Publication

Qualitative: Python Tool for MT Quality Estimation Supporting Server Mode and Hybrid MT

Eleftherios Avramidis

In: Jan Hajič (editor). The Prague Bulletin of Mathematical Linguistics (PBML) 106 Pages 147-158 Charles University 10/2016.

Abstract

We are presenting the development contributions of the last two years to our Python open-source Quality Estimation tool, a tool that can function in both experiment-mode and online web-service mode. The latest version provides a new MT interface, which communicates with SMT and rule-based translation engines and supports on-the-fly sentence selection. Additionally, we present an improved Machine Learning interface allowing more efficient communication with several state-of-the-art toolkits. Additions also include a more informative training process, a Python re-implementation of QuEst baseline features, a new LM toolkit integration, an additional PCFG parser and alignments of syntactic nodes.

Projekte

Weitere Links

art-avramidis.pdf (pdf, 293 KB)

German Research Center for Artificial Intelligence
Deutsches Forschungszentrum für Künstliche Intelligenz