Abstract
We study the relationship between word order freedom and preordering in statistical machine translation. To assess word order freedom, we first introduce a novel entropy measure which quantifies how difficult it is to predict word order given a source sentence and its syntactic analysis. We then address preordering for two target languages at the far ends of the word order freedom spectrum, German and Japanese, and argue that for languages with more word order freedom, attempting to predict a unique word order given source clues only is less justified. Subsequently, we examine lattices of n-best word order predictions as a unified representation for languages from across this broad spectrum and present an effective solution to a resulting technical issue, namely how to select a suitable source word order from the lattice during training. Our experiments show that lattices are crucial for good empirical performance for languages with freer word order (English‐German) and can provide additional improvements for fixed word order languages (English‐
Highlights
Word order differences between a source and a target language are a major challenge for machine translation systems
Preordering of the source sentence has been embraced as a way to ensure the reachability of certain target word order constellations for improved prediction of the target word order
Our goal in this paper was to examine the effect of word order freedom on machine translation and preordering
Summary
Word order differences between a source and a target language are a major challenge for machine translation systems. For phrase-based models, the number of possible phrase permutations is so large that reordering must be constrained locally to make the search space for the best hypothesis feasible. Preordering aims at predicting a permutation of the source sentence which has minimal word order differences with the target sentence; the permuted source sentence is passed on to a backend translation system trained to translate target-order source sentences into target sentences. The preordering approach makes the assumption that it is feasible to predict target word order given only clues from the source sentence. In the vast majority of work on preordering, a single preordered source sentence is passed on to the backend system, thereby making the stronger assumption that it is feasible to predict a unique preferred target word order. How reasonable are these assumptions and for which target languages?
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Free) 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call
