A Simple and Effective Approach to Automatic Post-Editing with Transfer Learning
Automatic post-editing (APE) seeks to automatically refine the output of a black-box machine translation (MT) system through human post-edits. APE systems are usually trained by complementing human post-edited data with large, artificial data generated through back-translations, a time-consuming process often no easier than training a MT system from scratch. in this paper, we propose an alternative where we fine-tune pre-trained BERT models on both the encoder and decoder of an APE system, exploring several parameter sharing strategies. By only training on a dataset of 23K sentences for 3 hours on a single GPU we obtain results that are competitive with systems that were trained on 5M artificial sentences. When we add this artificial data our method obtains state-of-the-art results.
Code (1)
Tasks
Automatic Post-EditingDecoderGPUMachine TranslationTransfer LearningTranslationMethods 이 논문이 사용한 방법론
Similar Papers 제목 키워드 기반
A Simple and Effective Approach to Automatic Post-Editing with Transfer Learning
Automatic post-editing (APE) seeks to automatically refine the output of a black-box machine translation (MT) system through human post-edits. APE systems are usually trained by complementing human post-edited data with …
Automatic Post-EditingDecoderGPUMachine Translation+2USAAR-DFKI -- The Transference Architecture for English--German Automatic Post-Editing
In this paper we present an English{--}German Automatic Post-Editing (APE) system called transference, submitted to the APE Task organized at WMT 2019. Our transference model is based on a multi-encoder transformer archi…
Automatic Post-EditingDecoderMachine TranslationTranslationSWIFT Aligner, A Multifunctional Tool for Parallel Corpora: Visualization, Word Alignment, and (Morpho)-Syntactic Cross-Language Transfer
It is well known that word aligned parallel corpora are valuable linguistic resources. Since many factors affect automatic alignment quality, manual post-editing may be required in some applications. While there are seve…
Machine TranslationWord AlignmentWord Sense DisambiguationThe Transference Architecture for Automatic Post-Editing
In automatic post-editing (APE) it makes sense to condition post-editing (pe) decisions on both the source (src) and the machine translated text (mt) as input. This has led to multi-source encoder based APE approaches. A…
Automatic Post-EditingDecoderNMTSimple Automatic Post-editing for Arabic-Japanese Machine Translation
A common bottleneck for developing machine translation (MT) systems for some language pairs is the lack of direct parallel translation data sets, in general and in certain domains. Alternative solutions such as zero-shot…
ArticlesAutomatic Post-EditingMachine TranslationTranslation