DeepAI AI Chat
Log In Sign Up

Morphological Constraints for Phrase Pivot Statistical Machine Translation

by   Ahmed El Kholy, et al.

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.


page 1

page 2

page 3

page 4


Role of Morphology Injection in Statistical Machine Translation

Phrase-based Statistical models are more commonly used as they perform o...

Augmenting Phrase Table by Employing Lexicons for Pivot-based SMT

Pivot language is employed as a way to solve the data sparseness problem...

Agreement-based Learning of Parallel Lexicons and Phrases from Non-Parallel Corpora

We introduce an agreement-based approach to learning parallel lexicons a...

Acquisition of Inflectional Morphology in Artificial Neural Networks With Prior Knowledge

How does knowledge of one language's morphology influence learning of in...

Morphology Generation for Statistical Machine Translation

When translating into morphologically rich languages, Statistical MT app...

Egyptian Arabic to English Statistical Machine Translation System for NIST OpenMT'2015

The paper describes the Egyptian Arabic-to-English statistical machine t...

Fast BTG-Forest-Based Hierarchical Sub-sentential Alignment

In this paper, we propose a novel BTG-forest-based alignment method. Bas...