Éva Mújdricza-Maydt

CRFalign

CRFalign: a CRF-based sentence-aligner written in Java, in collaboration with Huiqin Körkel-Qu.

The downloadable compressed folder (3.0 MB) entails

• the source code
• readme
• setup
• required external resources (except software listed below)

To use the aligner you additionally need the following software:

• TreeTagger
• Wapiti

Publication

• Éva Mújdricza-Maydt, Huiqin Körkel-Qu, Stefan Riezler, Sebastian Padó (2013): High-Precision Sentence Alignment by Bootstrapping from Wood Standard Annotations. The Prague Bulletin of Mathematical Linguistics No. 99, pp. 5-16. [pdf]

Sample data for the aligner

• OpenSubtitles (315 German-English file pairs)
• Gutenberg (114 German-English file pairs)

Contact

Mail to me and Huiqin