Catalan-English Statistical Machine Translation without Parallel Corpus: Bridging through Spanish

This paper presents a full experiment on large-vocabulary Catalan-English statistical machine translation without an English-Catalan parallel corpus, in the context of the debates of the European Parliament. For this, we make use of an English-Spanish European Parliament Proceedings parallel corpus and a Spanish-Catalan general newspaper parallel corpus, both of which of more than 30 M words. Given the language proximity between Spanish and Catalan languages, we investigate the cost of using Spanish as a bridge towards large-vocabulary Catalan-English translation in a wholly automatical statistical machine translation framework. Experimental results are promising, as the achieved translation quality is nearly equivalent to that of the Spanish-English language pair, practically carrying SMT research for the Catalan language to the level of more prominent language, in terms of data availability.