Augmenting Neural Machine Translation through Round-Trip Training Approach
نویسندگان
چکیده
منابع مشابه
Minimum Risk Training for Neural Machine Translation
We propose minimum risk training for end-to-end neural machine translation. Unlike conventional maximum likelihood estimation, minimum risk training is capable of optimizing model parameters directly with respect to evaluation metrics. Experiments on Chinese-English and EnglishFrench translation show that our approach achieves significant improvements over maximum likelihood estimation on a sta...
متن کاملThe Efficacy of Round-trip Translation for MT Evaluation
ound-trip translation (RTT), otherwise known as reverse translation or back-and-forth translation, involves the translation of text from one language to another (the forward translation or FT) and back again (the back translation or BT), e.g., a paragraph written in English can be translated to Spanish, and then, the resulting Spanish text can be translated back to English again. RTT has been u...
متن کاملRound-trip Translation: What Is It Good For?
This paper considers the popular but questionable technique of ‘round-trip translation’ (RTT) as a means of evaluating free on-line Machine Translation systems. Two experiments are reported, both relating to common requirements of lay-users of MT on the web. In the first we see whether RTT can accurately predict the overall quality of the MT system. In the second, we ask whether RTT can predict...
متن کاملA machine learning framework for TCP round-trip time estimation
In this paper, we explore a novel approach to end-to-end round-trip time (RTT) estimation using a machine-learning technique known as the experts framework. In our proposal, each of several ‘experts’ guesses a fixed value. The weighted average of these guesses estimates the RTT, with the weights updated after every RTT measurement based on the difference between the estimated and actual RTT. Th...
متن کاملNeural Name Translation Improves Neural Machine Translation
In order to control computational complexity, neural machine translation (NMT) systems convert all rare words outside the vocabulary into a single unk symbol. Previous solution (Luong et al., 2015) resorts to use multiple numbered unks to learn the correspondence between source and target rare words. However, testing words unseen in the training corpus cannot be handled by this method. And it a...
متن کاملذخیره در منابع من
با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید
ژورنال
عنوان ژورنال: Open Computer Science
سال: 2019
ISSN: 2299-1093
DOI: 10.1515/comp-2019-0019