paper-with-me

홈 › Papers

A Simple and Effective Approach to Automatic Post-Editing with Transfer Learning

2019-07-01 · ACL 2019 7 · Gon{\c{c}}alo M. Correia, Andr{\'e} F. T. Martins

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.

📄 PDF Abstract BibTeX

Code (1)

deep-spin/OpenNMT-APE 공식 구현 pytorch

Tasks

Automatic Post-EditingDecoderGPUMachine TranslationTransfer LearningTranslation

Methods 이 논문이 사용한 방법론

Linear Layer A Linear Layer is a projection $\mathbf{XW + b}$.
Residual Connection 설명 없음
Attention Dropout Attention Dropout is a type of dropout used in attention-based architectures, where elements are randomly dropped out of the…
Linear Warmup With Linear Decay Linear Warmup With Linear Decay is a learning rate schedule in which we increase the learning rate linearly for $n$ updates and then linearly decay afterwards.
Weight Decay 설명 없음
Refunds@Expedia|||How do I get a full refund from Expedia? “How do I get a full refund from Expedia? How do I get a full refund from Expedia? – Call ☎️ +1-(888) 829 (0881) or +1-805-330-4056 or +1-805-330-4056 for Quick Help &…
Dense Connections Dense Connections, or Fully Connected Connections, are a type of layer in a deep neural network that use a linear operation where every input is connected to every output…
Adam 설명 없음

Similar Papers 제목 키워드 기반

A Simple and Effective Approach to Automatic Post-Editing with Transfer Learning

2019-06-14 · Gonçalo M. Correia, André F. T. Martins

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+2

USAAR-DFKI -- The Transference Architecture for English--German Automatic Post-Editing

2019-08-01 · WS 2019 8 · Santanu Pal, Hongfei Xu, Nico Herbig, Antonio Kr{\"u}ger 외

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 TranslationTranslation

SWIFT Aligner, A Multifunctional Tool for Parallel Corpora: Visualization, Word Alignment, and (Morpho)-Syntactic Cross-Language Transfer

2014-05-01 · LREC 2014 5 · Timur Gilmanov, Olga Scrivner, S K{\"u}bler, ra

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 Disambiguation

The Transference Architecture for Automatic Post-Editing

2019-08-16 · COLING 2020 8 · Santanu Pal, Hongfei Xu, Nico Herbig, Sudip Kumar Naskar 외

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-EditingDecoderNMT

Simple Automatic Post-editing for Arabic-Japanese Machine Translation

2019-07-14 · Ella Noll, Mai Oudah, Nizar Habash

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