Publication at Faculty of Mathematics and Physics |
2011
Abstract
In this paper we present our attempt to improve machine translation of named entities by using Wikipedia. We recognize named entities based on categories of English Wikipedia articles, extract their potential translations from corresponding Czech articles and incorporate them into a statistical machine translation system as translation options.
Our results show a decrease of translation quality in terms of automatic metrics but positive results from human annotators. We conclude that this approach can lead to many errors in translation and therefore should always be combined with the standard statistical translation model and weighted appropriately.