
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.
January 13, 2025 at 1:52 AM
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?
January 8, 2025 at 8:02 AM
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
It is so refreshing to read an interesting, colorfully-written paper that isn’t hyperoptimized for reviewer preferences
January 8, 2025 at 7:56 AM
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
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
January 8, 2025 at 7:51 AM
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
Reposted by michael ginn
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
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
December 2, 2024 at 6:43 PM
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
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
Reposted by michael ginn
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/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
November 23, 2024 at 1:40 PM
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/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.
November 24, 2024 at 9:10 PM
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.
Reposted by michael ginn
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.
November 24, 2024 at 9:04 PM
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
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💪
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💪
November 23, 2024 at 6:26 AM
Interested in ML open source? There’s a great list for you
Python typing is great until you want to use any package ever
November 23, 2024 at 1:52 AM
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
November 22, 2024 at 8:53 PM
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
November 22, 2024 at 5:36 AM
Arxiv should have a comment section
November 20, 2024 at 7:16 AM
Just remade my personal website (michaelginn.com) with pure old-school HTML/CSS, and it’s honestly all you need
November 19, 2024 at 1:05 AM
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
go.bsky.app/JgneRQk
November 18, 2024 at 7:45 AM
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
go.bsky.app/JgneRQk
Attending emnlp virtually and seeing emails about the social event
November 13, 2024 at 9:02 PM
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
go.bsky.app/JgneRQk
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!
November 13, 2024 at 12:18 AM
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
go.bsky.app/JgneRQk
Has anyone made a starter pack for NLP/CL people doing linguistically-motivated research?
November 12, 2024 at 11:14 PM
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...
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
November 12, 2024 at 10:41 PM
In five minutes, I’ll be presenting (virtually) about teaching LLMs to help with endangered language documentation!
aclanthology.org/2024.finding...
aclanthology.org/2024.finding...
Reposted by michael ginn
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
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
November 12, 2024 at 12:23 PM
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
Virtual Poster Session 1 - 12 November 2024 at 15:45 ET
aclanthology.org/2024.finding...
cc @mginn.bsky.social @alexispalmer.bsky.social
#EMNLP2024
Don’t forget to come check out the hottest new thing in interlinear glossing @ EMNLP, Tuesday 2-3:30
📅 Tues. 2-3:30, Poster Session 3
🗺️GlossLM: A Massively Multilingual Corpus and Pretrained Model for Interlinear Glossed Text [EMNLP Main]
🗺️GlossLM: A Massively Multilingual Corpus and Pretrained Model for Interlinear Glossed Text [EMNLP Main]
November 12, 2024 at 6:36 AM
Don’t forget to come check out the hottest new thing in interlinear glossing @ EMNLP, Tuesday 2-3:30
Reposted by michael ginn
📢 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.🔍
November 11, 2024 at 2:30 AM
📢 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.🔍