Syntax-to-Morphology Mapping in Factored Phrase-Based Statistical Machine Translation from English to Turkish

Proceedings of the 48th Annual Meeting of the Association for Computational Linguistics, pages 454–464, Uppsala, Sweden, 11-16 July 2010. c⃝2010 Association for Computational Linguistics Syntax-to-Morphology Mapping in Factored Phrase-Based Statistical Machine Translation from English to Turkish Reyyan Yeniterzi Language Technologies Institute Carnegie Mellon University Pittsburgh, PA, 15213, USA reyyan@cs.cmu.edu Kemal Oflazer Computer Science Carnegie Mellon University-Qatar PO Box 24866, Doha, Qatar ko@cs.cmu.edu Abstract We present a novel scheme to apply fac- tored phrase-based SMT to a language pair with very disparate morphological struc- tures. Our approach relies on syntac- tic analysis on the source side (English) and then encodes a wide variety of local and non-local syntactic structures as com- plex structural tags which appear as ad- ditional factors in the training data. On the target side (Turkish), we only per- form morphological analysis and disam- biguation but treat the complete complex morphological tag as a factor, instead of separating morphemes. We incrementally explore capturing various syntactic sub- structures as complex tags on the En- glish side, and evaluate how our transla- tions improve in BLEU scores. Our max- imal set of source and target side trans- formations, coupled with some additional techniques, provide an 39% relative im- provement from a baseline 17.08 to 23.78 BLEU, all averaged over 10 training and test sets. Now that the syntactic analy- sis on the English side is available, we also experiment with more long distance constituent reordering to bring the English constituent order close to Turkish, but find that these transformations do not provide any additional consistent tangible gains when averaged over the 10 sets. 1 Introduction Statistical machine translation into a morphologi- cally complex language such as Turkish, Finnish or Arabic, involves the generation of target words with the proper morphology, in addition to prop- erly ordering the target words. Earlier work on translation from English to Turkish (Oflazer and Durgar-El-Kahlout, 2007; Oflazer, 2008; Durgar- El-Kahlout and Oflazer, 2010) has used an ap- proach which relied on identifying the contextu- ally correct parts-of-speech, roots and any mor- phemes on the English side, and the complete se- quence of roots and overt derivational and inflec- tional morphemes for each word on the Turkish side. Once these were identified as separate to- kens, they were then used as “words” in a stan- dard phrase-based framework (Koehn et al., 2003). They have reported that, given the typical com- plexity of Turkish words, there was a substantial percentage of words whose morphological struc- ture was incorrect: either the morphemes were not applicable for the part-of-speech category of the root word selected, or the morphemes were in the wrong order. The main reason given for these problems was that the same statistical trans- lation, reordering and language modeling mecha- nisms were being employed to both determine the morphological structure of the words and, at the same time, get the global order of the words cor- rect. Even though a significant improvement of a standard word-based baseline was achieved, fur- ther analysis hinted at a direction where …

Content truncated to 500 words