Our new X account is live! Follow @wizwand_team for updates
WorkDL logo mark

Minimum Risk Training for Neural Machine Translation

About

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 arbitrary evaluation metrics, which are not necessarily differentiable. Experiments show that our approach achieves significant improvements over maximum likelihood estimation on a state-of-the-art neural machine translation system across various languages pairs. Transparent to architectures, our approach can be applied to more neural networks and potentially benefit more NLP tasks.

Shiqi Shen, Yong Cheng, Zhongjun He, Wei He, Hua Wu, Maosong Sun, Yang Liu• 2015

Related benchmarks

TaskDatasetResultRank
Machine TranslationWMT En-De 2014 (test)
BLEU27.71
379
Machine TranslationWMT En-Fr 2014 (test)
BLEU31.3
237
Constituency ParsingPenn Treebank WSJ (section 23 test)
F1 Score95.2
55
Machine Translation (Chinese-to-English)NIST 2003 (MT-03)
BLEU37.32
52
Machine Translation (Chinese-to-English)NIST MT-05 2005
BLEU36.78
42
Machine TranslationNIST MT 06 2006 (test)
BLEU37.22
27
Machine TranslationNIST MT 04 2004 (test)
BLEU0.3941
27
Machine TranslationNIST Zh-En All (test)
BLEU Score37.92
10
Showing 8 of 8 rows

Other info

Follow for update