Abstract
The aim of this paper is to categorize and present the existence of resources for English- to-Urdu machine translation (MT) and to establish an empirical baseline for this task. By doing so, we hope to set up a common ground for MT research with Urdu to allow for a congruent progress in this field.
We build baseline phrase-based MT (PBMT) and hierarchical MT systems and report the results on 3 official independent test sets. On all test sets, hierarchial MT significantly outperformed PBMT.
The highest single-reference BLEU score is achieved by the hierarchical system and reaches 21.58% but this figure depends on the randomly selected test set. Our manual evaluation of 175 sentences suggests that in 45% of sentences, the hierarchical MT is ranked better than the PBMT output compared to 21% of sentences where PBMT wins, the rest being equal.