paper-with-me

홈 › Papers

Tagged Back-Translation

2019-06-15 · WS 2019 8 · Isaac Caswell, Ciprian Chelba, David Grangier

Recent work in Neural Machine Translation (NMT) has shown significant quality gains from noised-beam decoding during back-translation, a method to generate synthetic parallel data. We show that the main role of such synthetic noise is not to diversify the source side, as previously suggested, but simply to indicate to the model that the given source is synthetic. We propose a simpler alternative to noising techniques, consisting of tagging back-translated source sentences with an extra token. Our results on WMT outperform noised back-translation in English-Romanian and match performance on English-German, re-defining state-of-the-art in the former.

📄 PDF Abstract BibTeX arXiv:1906.06442

Code (0)

등록된 구현이 없습니다.

Tasks

Machine TranslationNMTTranslation

Similar Papers 제목 키워드 기반

Tagged Back-translation Revisited: Why Does It Really Work?

2020-07-01 · ACL 2020 6 · Benjamin Marie, Raphael Rubino, Atsushi Fujita

In this paper, we show that neural machine translation (NMT) systems trained on large back-translated data overfit some of the characteristics of machine-translated texts. Such NMT systems better translate human-produced…

Machine TranslationNMTTAGTranslation

CUNI Systems for the WMT22 Czech-Ukrainian Translation Task

2022-12-01 · Martin Popel, Jindřich Libovický, Jindřich Helcl

We present Charles University submissions to the WMT22 General Translation Shared Task on Czech-Ukrainian and Ukrainian-Czech machine translation. We present two constrained submissions based on block back-translation an…

Machine TranslationTranslation

Tag-less Back-Translation

2019-12-22 · Idris Abdulmumin, Bashir Shehu Galadanci, Aliyu Garba

An effective method to generate a large number of parallel sentences for training improved neural machine translation (NMT) systems is the use of the back-translations of the target-side monolingual data. The standard ba…

Domain AdaptationMachine TranslationNMTTAG+1

CROP: Zero-shot Cross-lingual Named Entity Recognition with Multilingual Labeled Sequence Translation

2022-10-13 · Jian Yang, Shaohan Huang, Shuming Ma, Yuwei Yin 외

Named entity recognition (NER) suffers from the scarcity of annotated training data, especially for low-resource languages without labeled data. Cross-lingual NER has been proposed to alleviate this issue by transferring…

Cross-Lingual NERMachine Translationnamed-entity-recognitionNamed Entity Recognition+4

Learning Translations for Tagged Words: Extending the Translation Lexicon of an ITG for Low Resource Languages

2016-06-01 · WS 2016 6 · Markus Saers, Dekai Wu
Machine TranslationTranslation