paper-with-me

Papers

Instance Weighting for Neural Machine Translation Domain Adaptation

2017-09-01 · EMNLP 2017 9 · Rui Wang, Masao Utiyama, Lemao Liu, Kehai Chen, Eiichiro Sumita

Instance weighting has been widely applied to phrase-based machine translation domain adaptation. However, it is challenging to be applied to Neural Machine Translation (NMT) directly, because NMT is not a linear model. In this paper, two instance weighting technologies, i.e., sentence weighting and domain weighting with a dynamic weight learning strategy, are proposed for NMT domain adaptation. Empirical results on the IWSLT English-German/French tasks show that the proposed methods can substantially improve NMT performance by up to 2.7-6.7 BLEU points, outperforming the existing baselines by up to 1.6-3.6 BLEU points.

📄 PDF Abstract BibTeX

Code (1)

wangruinlp/nmt_instance_weighting 공식 구현

Tasks

Domain AdaptationMachine TranslationNMTSentenceTranslation

Similar Papers 제목 키워드 기반

Cost Weighting for Neural Machine Translation Domain Adaptation

2017-08-01 · WS 2017 8 · Boxing Chen, Colin Cherry, George Foster, Samuel Larkin

In this paper, we propose a new domain adaptation technique for neural machine translation called cost weighting, which is appropriate for adaptation scenarios in which a small in-domain data set and a large general-doma…

Domain AdaptationMachine TranslationTranslation

Multi-Domain Adaptation in Neural Machine Translation with Dynamic Sampling Strategies

2022-06-01 · EAMT 2022 6 · Minh-Quang Pham, Josep Crego, François Yvon

Building effective Neural Machine Translation models often implies accommodating diverse sets of heterogeneous data so as to optimize performance for the domain(s) of interest. Such multi-source / multi-domain adaptation…

Domain AdaptationMachine TranslationTranslationUnsupervised Domain Adaptation

Sentence Weighting for Neural Machine Translation Domain Adaptation

2018-08-01 · COLING 2018 8 · Shiqi Zhang, Deyi Xiong

In this paper, we propose a new sentence weighting method for the domain adaptation of neural machine translation. We introduce a domain similarity metric to evaluate the relevance between a sentence and an available ent…

Domain AdaptationLanguage ModelingLanguage ModellingMachine Translation+2

Revisiting Simple Domain Adaptation Methods in Unsupervised Neural Machine Translation

2019-08-26 · Haipeng Sun, Rui Wang, Kehai Chen, Masao Utiyama 외

Domain adaptation has been well-studied in supervised neural machine translation (SNMT). However, it has not been well-studied for unsupervised neural machine translation (UNMT), although UNMT has recently achieved remar…

Domain AdaptationMachine TranslationTranslation

Dynamic Data Selection and Weighting for Iterative Back-Translation

2020-04-07 · EMNLP 2020 11 · Zi-Yi Dou, Antonios Anastasopoulos, Graham Neubig

Back-translation has proven to be an effective method to utilize monolingual data in neural machine translation (NMT), and iteratively conducting back-translation can further improve the model performance. Selecting whic…

Domain AdaptationMachine TranslationNMTSentence+1