Morphology-inspired word segmentation for neural machine translation

This paper proposes the Prefix-Root-Postfix-Encoding (PRPE) algorithm, which performs close-to-morphological segmentation of words as part of text pre-processing in machine translation. PRPE is a cross-language algorithm requiring only minor tweaking to adapt it for any particular language, a property which makes it potentially useful for morphologically rich languages with no morphological analysers available. As a key part of the proposed algorithm we introduce the ‘Root alignment’ principle to extract potential sub-words from a corpus, as well as a special technique for constructing words from potential sub-words. In addition, we supplemented the algorithm with specific processing for named-entities based on transliteration. We conducted experiments with two different neural machine translation systems, training them on parallel corpora for English-Latvian and Latvian-English translation. Evaluation of translation quality showed improvements in BLEU scores when the data were pre-processed using the proposed algorithm, compared to a couple of baseline word segmentation algorithms. Although we were able to demonstrate improvements in both translation directions and for both NMT systems, they were relatively minor, and our experiments show that machine translation with inflected languages remains challenging, especially with translation direction towards a highly inflected language.