paper-with-me

홈 › Papers

Illinois Japanese \leftrightarrow English News Translation for WMT 2021

2021-11-01 · WMT (EMNLP) 2021 11 · Giang Le, Shinka Mori, Lane Schwartz

This system paper describes an end-to-end NMT pipeline for the Japanese \leftrightarrow English news translation task as submitted to WMT 2021, where we explore the efficacy of techniques such as tokenizing with language-independent and language-dependent tokenizers, normalizing by orthographic conversion, creating a politeness-and-formality-aware model by implementing a tagger, back-translation, model ensembling, and n-best reranking. We use parallel corpora provided by WMT 2021 organizers for training, and development and test data from WMT 2020 for evaluation of different experiment models. The preprocessed corpora are trained with a Transformer neural network model. We found that combining various techniques described herein, such as language-independent BPE tokenization, incorporating politeness and formality tags, model ensembling, n-best reranking, and back-translation produced the best translation models relative to other experiment systems.

📄 PDF Abstract BibTeX

Code (0)

등록된 구현이 없습니다.

Tasks

NMTRerankingTranslation

Similar Papers 제목 키워드 기반

OPPO’s Machine Translation Systems for WMT20

2020-11-01 · WMT (EMNLP) 2020 11 · Tingxun Shi, Shiyu Zhao, Xiaopu Li, Xiaoxue Wang 외

In this paper we demonstrate our (OPPO’s) machine translation systems for the WMT20 Shared Task on News Translation for all the 22 language pairs. We will give an overview of the common aspects across all the systems fir…

Machine TranslationTranslation

The NiuTrans Machine Translation Systems for WMT21

2021-09-22 · WMT (EMNLP) 2021 11 · Shuhan Zhou, Tao Zhou, Binghao Wei, Yingfeng Luo 외

This paper describes NiuTrans neural machine translation systems of the WMT 2021 news translation tasks. We made submissions to 9 language directions, including English$\leftrightarrow$$\{$Chinese, Japanese, Russian, Ice…

Knowledge DistillationMachine TranslationTranslation

Neural Machine Translation Using Extracted Context Based on Deep Analysis for the Japanese-English Newswire Task at WAT 2020

2020-12-01 · AACL (WAT) 2020 12 · Isao Goto, Hideya Mino, Hitoshi Ito, Kazutaka Kinugawa 외

This paper describes the system of the NHK-NES team for the WAT 2020 Japanese–English newswire task. There are two main problems in Japanese-English news translation: translation of dropped subjects and compatibility bet…

Machine TranslationTranslation

Neural Machine Translation System using a Content-equivalently Translated Parallel Corpus for the Newswire Translation Tasks at WAT 2019

2019-11-01 · WS 2019 11 · Hideya Mino, Hitoshi Ito, Isao Goto, Ichiro Yamada 외

This paper describes NHK and NHK Engineering System (NHK-ES){'}s submission to the newswire translation tasks of WAT 2019 in both directions of Japanese→English and English→Japanese. In addition to the JIJI Corpus that w…

Machine TranslationSentenceTranslation

Tencent Neural Machine Translation Systems for the WMT20 News Translation Task

2020-11-01 · WMT (EMNLP) 2020 11 · Shuangzhi Wu, Xing Wang, Longyue Wang, Fangxu Liu 외

This paper describes Tencent Neural Machine Translation systems for the WMT 2020 news translation tasks. We participate in the shared news translation task on English \leftrightarrow Chinese and English \rightarrow Germa…

Data AugmentationMachine TranslationTranslation