[Corpora-List] English to German Alignment tool

Johannes Hellrich johannes.hellrich at uni-jena.de
Tue Feb 26 13:02:49 CET 2013


Hi Negacy,

You probably want phrase alignment, not only word alignment. The latter simply aligns tokens, so it wouldn't help you with endoplasmic reticulum --> endoplasmatische Retikulum but only with endoplasmic --> endoplasmatische and reticulum --> Retikulum Moses/GIZA++ is still the right tool. Regards,

Johannes

PS: You could be interested in a challenge I help organizing: https://sites.google.com/site/mantraeu/clef-er-challenge

On 02/25/2013 08:54 PM, Hailu, Negacy wrote:
> Hi,
> I have a parallel English-German sentences and I was wondering if there is a tool that can help me get word alignments.
> For example:
> English: The endoplasmic reticulum (ER) is an organelle of cells in eukaryotic organisms that forms an interconnected network of membrane vesicles
> German: Das endoplasmatische Retikulum (ER) ist eine Organelle von Zellen in eukaryotischen Organismen, die ein miteinander verbundenes Netzwerk von Membranvesikeln bildet.
>
> The --> Das
> endoplasmic reticulum --> endoplasmatische Retikulum
>
>
>
>
> Thanks.
>
> Negacy.



More information about the Corpora mailing list