Improving Mongolian-Chinese Neural Machine Translation with Morphological Noise
For the translation of agglutinative language such as typical Mongolian, unknown (UNK) words not only come from the quite restricted vocabulary, but also mostly from misunderstanding of the translation model to the morphological changes. In this study, we introduce a new adversarial training model to alleviate the UNK problem in Mongolian-Chinese machine translation. The training process can be described as three adversarial sub models (generator, value screener and discriminator), playing a win-win game. In this game, the added screener plays the role of emphasizing that the discriminator pays attention to the added Mongolian morphological noise in the form of pseudo-data and improving the training efficiency. The experimental results show that the newly emerged Mongolian-Chinese task is state-of-the-art. Under this premise, the training time is greatly shortened.
Code (0)
등록된 구현이 없습니다.
Tasks
Machine TranslationTranslationSimilar Papers 제목 키워드 기반
A Simple and General Strategy for Referential Problem in Low-Resource Neural Machine Translation
This paper aims to solve a series of referential problems in sequence decoding caused by data sparsity and corpus scarce in low-resource Neural Machine Translation (NMT), including pronoun missing, reference error, bias …
Low Resource Neural Machine TranslationLow-Resource Neural Machine TranslationLow Resource NMTMachine Translation+2Multi-Reward based Reinforcement Learning for Neural Machine Translation
Reinforcement learning (RL) has made remarkable progress in neural machine translation (NMT). However, it exists the problems with uneven sampling distribution, sparse rewards and high variance in training phase. Therefo…
Language ModelingLanguage ModellingMachine TranslationNMT+4Low-Resource Machine Translation based on Asynchronous Dynamic Programming
“Reinforcement learning has been proved to be effective in handling low resource machine trans-lation tasks and different sampling methods of reinforcement learning affect the performance ofthe model. The reward for gene…
General Reinforcement LearningLow Resource Neural Machine TranslationLow-Resource Neural Machine TranslationMachine Translation+4Syntactic Relevance XLNet Word Embedding Generation in Low-Resource Machine Translation
Semantic understanding is an important factor affecting the quality of machine translation of low resource agglutination language. The common methods(sub-word modeling, pre-training word embedding, etc.) will increase th…
Language ModelingLanguage ModellingMachine TranslationTranslationIncorporating Inner-word and Out-word Features for Mongolian Morphological Segmentation
Mongolian morphological segmentation is regarded as a crucial preprocessing step in many Mongolian related NLP applications and has received extensive attention. Recently, end-to-end segmentation approaches with long sho…
DecoderSegmentationSentence