中文
相关论文

相关论文: On The Evaluation of Machine Translation Systems T…

200 篇论文

An effective method to improve neural machine translation with monolingual data is to augment the parallel training corpus with back-translations of target language sentences. This work broadens the understanding of back-translation and…

计算与语言 · 计算机科学 2018-10-04 Sergey Edunov , Myle Ott , Michael Auli , David Grangier

Neural Machine Translation has achieved state-of-the-art performance for several language pairs using a combination of parallel and synthetic data. Synthetic data is often generated by back-translating sentences randomly sampled from…

计算与语言 · 计算机科学 2018-09-24 Marzieh Fadaee , Christof Monz

The quality of neural machine translation can be improved by leveraging additional monolingual resources to create synthetic training data. Source-side monolingual data can be (forward-)translated into the target language for self-training;…

计算与语言 · 计算机科学 2020-10-06 Nikolay Bogoychev , Rico Sennrich

Machine translation has an undesirable propensity to produce "translationese" artifacts, which can lead to higher BLEU scores while being liked less by human raters. Motivated by this, we model translationese and original (i.e. natural)…

计算与语言 · 计算机科学 2020-07-13 Parker Riley , Isaac Caswell , Markus Freitag , David Grangier

Our research extends the Bilingual Evaluation Understudy (BLEU) evaluation technique for statistical machine translation to make it more adjustable and robust. We intend to adapt it to resemble human evaluation more. We perform experiments…

计算与语言 · 计算机科学 2015-10-01 Krzysztof Wołk , Krzysztof Marasek

The quality of automatic metrics for machine translation has been increasingly called into question, especially for high-quality systems. This paper demonstrates that, while choice of metric is important, the nature of the references is…

计算与语言 · 计算机科学 2020-10-21 Markus Freitag , David Grangier , Isaac Caswell

Unsupervised on-the-fly back-translation, in conjunction with multilingual pretraining, is the dominant method for unsupervised neural machine translation. Theoretically, however, the method should not work in general. We therefore conduct…

计算与语言 · 计算机科学 2024-03-28 Nicolas Guerin , Shane Steinert-Threlkeld , Emmanuel Chemla

Neural Machine Translation (MT) has radically changed the way systems are developed. A major difference with the previous generation (Phrase-Based MT) is the way monolingual target data, which often abounds, is used in these two paradigms.…

计算与语言 · 计算机科学 2019-03-28 Franck Burlot , François Yvon

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 which monolingual data…

计算与语言 · 计算机科学 2020-10-09 Zi-Yi Dou , Antonios Anastasopoulos , Graham Neubig

Back-translation is an effective strategy to improve the performance of Neural Machine Translation~(NMT) by generating pseudo-parallel data. However, several recent works have found that better translation quality of the pseudo-parallel…

计算与语言 · 计算机科学 2021-02-17 Hieu Pham , Xinyi Wang , Yiming Yang , Graham Neubig

Machine translation (MT) has benefited from using synthetic training data originating from translating monolingual corpora, a technique known as backtranslation. Combining backtranslated data from different sources has led to better results…

计算与语言 · 计算机科学 2020-05-04 Xabier Soto , Dimitar Shterionov , Alberto Poncelas , Andy Way

Back-translation - data augmentation by translating target monolingual data - is a crucial component in modern neural machine translation (NMT). In this work, we reformulate back-translation in the scope of cross-entropy optimization of an…

计算与语言 · 计算机科学 2019-06-19 Miguel Graça , Yunsu Kim , Julian Schamper , Shahram Khadivi , Hermann Ney

This paper illustrates our approach to the shared task on large-scale multilingual machine translation in the sixth conference on machine translation (WMT-21). This work aims to build a single multilingual translation system with a…

计算与语言 · 计算机科学 2021-09-21 Baohao Liao , Shahram Khadivi , Sanjika Hewavitharana

Improving neural machine translation (NMT) models using the back-translations of the monolingual target data (synthetic parallel data) is currently the state-of-the-art approach for training improved translation systems. The quality of the…

计算与语言 · 计算机科学 2021-02-16 Idris Abdulmumin , Bashir Shehu Galadanci , Abubakar Isa

Non-autoregressive approaches aim to improve the inference speed of translation models by only requiring a single forward pass to generate the output sequence instead of iteratively producing each predicted token. Consequently, their…

计算与语言 · 计算机科学 2022-10-24 Robin M. Schmidt , Telmo Pires , Stephan Peitz , Jonas Lööf

Back Translation (BT) is widely used in the field of machine translation, as it has been proved effective for enhancing translation quality. However, BT mainly improves the translation of inputs that share a similar style (to be more…

计算与语言 · 计算机科学 2023-06-05 Daimeng Wei , Zhanglin Wu , Hengchao Shang , Zongyao Li , Minghan Wang , Jiaxin Guo , Xiaoyu Chen , Zhengzhe Yu , Hao Yang

Machine-translated text plays a crucial role in the communication of people using different languages. However, adversaries can use such text for malicious purposes such as plagiarism and fake review. The existing methods detected a…

计算与语言 · 计算机科学 2019-10-16 Hoang-Quoc Nguyen-Son , Tran Phuong Thao , Seira Hidano , Shinsaku Kiyomoto

Back-translation has become a commonly employed heuristic for semi-supervised neural machine translation. The technique is both straightforward to apply and has led to state-of-the-art results. In this work, we offer a principled…

计算与语言 · 计算机科学 2018-06-13 Ryan Cotterell , Julia Kreutzer

The success of end-to-end speech-to-text translation (ST) is often achieved by utilizing source transcripts, e.g., by pre-training with automatic speech recognition (ASR) and machine translation (MT) tasks, or by introducing additional ASR…

计算与语言 · 计算机科学 2023-05-16 Qingkai Fang , Yang Feng

Even with the latest developments in deep learning and large-scale language modeling, the task of machine translation (MT) of low-resource languages remains a challenge. Neural MT systems can be trained in an unsupervised way without any…

计算与语言 · 计算机科学 2023-10-24 Ivana Kvapilíková , Ondřej Bojar
‹ 上一页 1 2 3 10 下一页 ›