@inproceedings{gao2014learning,
author = {Gao, Jianfeng and He, Xiaodong and Yih, Scott Wen-tau and Deng, Li},
title = {Learning Continuous Phrase Representations for Translation Modeling},
booktitle = {Proceedings of ACL},
year = {2014},
month = {June},
abstract = {This paper tackles the sparsity problem in estimating phrase translation probabilities by learning continuous phrase representations, whose distributed nature enables the sharing of related phrases in their representations. A pair of source and target phrases are projected into continuous-valued vector representations in a low-dimensional latent space, where their translation score is computed by the distance between the pair in this new space. The projection is performed by a neural network whose weights are learned on parallel training data. Experimental evaluation has been performed on two WMT translation tasks. Our best result improves the performance of a state-of-the-art phrase-based statistical machine translation system trained on WMT 2012 French-English data by up to 1.3 BLEU points.},
publisher = {Association for Computational Linguistics},
url = {http://approjects.co.za/?big=en-us/research/publication/learning-continuous-phrase-representations-for-translation-modeling/},
edition = {Proceedings of ACL},
}