Tagged Back-Translation
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.
Code (0)
등록된 구현이 없습니다.
Tasks
Machine TranslationNMTTranslationSimilar Papers 제목 키워드 기반
Tagged Back-translation Revisited: Why Does It Really Work?
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 TranslationNMTTAGTranslationCUNI Systems for the WMT22 Czech-Ukrainian Translation Task
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 TranslationTranslationTag-less Back-Translation
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+1CROP: Zero-shot Cross-lingual Named Entity Recognition with Multilingual Labeled Sequence Translation
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