I’ll be presenting our work ✨VocADT, tomorrow at #ICLR2025
Check out our poster session: iclr.cc/virtual/2025...
🗓️Thu 24 Apr 3 p.m. - 5:30 p.m
📍Hall 3 + Hall 2B #250
So excited to be attending @iclr_conf in Singapore 🇸🇬!

VocADT - a h-j-han Collection Adapters for Altering LLM Vocabularies: What Languages Benefit the Most? at ICLR2025

Check out our paper: arxiv.org/abs/2410.09644
Github: github.com/h-j-han/VocADT
Huggingface 🤗 Models: huggingface.co/collections/...

Accepted at #ICLR2025✨

🧐Which languages benefit the most from vocabulary adaptation?

We introduce VocADT, a new vocabulary adaptation method with a vocabulary adapter.
We explore the impact of various adaptation strategies on languages with diverse scripts and fragmentation to answer this question

starter pack for the Computational Linguistics and Information Processing group at the University of Maryland - get all your NLP and data science here!

go.bsky.app/V9qWjEi

Awesome starter pack! Thank you👍

👍

Wow nice picture!

SpeechQE: Estimating the Quality of Direct Speech Translation HyoJung Han, Kevin Duh, Marine Carpuat. Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing. 2024.

Estimating translation quality is key to building trustworthy machine translation systems, but most work focuses on text. How well can we assess *speech* translation? 🎤
Check out our 𝐒𝐩𝐞𝐞𝐜𝐡𝐐𝐄 💬 paper with Hyojung Han and Kevin Duh at #EMNLP2024!
aclanthology.org/2024.emnlp-m...