Lightnews — Scholar-powered news

Reposted by Adam Morgan

Liina Pylkkänen @liinapy.bsky.social · 26d

Spectacular talk by SNL Early Career Award winner Esti Blanco Elorrieta! Much NeLLab pride, congratulations Esti! 🎉🎉 #SNL2025 @snlmtg.bsky.social

1 9 47

Adam Morgan @adumbmoron.bsky.social · 25d

Excited to present this (now-published) project at the 11am poster session today. Poster C36 for the elevator version! #SNL2025

www.nature.com/articles/s44...

Decoding words during sentence production with ECoG reveals syntactic role encoding and structure-dependent temporal dynamics - Communications Psychology

Using electrical recordings taken from the surface of the brain, researchers decode what words neurosurgical patients are saying and show that the brain plans words in a different order than they are ...

www.nature.com

5 29

Adam Morgan @adumbmoron.bsky.social · Jul 31

Check it out:
📰 Paper: doi.org/10.48550/arX...
💾 Code + data: osf.io/frqbe/files
Let us know what you find!

A Scalable Pipeline for Estimating Verb Frame Frequencies Using Large Language Models

We present an automated pipeline for estimating Verb Frame Frequencies (VFFs), the frequency with which a verb appears in particular syntactic frames. VFFs provide a powerful window into syntax in bot...

doi.org

Adam Morgan @adumbmoron.bsky.social · Jul 31

There’s lots more work to be done here, including tinkering with prompts, model parameters, and extending to freely-available LLMs. In the meantime, we hope this is useful to folks and complements existing tools with something new: fast, scalable, and customizable VFF estimation.

1

Adam Morgan @adumbmoron.bsky.social · Jul 31

📌 VFFs from Gahl et al. (2004)'s manually annotated (i.e. gold-standard) VFFs
📌 against preferences for competing frames (the dative alternation and NP/SC ambiguity) 🧵6/8

Evaluating the LLM's, benepar's, and the Stanford Parser's VFF estimates by comparison to Gahl et al.'s (2004) database. The LLM produced the best fit, across 7 different verb frames.

1

Adam Morgan @adumbmoron.bsky.social · Jul 31

We benchmarked it thoroughly. The LLM consistently outperformed benepar & the Stanford Parser:
📌 300 human-annotated sentences (LLM accuracy = 79%, vs. 69% for benepar and 59% for Stanford) 🧵5/8

Accuracy for the GPT-4o (LLM) parser, Berkeley Neural Parser (benepar), and Stanford Parser on three manually-parsed verbs. The LLM consistently showed higher agreement with manual parses.

1

Adam Morgan @adumbmoron.bsky.social · Jul 31

That’s particularly exciting because existing datasets don’t scale well. They’re hard to adapt to new verbs/contexts/languages according to experimental need. Our pipeline is simple, scalable, and adaptable. We release the full code + VFF norms for 476 English verbs. 🧵4/8

1 1

Adam Morgan @adumbmoron.bsky.social · Jul 31

So we got creative and tried asking an LLM to parse a bunch of sentences. As it turns out, not only did this work, but the LLM outperformed both the Stanford Parser and the Berkeley Neural Parser (benepar), a state-of-the-art deep-learning parser trained on treebanks. 🧵3/8

1 1

Adam Morgan @adumbmoron.bsky.social · Jul 31

We needed syntactic norms for an experiment -- specifically Verb Frame Frequencies (VFFs), or how often particular verbs appear in different syntactic frames (e.g., intransitive, prepositional object, etc.). Nothing in the literature quite fit. 🧵2/8

1

Adam Morgan @adumbmoron.bsky.social · Jul 31

📊 New Preprint! A Scalable Pipeline for Estimating Verb Frame Frequencies Using Large Language Models. We introduce another unexpected use for LLMs: custom treebanks via automated corpus annotation 🧵1/8
doi.org/10.48550/arX...

A Scalable Pipeline for Estimating Verb Frame Frequencies Using Large Language Models

We present an automated pipeline for estimating Verb Frame Frequencies (VFFs), the frequency with which a verb appears in particular syntactic frames. VFFs provide a powerful window into syntax in bot...

doi.org

1 1 3

Adam Morgan @adumbmoron.bsky.social · Jun 26

Very cool opportunity here!!

Brielle Stark, PhD {she} @briellestark.bsky.social · Jun 25

I am #hiring for a #postdoc in #aphasia to join me at IU! www.linkedin.com/jobs/view/42...

Indiana University Bloomington hiring Postdoctoral Fellow in Bloomington, IN | LinkedIn

Posted 2:59:55 PM. Join a high-impact, data-rich initiative drawing on our extensive AphasiaBank corpus to advance the…See this and similar jobs on LinkedIn.

www.linkedin.com

2

Reposted by Adam Morgan

Brielle Stark, PhD {she} @briellestark.bsky.social · Jun 25

I am #hiring for a #postdoc in #aphasia to join me at IU! www.linkedin.com/jobs/view/42...

Indiana University Bloomington hiring Postdoctoral Fellow in Bloomington, IN | LinkedIn

Posted 2:59:55 PM. Join a high-impact, data-rich initiative drawing on our extensive AphasiaBank corpus to advance the…See this and similar jobs on LinkedIn.

www.linkedin.com

2 9 14

Adam Morgan @adumbmoron.bsky.social · Jun 5

Thank you, Florence!!

Adam Morgan @adumbmoron.bsky.social · Jun 5

P.S. Yes, we know, Frankenstein wasn't the monster's name. 🤣

2 6

Adam Morgan @adumbmoron.bsky.social · Jun 5

Read more here:
doi.org/10.1038/s442...
Work with my PI Adeen Flinker and our clinical team. So many thanks to labmates and everyone else who helped along the way! 🧵✂️

Decoding words during sentence production with ECoG reveals syntactic role encoding and structure-dependent temporal dynamics - Communications Psychology

Using electrical recordings taken from the surface of the brain, researchers decode what words neurosurgical patients are saying and show that the brain plans words in a different order than they are ...

doi.org

3 1 9

Adam Morgan @adumbmoron.bsky.social · Jun 5

More broadly, the field has largely assumed that the representations we study with single word production tasks are the same as those involved in sentences. By successfully using models trained on picture naming to decode words in sentences, we verify this 🔑 point. 🧵8/9

1 4

Adam Morgan @adumbmoron.bsky.social · Jun 5

These findings show that word processing doesn't always look like it does in picture naming: it depends on task demands. This complexity may even help explain why languages globally prefer placing subjects before objects! 🧵7/9

1 5

Adam Morgan @adumbmoron.bsky.social · Jun 5

We took a closer look at what was going on in prefrontal cortex. This revealed that these sustained representations traced back to different regions depending on a word's sentence position: when it was a subject, it was encoded in IFG, while MFG encoded objects. 🧵6/9

Density plots for the number of detections of subjects (left) and objects (right) during the production of subjects and objects in passive sentences, split by two prefrontal regions: IFG (top) and MFG (bottom). IFG sustained representations of subjects throughout both words while MFG sustained representations of objects.

1 5

Adam Morgan @adumbmoron.bsky.social · Jun 5

In passive sentences like "Frankenstein was hit by Dracula", we observed sustained neural activity encoding BOTH nouns simultaneously throughout the entire utterance. This was particularly true in prefrontal cortex. 🧵5/9

Decoding results from middle frontal gyrus during passive sentences showed sustained encoding of the object noun.

1 6

Adam Morgan @adumbmoron.bsky.social · Jun 5

For straightforward active sentences ("Dracula hit Frankenstein"), the brain activated words sequentially, matching their spoken order. But things changed dramatically for more complex sentences... 🧵4/9

Decoding results from sensorimotor cortex for active sentences: the subject noun is predicted above chance while it is being said, and the object noun while it is being said.

1 4

Adam Morgan @adumbmoron.bsky.social · Jun 5

We trained machine learning classifiers to identify each word's specific neural pattern. 🔑We ONLY used data from picture naming (single word production) to train the models. We then used the models to predict what word patients were saying in real time as they said sentences.🧵3

Word-specific patterns of neural activity: electrodes that selectively responded to each of the six words.

1 4

Adam Morgan @adumbmoron.bsky.social · Jun 5

We recorded brain activity directly from cortex in neurosurgical patients (ECoG) while they used 6 words in two tasks: picture naming ("Dracula") and scene description ("Dracula hit Frankenstein"). 🧵2/9

Task screenshots (picture naming: a cartoon picture of Frankenstein; scene description: cartoon image of Dracula hitting Frankenstein) and mean neural activity per word for one electrode in middle temporal gyrus.

1 4

Adam Morgan @adumbmoron.bsky.social · Jun 5

🧠 Newly out: Paper-with-a-way-too-long-name-for-social-media! How does the brain turn words into sentences? We tracked words in participants' brains while they produced sentences, and found some unexpectedly neat patterns. 🧵1/9
rdcu.be/epA1J in @commspsychol.nature.com

Decoding words during sentence production with ECoG reveals syntactic role encoding and structure-dependent temporal dynamics

Communications Psychology - Using electrical recordings taken from the surface of the brain, researchers decode what words neurosurgical patients are saying and show that the brain plans words in a...

rdcu.be

1 21 49

Adam Morgan @adumbmoron.bsky.social · Jun 4

Super proud of this! Thread to come soon…

Communications Psychology @commspsychol.nature.com · Jun 4

Using electrical recordings taken from the surface of the brain, researchers decode what words neurosurgical patients are saying and show that the brain plans words in a different order than they are ultimately spoken.
@adumbmoron.bsky.social
www.nature.com/articles/s44...

Decoding words during sentence production with ECoG reveals syntactic role encoding and structure-dependent temporal dynamics - Communications Psychology

Using electrical recordings taken from the surface of the brain, researchers decode what words neurosurgical patients are saying and show that the brain plans words in a different order than they are ...

www.nature.com

1 4 12

Adam Morgan @adumbmoron.bsky.social · Mar 29

Wow, thanks Laurel! Honestly one of the best compliments I’ve ever gotten given the quality of the other talks!

1 1