Phoebe Mulcaire
@PhoebeNLP
Followers
212
Following
329
Media
2
Statuses
31
Machine learning at @duolingo. Multilingual structured prediction and language modeling.
Joined July 2018
RT @klintonbicknell: Duolingo AI is hiring new PhDs and PhD interns! Come define the future of AI-driven education!. (New PhDs must graduat….
0
80
0
my influence is subtle, but inescapable.
0
0
1
"you must make reasonable efforts to use the latest version" in the DBRX and Gemma licenses makes it feel so dishonest to call them "open models." like, yes, you can see the weights, but they can just take away all your usage rights by publishing a broken "update".
3
0
2
RT @mattf1n: Wanna know gpt-3.5-turbo's embed size? We find a way to extract info from LLM APIs and estimate gpt-3.5-turbo’s embed size to….
0
79
0
RT @alisawuffles: LMs are increasingly large🐘 and proprietary🔒 — what if we could “tune”🔧 them without accessing their internal weights?. E….
0
83
0
RT @mayhewsw: 🚨 New Dataset Alert 🚨 I'm extremely excited to announce Universal NER v1, available now. It is gold-standard human annotati….
0
51
0
come see our poster, "Automated Evaluation of Written Discourse Coherence Using GPT-4", at the BEA workshop, today at 2:30! #ACL2023NLP
1
0
9
at #ACL2023NLP ! I'll be presenting a poster at BEA on Thursday: work with @BenNaismithELT and @JillBurstein on discourse grading with GPT-4. come say hi :).
0
2
9
RT @milesaturpin: ⚡️New paper!⚡️. It’s tempting to interpret chain-of-thought explanations as the LLM's process for solving a task. In this….
0
113
0
I'll be in Seattle from this Wednesday to next Tuesday—let me know if you'd like to meet up and say hi!.
0
0
0
RT @MaartenSap: 🌟Update🌟there's been a lot of debate of whether Theory of Mind (ToM) has emerged in new models (ChatGPT/GPT-3.5/GPT4), as p….
0
53
0
RT @nostalgebraist: wait,. what??. why do Bard AND ChatGPT *both* write an anodyne story about a young woman in idyllic "Willow Creek" at s….
0
10
0
RT @XiangLisaLi2: .We propose contrastive decoding (CD), a more reliable search objective for text generation by co….
0
119
0
RT @jwthickstun: In addition to proposing an interesting new truncation sampler, this paper draws a connection between truncation and n-gra….
0
2
0
"improves over BERT on unseen scripts" struck me as really silly but it makes sense! fascinating work.
Tired of tokenizers/subwords? Check out PIXEL, a new language model that processes written text as images📸. “Language Modelling with Pixels”. 📄 🧑💻🤖 by @rust_phillip @jonasflotz me @esalesk @mdlhx @delliott
0
0
4
I passed my defense! looking forward to starting at @duolingo this summer, working on ML for language learning.
3
2
173
RT @dginev: 📢 Welcome to Change the "X" in any arXiv article link to the "5" in ar5iv to get a modern HTML5 docume….
0
813
0
RT @wittgen_ball: We introduce 𝐁𝐢𝐝𝐢𝐦𝐞𝐧𝐬𝐢𝐨𝐧𝐚𝐥 𝐋𝐞𝐚𝐝𝐞𝐫𝐛𝐨𝐚𝐫𝐝𝐬 (𝐁𝐢𝐥𝐥𝐛𝐨𝐚𝐫𝐝𝐬), a generalization of leaderboards that simultaneously drives progres….
0
39
0
RT @nik0spapp: How can we make language models be less data-hungry? . We show that fully compositional word representations grounded on….
0
22
0