The Impact of Named Entity Translation for Neural Machine Translation

Named entity translation has been shown in many studies that could have positive impact on performance of sentence level neural machine translation. In this paper, we study a mainstream structure that incorporating an external named entity translation model to neural machine translation. We give several comparison experiments by applying different named entity translation model structures, to clearly represent the impact of this structure in improving quality of neural machine translation. The experiments show that the proposed approach is able to achieve posistive result on some datasets and we give our analysis of influence factors.

[1]  Jiajun Zhang,et al.  Neural Name Translation Improves Neural Machine Translation , 2016, Communications in Computer and Information Science.

[2]  Phil Blunsom,et al.  Recurrent Continuous Translation Models , 2013, EMNLP.

[3]  Yoshua Bengio,et al.  Learning Phrase Representations using RNN Encoder–Decoder for Statistical Machine Translation , 2014, EMNLP.

[4]  Wei Chen,et al.  Sogou Neural Machine Translation Systems for WMT17 , 2017, WMT.

[5]  Quoc V. Le,et al.  Addressing the Rare Word Problem in Neural Machine Translation , 2014, ACL.

[6]  Dong Yang,et al.  Combining a Two-step Conditional Random Field Model and a Joint Source Channel Model for Machine Transliteration , 2009, NEWS@IJCNLP.

[7]  Jian Su,et al.  A Joint Source-Channel Model for Machine Transliteration , 2004, ACL.

[8]  Rico Sennrich,et al.  Neural Machine Translation of Rare Words with Subword Units , 2015, ACL.

[9]  Jimmy Ba,et al.  Adam: A Method for Stochastic Optimization , 2014, ICLR.

[10]  Haizhou Li,et al.  Named entity transliteration with sequence-to-sequence neural network , 2017, 2017 International Conference on Asian Language Processing (IALP).

[11]  Tariq S. Durrani,et al.  Towards a Chinese Common and Common Sense Knowledge Base for Sentiment Analysis , 2012, IEA/AIE.

[12]  Lukasz Kaiser,et al.  Attention is All you Need , 2017, NIPS.

[13]  Sivaji Bandyopadhyay,et al.  A Modified Joint Source-Channel Model for Transliteration , 2006, ACL.

[14]  Yoshua Bengio,et al.  Neural Machine Translation by Jointly Learning to Align and Translate , 2014, ICLR.

[15]  Jiajun Zhang,et al.  Sentence Type Based Reordering Model for Statistical Machine Translation , 2008, COLING.

[16]  Jiajun Zhang,et al.  Word, Subword or Character? An Empirical Study of Granularity in Chinese-English NMT , 2017, CWMT.

[17]  Philip Gage,et al.  A new algorithm for data compression , 1994 .

[18]  Keh-Yih Su,et al.  Joint Chinese-English Named Entity Recognition and Alignment: Joint Chinese-English Named Entity Recognition and Alignment , 2011 .

[19]  Karin M. Verspoor,et al.  Automatic English-Chinese name transliteration for development of multilingual resources , 1998, ACL.