Apertium-IceNLP: A rule-based Icelandic to English machine translation system

We describe the development of a prototype of an open source rule-based Icelandic→English MT system, based on the Apertium MT framework and IceNLP, a natural language processing toolkit for Icelandic. Our system, Apertium-IceNLP, is the first system in which the whole morphological and tagging component of Apertium is replaced by modules from an external system. Evaluation shows that the word error rate and the positionindependent word error rate for our prototype is 50.6% and 40.8%, respectively. As expected, this is higher than the corresponding error rates in two publicly available MT systems that we used for comparison. Contrary to our expectations, the error rates of our prototype is also higher than the error rates of a comparable system based solely on Apertium modules. Based on error analysis, we conclude that better translation quality may be achieved by replacing only the tagging component of Apertium with the corresponding module in IceNLP, but leaving morphological analysis to Apertium.