4 papers · 1 filter
Quit While You're Ahead: Quit for Efficient Candidate Generation in Machine Translation Reranking
Guangyu Chen, Boxuan Lyu, Hidetaka Kamigaito +2
Reranking methods, such as Minimum Bayes Risk (MBR) decoding and Quality Estimation (QE) reranking, have been widely used in modern neural machine translation (NMT) to select an ou…
Rewrite to Translate, Translate to Reward: Reinforcement Learning for Source Rewriting in Machine Translation
Boxuan Lyu, Haiyue Song, Zhi Qu +3
Prior work has explored prompting large language models (LLMs) to rewrite source text before translation, with the goal of improving machine translation (MT) quality. However, we f…
Is Human Annotation Necessary? Iterative MBR Distillation for Error Span Detection in Machine Translation
Boxuan Lyu, Haiyue Song, Zhi Qu
Error Span Detection (ESD) is a crucial subtask in Machine Translation (MT) evaluation, aiming to identify the location and severity of translation errors. While fine-tuning models…
Routing by Analogy: kNN-Augmented Expert Assignment for Mixture-of-Experts
Boxuan Lyu, Soichiro Murakami, Hidetaka Kamigaito +1
Mixture-of-Experts (MoE) architectures scale large language models efficiently by employing a parametric ``router'' to dispatch tokens to a sparse subset of experts. Typically, thi…