activity
20182022
most citedA Supervised Word Alignment Method based on Cross-Language Span Prediction using Multilingual BERT

6 citations · 11 across the 4 of their papers we have counts for

collaborators
Showing cs.CLShow all

6 papers · 1 filter

cs.CL2022

JParaCrawl v3.0: A Large-scale English-Japanese Parallel Corpus

Makoto Morishita, Katsuki Chousa, Jun Suzuki +1

Most current machine translation models are mainly trained with parallel corpora, and their translation accuracy largely depends on the quality and quantity of the corpora. Althoug…

cs.CL2021

Input Augmentation Improves Constrained Beam Search for Neural Machine Translation: NTT at WAT 2021

Katsuki Chousa, Makoto Morishita

This paper describes our systems that were submitted to the restricted translation task at WAT 2021. In this task, the systems are required to output translated sentences that cont…

cs.CL2020

Bilingual Text Extraction as Reading Comprehension

Katsuki Chousa, Masaaki Nagata, Masaaki Nishino

In this paper, we propose a method to extract bilingual texts automatically from noisy parallel corpora by framing the problem as a token-level span prediction, such as SQuAD-style…

cs.CL20206 cited

A Supervised Word Alignment Method based on Cross-Language Span Prediction using Multilingual BERT

Masaaki Nagata, Chousa Katsuki, Masaaki Nishino

We present a novel supervised word alignment method based on cross-language span prediction. We first formalize a word alignment problem as a collection of independent predictions…

cs.CL20195 cited

Simultaneous Neural Machine Translation using Connectionist Temporal Classification

Katsuki Chousa, Katsuhito Sudoh, Satoshi Nakamura

Simultaneous machine translation is a variant of machine translation that starts the translation process before the end of an input. This task faces a trade-off between translation…

cs.CL2018

Training Neural Machine Translation using Word Embedding-based Loss

Katsuki Chousa, Katsuhito Sudoh, Satoshi Nakamura

In neural machine translation (NMT), the computational cost at the output layer increases with the size of the target-side vocabulary. Using a limited-size vocabulary instead may c…