Apertium-fin-eng-rule-based shallow machine translation for WMT 2019 shared task

Abstract

In this paper I describe a rule-based, bidirectional machine translation system for the Finnish-English language pair. The original system is based on the existing data of FinnWordNet, omorfi and apertium-eng. I have built the disambiguation, lexical selection and translation rules by hand. The dictionaries and rules have been developed based on the shared task data. I describe in this article the use of the shared task data as a kind of a test-driven development workflow in RBMT development and show that it suits perfectly to a modern software engineering continuous integration workflow of RBMT and yields big increases to BLEU scores with minimal effort. The system described in the article is mainly developed during shared tasks.