paper-with-me

홈 › Papers

Evolution Strategy Based Automatic Tuning of Neural Machine Translation Systems

2017-12-01 · IWSLT 2017 12 · Hao Qin, Takahiro Shinozaki, Kevin Duh

Neural machine translation (NMT) systems have demonstrated promising results in recent years. However, non-trivial amounts of manual effort are required for tuning network architectures, training configurations, and pre-processing settings such as byte pair encoding (BPE). In this study, we propose an evolution strategy based automatic tuning method for NMT. In particular, we apply the covariance matrix adaptation-evolution strategy (CMA-ES), and investigate a Pareto-based multi-objective CMA-ES to optimize the translation performance and computational time jointly. Experimental results show that the proposed method automatically finds NMT systems that outperform the initial manual setting.

📄 PDF Abstract BibTeX

Code (0)

등록된 구현이 없습니다.

Tasks

Machine TranslationNMTTranslation

Similar Papers 제목 키워드 기반

Huawei’s Submissions to the WMT20 Biomedical Translation Task

2020-11-01 · WMT (EMNLP) 2020 11 · Wei Peng, Jianfeng Liu, Minghan Wang, Liangyou Li 외

This paper describes Huawei’s submissions to the WMT20 biomedical translation shared task. Apart from experimenting with finetuning on domain-specific bitexts, we explore effects of in-domain dictionaries on enhancing cr…

Machine TranslationTransfer LearningTranslation

Developing automatic verbatim transcripts for international multilingual meetings: an end-to-end solution

2023-09-27 · Akshat Dewan, Michal Ziemski, Henri Meylan, Lorenzo Concina 외

This paper presents an end-to-end solution for the creation of fully automated conference meeting transcripts and their machine translations into various languages. This tool has been developed at the World Intellectual …

Machine TranslationManagementSpeech-to-Text

A Quality-based Active Sample Selection Strategy for Statistical Machine Translation

2014-05-01 · LREC 2014 5 · Varvara Logacheva, Lucia Specia

This paper presents a new active learning technique for machine translation based on quality estimation of automatically translated sentences. It uses an error-driven strategy, i.e., it assumes that the more errors an au…

Active LearningMachine TranslationSentenceSentiment Analysis+1

Netmarble AI Center's WMT21 Automatic Post-Editing Shared Task Submission

2021-09-14 · Shinhyeok Oh, Sion Jang, Hu Xu, Shounan An 외

This paper describes Netmarble's submission to WMT21 Automatic Post-Editing (APE) Shared Task for the English-German language pair. First, we propose a Curriculum Training Strategy in training stages. Facebook Fair's WMT…

Automatic Post-EditingMachine TranslationMulti-Task LearningTranslation

Netmarble AI Center’s WMT21 Automatic Post-Editing Shared Task Submission

2021-11-01 · WMT (EMNLP) 2021 11 · Shinhyeok Oh, Sion Jang, Hu Xu, Shounan An 외

This paper describes Netmarble’s submission to WMT21 Automatic Post-Editing (APE) Shared Task for the English-German language pair. First, we propose a Curriculum Training Strategy in training stages. Facebook Fair’s WMT…

Automatic Post-EditingMachine TranslationMulti-Task LearningTranslation