1 |
Domain adaptation for statistical machine translation and neural machine translation
|
|
Zhang, Jian. - : Dublin City University. School of Computing, 2017. : Dublin City University. ADAPT, 2017
|
|
In: Zhang, Jian orcid:0000-0001-5659-5865 (2017) Domain adaptation for statistical machine translation and neural machine translation. PhD thesis, Dublin City University. (2017)
|
|
BASE
|
|
Show details
|
|
2 |
Fast gated neural domain adaptation: language model as a case study
|
|
|
|
In: Zhang, Jian orcid:0000-0001-5659-5865 , Wu, Xiaofeng, Way, Andy orcid:0000-0001-5736-5930 and Liu, Qun orcid:0000-0002-7000-1792 (2017) Fast gated neural domain adaptation: language model as a case study. In: Proceedings of FETLT 2016: Future and Emerging Trends in Language Technologies, Machine Learning and Big Data, 30 Nov- 2 Dec 2016, Seville, Spain. (2017)
|
|
Abstract:
Neural network training has been shown to be advantageous in many natural language processing applications, such as language modelling or machine translation. In this paper, we describe in detail a novel domain adaptation mechanism in neural network training. Instead of learning and adapting the neural network on millions of training sentences – which can be very timeconsuming or even infeasible in some cases – we design a domain adaptation gating mechanism which can be used in recurrent neural networks and quickly learn the out-of-domain knowledge directly from the word vector representations with little speed overhead. In our experiments, we use the recurrent neural network language model (LM) as a case study. We show that the neural LM perplexity can be reduced by 7.395 and 12.011 using the proposed domain adaptation mechanism on the Penn Treebank and News data, respectively. Furthermore, we show that using the domain-adapted neural LM to re-rank the statistical machine translation n-best list on the French-to-English language pair can significantly improve translation quality
|
|
Keyword:
Machine learning
|
|
URL: http://doras.dcu.ie/23233/
|
|
BASE
|
|
Hide details
|
|
|
|