Hierarchical Phrase-Based MT at the Charles University for the WMT 2011 Shared Task

Proceedings of the 6th Workshop on Statistical Machine Translation, pages 496–500, Edinburgh, Scotland, UK, July 30–31, 2011. c⃝2011 Association for Computational Linguistics Hierarchical Phrase-Based MT at the Charles University for the WMT 2011 Shared Task Daniel Zeman Charles University in Prague, Institute of Formal and Applied Linguistics (ÚFAL) Univerzita Karlova v Praze, Ústav formální a aplikované lingvistiky (ÚFAL) Malostranské náměstí 25, Praha, CZ-11800, Czechia zeman@ufal.mff.cuni.cz Abstract We describe our experiments with hier- archical phrase-based machine translation for the WMT 2011 Shared Task. We trained a system for all 8 translation di- rections between English on one side and Czech, German, Spanish or French on the other side, though we focused slightly more on the English-to-Czech direction. We provide a detailed description of our configuration and data so the results are replicable. 1 Introduction With so many official languages, Europe is a par- adise for machine translation research. One of the largest bodies of electronically available parallel texts is being nowadays generated by the European Union and its institutions. At the same time, the EU also provides motivation and boosts potential market for machine translation outcomes. Most of the major European languages belong to one of the following three branches of the Indo-European language family: Germanic, Ro- mance or Slavic. Such relatedness is responsible for many structural similarities in European lan- guages, although significant differences still ex- ist. Within the language portfolio selected for the WMT shared task, English, French and Spanish seem to be closer to each other than to the rest. German, despite being genetically related to En- glish, differs in many properties. Its word or- der rules, shifting verbs from one end of the sen- tence to the other, easily create long-distance de- pendencies. Long German compound words are notorious for increasing out-of-vocabulary rate, which has led many researchers to devising un- supervised compound-splitting techniques. Also, uppercase/lowercase distinction is more important because all German nouns start with an uppercase letter by the rule. Czech is a language with rich morphology (both inflectional and derivational) and relatively free word order. In fact, the predicate-argument struc- ture, often encoded by fixed word order in English, is usually captured by inflection (especially the system of 7 grammatical cases) in Czech. While the free word order of Czech is a problem when translating to English (the text should be parsed first in order to determine the syntactic functions and the English word order), generating correct in- flectional affixes is indeed a challenge for English- to-Czech systems. Furthermore, the multitude of possible Czech word forms (at least order of magnitude higher than in English) makes the data sparseness problem really severe, hindering both directions. There are numerous ways how these issues could be addressed. For instance, parsing and syntax-aware reordering of the source-language sentences can help with the word order differ- ences (same goal could be achieved by a reorder- ing model or a synchronous context-free grammar in a hierarchical system). Factored translation, a secondary language model of morphological tags or even a …

Content truncated to 500 words