no code implementations • WMT (EMNLP) 2020 • Jiwan Kim, Soyoon Park, Sangha Kim, Yoonjung Choi
This paper describes our submission to the WMT20 news translation shared task in English to Japanese direction.
no code implementations • WMT (EMNLP) 2021 • Hyojung Han, Seokchan Ahn, Yoonjung Choi, Insoo Chung, Sangha Kim, Kyunghyun Cho
Recent work in simultaneous machine translation is often trained with conventional full sentence translation corpora, leading to either excessive latency or necessity to anticipate as-yet-unarrived words, when dealing with a language pair whose word orders significantly differ.
no code implementations • Findings of the Association for Computational Linguistics 2020 • Insoo Chung, Byeongwook Kim, Yoonjung Choi, Se Jung Kwon, Yongkweon Jeon, Baeseong Park, Sangha Kim, Dongsoo Lee
Our analysis shows that for a given number of quantization bits, each block of Transformer contributes to translation quality and inference computations in different manners.