A Translation Evaluation Function based on Neural Network

In this paper, we study the feasibility of using a neural network to learn a fitness function for a machine translation system based on a genetic algorithm termed GAMaT. The neural network is learned on features extracted from pairs of source sentences and their translations. The fitness function is trained in order to estimate the BLEU of a translation as precisely as possible. The estimator has been trained on a corpus of more than 1.3 million data. The performance is very promising: the difference between the real BLEU and the one given by the estimator is equal to 0.12 in terms of Mean Absolute Error.

[1]  Razvan Pascanu,et al.  Theano: Deep Learning on GPUs with Python , 2012 .

[2]  Jong-Hyeok Lee,et al.  A Recurrent Neural Networks Approach for Estimating the Quality of Machine Translation Output , 2016, NAACL.

[3]  Philipp Koehn,et al.  Moses: Open Source Toolkit for Statistical Machine Translation , 2007, ACL.

[4]  Salim Roukos,et al.  Bleu: a Method for Automatic Evaluation of Machine Translation , 2002, ACL.

[5]  Taro Watanabe,et al.  Optimization for Statistical Machine Translation: A Survey , 2016, CL.

[6]  Chris Callison-Burch,et al.  Open Source Toolkit for Statistical Machine Translation: Factored Translation Models and Lattice Decoding , 2006 .

[7]  Mostafa Zandieh,et al.  Bi-objective optimization research on integrated fixed time interval preventive maintenance and production for scheduling flexible job-shop problem , 2011, Expert Syst. Appl..

[8]  C. Willmott,et al.  Advantages of the mean absolute error (MAE) over the root mean square error (RMSE) in assessing average model performance , 2005 .

[9]  Kamel Smaïli,et al.  Genetic-Based Decoder for Statistical Machine Translation , 2016, CICLing.

[10]  Franz Josef Och,et al.  Minimum Error Rate Training in Statistical Machine Translation , 2003, ACL.

[11]  Hermann Ney,et al.  A Systematic Comparison of Various Statistical Alignment Models , 2003, CL.

[12]  Philipp Koehn,et al.  Findings of the 2014 Workshop on Statistical Machine Translation , 2014, WMT@ACL.

[13]  Kamel Smaïli,et al.  LORIA System for the WMT13 Quality Estimation Shared Task , 2013, WMT@ACL.

[14]  Daniel Marcu,et al.  Statistical Phrase-Based Translation , 2003, NAACL.

[15]  P. Cochat,et al.  Et al , 2008, Archives de pediatrie : organe officiel de la Societe francaise de pediatrie.