A Deep Learning-Based Intelligent Quality Detection Model for Machine Translation

With more and more active international connections, the complex scenes-aware machine translation has been a novel concern in the area of natural language processing. Although various machine translation methods have been proposed during the past few years, automatic and intelligent quality detection for translation results failed to receive sufficient attention. Actually, the real-time quality evaluation for machine translation results remains important, because it can facilitate constant debugging and optimization of machine translation products. Existing approaches mostly focused on the offline written contents rather than real-time extensive oral contents. To bridge current gap, a sentence-level machine translation quality estimation method is deployed in this paper. In particular, a specifical recurrent neural network with double directions (Double-RNN) is proposed as the backbone network structure. The feature extraction process utilizes the Double-RNN translation model, which makes full use of a large amount of parallel corpus. The evaluations show that Double-RNN method proposed in this paper is the closest to the standard quality assessment, and thus can also evaluate the quality of Chinese and English translations more fairly.