Adversarial Training for Unknown Word Problems in Neural Machine Translation

2020 ◽  
Vol 19 (1) ◽  
pp. 1-12
Author(s):  
Yatu Ji ◽  
Hongxu Hou ◽  
Junjie Chen ◽  
Nier Wu
Keyword(s):  
Machine Translation ◽  
Word Problems ◽  
Neural Machine Translation ◽  
Unknown Word ◽  
Adversarial Training

scholarly journals A Transformer-Based Neural Machine Translation Model for Arabic Dialects That Utilizes Subword Units

Sensors ◽  
2021 ◽  
Vol 21 (19) ◽  
pp. 6509
Author(s):  
Laith H. Baniata ◽  
Isaac. K. E. Ampomah ◽  
Seyoung Park
Keyword(s):  
Machine Translation ◽  
Target Language ◽  
Modern Standard Arabic ◽  
Neural Machine Translation ◽  
Unknown Word ◽  
Translation Model ◽  
Standard Arabic ◽  
Arabic Dialects ◽  
Transformer Model ◽  
Modern Standard

Languages that allow free word order, such as Arabic dialects, are of significant difficulty for neural machine translation (NMT) because of many scarce words and the inefficiency of NMT systems to translate these words. Unknown Word (UNK) tokens represent the out-of-vocabulary words for the reason that NMT systems run with vocabulary that has fixed size. Scarce words are encoded completely as sequences of subword pieces employing the Word-Piece Model. This research paper introduces the first Transformer-based neural machine translation model for Arabic vernaculars that employs subword units. The proposed solution is based on the Transformer model that has been presented lately. The use of subword units and shared vocabulary within the Arabic dialect (the source language) and modern standard Arabic (the target language) enhances the behavior of the multi-head attention sublayers for the encoder by obtaining the overall dependencies between words of input sentence for Arabic vernacular. Experiments are carried out from Levantine Arabic vernacular (LEV) to modern standard Arabic (MSA) and Maghrebi Arabic vernacular (MAG) to MSA, Gulf–MSA, Nile–MSA, Iraqi Arabic (IRQ) to MSA translation tasks. Extensive experiments confirm that the suggested model adequately addresses the unknown word issue and boosts the quality of translation from Arabic vernaculars to Modern standard Arabic (MSA).

scholarly journals Neural Machine Translation with Adequacy-Oriented Learning

2019 ◽  
Vol 33 ◽  
pp. 6618-6625 ◽  
Author(s):  
Xiang Kong ◽  
Zhaopeng Tu ◽  
Shuming Shi ◽  
Eduard Hovy ◽  
Tong Zhang
Keyword(s):  
Machine Translation ◽  
State Of The Art ◽  
Likelihood Estimation ◽  
Neural Machine Translation ◽  
Learning Mechanism ◽  
Translation Quality ◽  
Word Level ◽  
Adversarial Training ◽  
Level Training ◽  
Qualitative Analyses

Although Neural Machine Translation (NMT) models have advanced state-of-the-art performance in machine translation, they face problems like the inadequate translation. We attribute this to that the standard Maximum Likelihood Estimation (MLE) cannot judge the real translation quality due to its several limitations. In this work, we propose an adequacyoriented learning mechanism for NMT by casting translation as a stochastic policy in Reinforcement Learning (RL), where the reward is estimated by explicitly measuring translation adequacy. Benefiting from the sequence-level training of RL strategy and a more accurate reward designed specifically for translation, our model outperforms multiple strong baselines, including (1) standard and coverage-augmented attention models with MLE-based training, and (2) advanced reinforcement and adversarial training strategies with rewards based on both word-level BLEU and character-level CHRF3. Quantitative and qualitative analyses on different language pairs and NMT architectures demonstrate the effectiveness and universality of the proposed approach.

Generative adversarial training for neural machine translation

2018 ◽  
Vol 321 ◽  
pp. 146-155 ◽  
Author(s):  
Zhen Yang ◽  
Wei Chen ◽  
Feng Wang ◽  
Bo Xu
Keyword(s):  
Machine Translation ◽  
Neural Machine Translation ◽  
Adversarial Training

scholarly journals An Empirical Study on Learning Bug-Fixing Patches in the Wild via Neural Machine Translation

2019 ◽  
Vol 28 (4) ◽  
pp. 1-29 ◽  
Author(s):  
Michele Tufano ◽  
Cody Watson ◽  
Gabriele Bavota ◽  
Massimiliano Di Penta ◽  
Martin White ◽  
...  
Keyword(s):  
Empirical Study ◽  
Machine Translation ◽  
Neural Machine Translation ◽  
Bug Fixing ◽  
In The Wild

scholarly journals Neural Machine Translation for Semantic-Driven Q&A Systems in the Factory Planning

Procedia CIRP ◽  
2021 ◽  
Vol 96 ◽  
pp. 9-14
Author(s):  
Uwe Dombrowski ◽  
Alexander Reiswich ◽  
Raphael Lamprecht
Keyword(s):  
Machine Translation ◽  
Neural Machine Translation ◽  
Factory Planning
Sign in / Sign up

Export Citation Format

Share Document