Machine Translation Evaluation with Neural Networks

TL;DR

This paper introduces a neural network-based framework for machine translation evaluation that effectively models complex interactions and achieves state-of-the-art correlation with human judgments on benchmark datasets.

Contribution

It presents a novel neural network approach for pairwise MT evaluation that integrates lexical, syntactic, and semantic features into a flexible, high-performing metric.

Findings

Achieved best results on WMT Metrics shared task datasets.

Demonstrated the effectiveness of neural network models in MT evaluation.

Analyzed the impact of different network components and extensions.

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.