97 citations · 133 across the 9 of their papers we have counts for
8 papers · 1 filter
Metric-Construction Coupling Inflates Measured Synthetic Dialect Recovery
Hyojung Han
Korean dialect corpora are available but not redistributable: weights may be released, while reproducing training and evaluation from the underlying data cannot be. We ask how much…
SpeechQE: Estimating the Quality of Direct Speech Translation
HyoJung Han, Kevin Duh, Marine Carpuat
Recent advances in automatic quality estimation for machine translation have exclusively focused on written language, leaving the speech modality underexplored. In this work, we fo…
Adapters for Altering LLM Vocabularies: What Languages Benefit the Most?
HyoJung Han, Akiko Eriguchi, Haoran Xu +3
Vocabulary adaptation, which integrates new vocabulary into pre-trained language models, enables expansion to new languages and mitigates token over-fragmentation. However, existin…
The Prompt Report: A Systematic Survey of Prompt Engineering Techniques
Sander Schulhoff, Michael Ilie, Nishant Balepur +28
Generative Artificial Intelligence (GenAI) systems are increasingly being deployed across diverse industries and research domains. Developers and end-users interact with these syst…
Bridging Background Knowledge Gaps in Translation with Automatic Explicitation
HyoJung Han, Jordan Lee Boyd-Graber, Marine Carpuat
Translations help people understand content written in another language. However, even correct literal translations do not fulfill that goal when people lack the necessary backgrou…
Monotonic Simultaneous Translation with Chunk-wise Reordering and Refinement
HyoJung Han, Seokchan Ahn, Yoonjung Choi +3
Recent work in simultaneous machine translation is often trained with conventional full sentence translation corpora, leading to either excessive latency or necessity to anticipate…
Faster Re-translation Using Non-Autoregressive Model For Simultaneous Neural Machine Translation
Hyojung Han, Sathish Indurthi, Mohd Abbas Zaidi +5
Recently, simultaneous translation has gathered a lot of attention since it enables compelling applications such as subtitle translation for a live event or real-time video-call tr…
Data Efficient Direct Speech-to-Text Translation with Modality Agnostic Meta-Learning
Sathish Indurthi, Houjeung Han, Nikhil Kumar Lakumarapu +4
End-to-end Speech Translation (ST) models have several advantages such as lower latency, smaller model size, and less error compounding over conventional pipelines that combine Aut…