Machine translation evaluation with neural networks. (September 2017)

• Record Type: Journal Article
• Authors: Guzmán, Francisco; Joty, Shafiq; Màrquez, Lluís; Nakov, Preslav
• Is Part Of: Computer speech & language. Volume 45(2017)
• Page Start: 180
• Page End: 200
• Publication Date: 2017-09
• Subjects: Machine translation -- Reference-based MT evaluation -- Deep neural networks -- Distributed representation of texts -- Textual similarity; Speech processing systems -- Periodicals; Automatic speech recognition -- Periodicals; Computers -- Periodicals; Linguistics -- Periodicals; Speech-Language Pathology -- Periodicals; Traitement automatique de la parole -- Périodiques; Reconnaissance automatique de la parole -- Périodiques; Automatic speech recognition; Speech processing systems; Electronic journals; Periodicals; 006.454
• DOI: 10.1016/j.csl.2016.12.005
• Languages: English
• ISSNs: 0885-2308

Abstract

Highlights: A pairwise neural network (NN) is proposed for machine translation evaluation. The NN model incorporates syntactic and semantic embedded information. The NN architecture is motivated, in a principled way, by our knowledge of the task. The NN is flexible and robust, and it is extended in many different ways. The pairwise NN can produce a standard metric for MT evaluation, efficient, and performing on par with the state of the art. Abstract: We present a framework for machine translation evaluation using neural networks in a pairwise setting, where the goal is to select the better translation from a pair of hypotheses, given the reference translation. In this framework, lexical, syntactic and semantic information from the reference and the two hypotheses is embedded into compact distributed vector representations, and fed into a multi-layer neural network that models nonlinear interactions between each of the hypotheses and the reference, as well as between the two hypotheses. We experiment with the benchmark datasets from the WMT Metrics shared task, on which we obtain the best results published so far, with the basic network configuration. We also perform a series of experiments to analyze and understand the contribution of the different components of the network. We evaluate variants and extensions, including fine-tuning of the semantic embeddings, and sentence-based representations modeled with convolutional and recurrent neural networks. In summary, the proposed framework is flexible and generalizable, allows for efficient learning and scoring, and provides an MT evaluation metric that correlates with human judgments, and is on par with the state of the art.