Pairwise Neural Machine Translation Evaluation

by   Francisco Guzmán, et al.

We present a novel 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 compacted into relatively small distributed vector representations, and fed into a multi-layer neural network that models the interaction between each of the hypotheses and the reference, as well as between the two hypotheses. These compact representations are in turn based on word and sentence embeddings, which are learned using neural networks. The framework is flexible, allows for efficient learning and classification, and yields correlation with humans that rivals the state of the art.


page 1

page 2

page 3

page 4


Machine Translation Evaluation with Neural Networks

We present a framework for machine translation evaluation using neural n...

Single-Queue Decoding for Neural Machine Translation

Neural machine translation models rely on the beam search algorithm for ...

Metric for Automatic Machine Translation Evaluation based on Universal Sentence Representations

Sentence representations can capture a wide range of information that ca...

Machine Translation Evaluation Meets Community Question Answering

We explore the applicability of machine translation evaluation (MTE) met...

One Homonym per Translation

The study of homonymy is vital to resolving fundamental problems in lexi...

Not All Neural Embeddings are Born Equal

Neural language models learn word representations that capture rich ling...

Simple and Effective Text Simplification Using Semantic and Neural Methods

Sentence splitting is a major simplification operator. Here we present a...