The RWTH Aachen German-English Machine Translation System for WMT 2014

Proceedings of the Ninth Workshop on Statistical Machine Translation, pages 157–162, Baltimore, Maryland USA, June 26–27, 2014. c⃝2014 Association for Computational Linguistics The RWTH Aachen German-English Machine Translation System for WMT 2014 Stephan Peitz, Joern Wuebker, Markus Freitag and Hermann Ney Human Language Technology and Pattern Recognition Group Computer Science Department RWTH Aachen University D-52056 Aachen, Germany <surname>@cs.rwth-aachen.de Abstract This paper describes the statistical ma- chine translation (SMT) systems devel- oped at RWTH Aachen University for the German→English translation task of the ACL 2014 Eighth Workshop on Statisti- cal Machine Translation (WMT 2014). Both hierarchical and phrase-based SMT systems are applied employing hierarchi- cal phrase reordering and word class lan- guage models. For the phrase-based sys- tem, we run discriminative phrase training. In addition, we describe our preprocessing pipeline for German→English. 1 Introduction For the WMT 2014 shared translation task1 RWTH utilized state-of-the-art phrase-based and hierarchical translation systems. First, we describe our preprocessing pipeline for the language pair German→English in Section 2. Furthermore, we utilize morpho-syntactic analysis to preprocess the data (Section 2.3). In Section 3, we give a survey of the employed systems and the basic methods they implement. More details are given about the discriminative phrase training (Section 3.4) and the hierarchical reordering model for hierarchical machine translation (Section 3.5). Experimental results are discussed in Section 4. 2 Preprocessing In this section we will describe the modification of our preprocessing pipeline compared to our 2013 WMT German→English setup. 2.1 Categorization We put some effort in building better categories for digits and written numbers. All written numbers 1http://www.statmt.org/wmt14/ translation-task.html were categorized. In 2013 they were just handled as normal words which leads to a higher number of out-of-vocabulary words. For German→English, in most cases for numbers like ’3,000’ or ’2.34’ the decimal mark ’,’ and the thousands separator ’.’ has to be inverted. As the training data and also the test sets contain several errors for numbers in the source as well as in the target part, we put more effort into producing correct English numbers. 2.2 Remove Foreign Languages The WMT German→English corpus contains some bilingual sentence pairs with non-German source or/and non-English target sentences. For this WMT translation task, we filtered all non- matching language pairs (in terms of source lan- guage German and target language English) from our bilingual training set. First, we filtered languages which contain non- ascii characters. For example Chinese, Arabic or Russian can be easily filtered when deleting sen- tences which contain more than 70 percent non- ascii words. The first examples of Table 1 was filtered due to the fact, that the source sentence contains too many non-ascii characters. In a second step, we filtered European lan- guages containing ascii characters. We used the WMT monolingual corpora in Czech, French, Spanish, English and German to filter these lan- guages from our bilingual data. We could both delete a sentence pair if it contains a wrong source language or a wrong target language. That is the reason why we even search for …

Content truncated to 500 words