LEALLA: Learning Lightweight Language-agnostic Sentence Embeddings with Knowledge Distillation

no code implementations • 16 Feb 2023 • Zhuoyuan Mao, Tetsuji Nakagawa

Large-scale language-agnostic sentence embedding models such as LaBSE (Feng et al., 2022) obtain state-of-the-art performance for parallel sentence alignment.

Knowledge Distillation Sentence +2

Denoising Neural Machine Translation Training with Trusted Data and Online Data Selection

no code implementations • WS 2018 • Wei Wang, Taro Watanabe, Macduff Hughes, Tetsuji Nakagawa, Ciprian Chelba

Measuring domain relevance of data and identifying or selecting well-fit domain data for machine translation (MT) is a well-studied topic, but denoising is not yet.

Denoising Machine Translation +2

An Empirical Study of Language Relatedness for Transfer Learning in Neural Machine Translation

no code implementations • PACLIC 2017 • Raj Dabre, Tetsuji Nakagawa, Hideto Kazawa

Machine Translation Transfer Learning +1

Phrase-based Machine Translation using Multiple Preordering Candidates

no code implementations • COLING 2016 • Yusuke Oda, Taku Kudo, Tetsuji Nakagawa, Taro Watanabe

In this paper, we propose a new decoding method for phrase-based statistical machine translation which directly uses multiple preordering candidates as a graph structure.

Machine Translation Translation

Efficient Top-Down BTG Parsing for Machine Translation Preordering

no code implementations • IJCNLP 2015 • Tetsuji Nakagawa

Machine Translation Translation +1