Hybrid Machine Translation by Combining Output from Multiple Machine Translation Systems

Abstract

This paper aims to combine output from various machine translation (MT) systems so that the overall translation quality of the source text would increase. Applicability of the developed methods for small, morphologically rich and under-resourced languages is evaluated, especially Latvian and Estonian. Existing methods have been analysed, and several combinations of methods have been proposed. The proposed methods have been implemented and evaluated using automatic and human evaluation. During this research novel methods have been created that structure source language sentences into linguistically motivated fragments and combine them using a character level neural language model; combine neural machine translation output by employing sourcetranslation attention alignments; use a multi-pass approach to produce additional incrementally improving training data. The key results of this research are new state-of-the-art machine translation systems for English ↔ Estonian; approaches for utilising neural MT generated attention alignments for MT combination and comprehension of resulting translations; MT combination systems for combining output from English → Latvian statistical MT. A practical application of the methods is implemented and described.

Hybrid System Combination Framework for Uyghur–Chinese Machine Translation

“…Recently, various studies of hybrid system combination methods are available in the literature [41][42][43]. Some researchers proposed a three-stack architecture for both utilizing the neural-based system combination model and the statistical-based neural system combination model to improve the translation quality [41].…”

“…Other researchers proposed a simple reranking system using a smorgasbord of the informative features [42]. Some novel methods are proposed in the literature [43], such as structuring source-side language sentences into the linguistically motivated fragments and combining them using a character-level neural language model, and combining neural machine translation output by employing the source-side translation attention alignments. The main goal is to assemble a set of methods that would be able to improve the quality of the Uyghur-Chinese machine translation, which has rich morphology and limited corpora resources.…”