Statistical Machine Translation of Croatian Weather Forecasts: How Much Data Do We Need?

Nikola Ljubešić, Petra Bago, Damir Boras

Abstract


This research is the first step towards developing a system for translating Croatian weather forecasts into multiple languages. This step deals with the Croatian-English language pair. The parallel corpus consists of a one-year sample of the weather forecasts for the Adriatic, consisting of 7,893 sentence pairs. Evaluation is performed by the automatic evaluation measures BLUE, NIST and METEOR, as well as by manually evaluating a sample of 200 translations. We have shown that with a small-sized training set and the state-of-the-art Moses system, decoding can be done with 96% accuracy concerning adequacy and fluency. Additional improvement is expected by increasing the training set size. Finally, the correlation of the recorded evaluation measures is explored.

Keywords


statistical machine translation, automatic evaluation, manual evaluation, correlation between evaluation measures

Full Text:

PDF


DOI: https://doi.org/10.2498/cit.1001917

Creative Commons License
This work is licensed under a Creative Commons Attribution-NoDerivatives 4.0 International License.

Crossref Similarity Check logo

Crossref logologo_doaj