iiinova — where your digital self keeps evolving

HyoJung Han @hjhan.bsky.social · 23/04/2025

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 🇸🇬!

iclr.cc

ICLR Poster Adapters for Altering LLM Vocabularies: What Languages Benefit the Most?ICLR 2025

020

HyoJung Han @hjhan.bsky.social · 22/01/2025

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

huggingface.co

VocADT - a h-j-han Collection

Adapters for Altering LLM Vocabularies: What Languages Benefit the Most? at ICLR2025

040

HyoJung Han @hjhan.bsky.social · 22/01/2025

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

271

Reposted by HyoJung Han

Hal Daumé III @haldaume3.bsky.social · 10/12/2024

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

12912

HyoJung Han @hjhan.bsky.social · 11/12/2024

Awesome starter pack! Thank you👍

010

Reposted by HyoJung Han

Marine Carpuat @marinecarpuat.bsky.social · 12/11/2024

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...

aclanthology.org

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.

261