Morphological Constraints for Phrase Pivot Statistical Machine Translation

TL;DR

This paper explores the use of morphological constraints to enhance phrase pivot statistical machine translation, addressing issues caused by poor morphology languages as pivots, and demonstrates improved translation quality.

Contribution

It introduces synchronous morphology constraint features, comparing handcrafted and learned constraints, to improve pivot SMT quality using limited parallel data.

Findings

Achieved 1.5 BLEU point improvement over baseline

Achieved 0.8 BLEU point improvement over direct model

Positive results on Hebrew-Arabic translation with English pivot

Abstract

The lack of parallel data for many language pairs is an important challenge to statistical machine translation (SMT). One common solution is to pivot through a third language for which there exist parallel corpora with the source and target languages. Although pivoting is a robust technique, it introduces some low quality translations especially when a poor morphology language is used as the pivot between rich morphology languages. In this paper, we examine the use of synchronous morphology constraint features to improve the quality of phrase pivot SMT. We compare hand-crafted constraints to those learned from limited parallel data between source and target languages. The learned morphology constraints are based on projected align- ments between the source and target phrases in the pivot phrase table. We show positive results on Hebrew-Arabic SMT (pivoting on English). We get 1.5 BLEU points over a phrase pivot baseline and 0.8 BLEU points over a system combination baseline with a direct model built from parallel data.