Hi, I am glad you found this piece of software interesting. If you do not have access to the journal you can download a copy of the paper from my personal web page: http://www.dlsi.ua.es/~fsanchez/pub/pdf/sanchez-martinez11a.pdf
As you say the software might be somehow outdated in terms of automake and also in how it access the binarised phrase table produced by Moses. I will happy to update the repository with any updates you send me. Please, do not hesitate to contact me for any other question you might have, I'll be happy to help. Cheers -- Felipe El 03/08/11 07:09, Tom Hoar escribió: > Felipe, > > I have a few projects where this could be helpful. I noticed that the > google source is a bit outdated with automake. If we update the changes, > we'll feed them back to you to update the repository. > > The google code doesn't have much documentation. Can you point me to a > link for your reference paper? I couldn't find it on mt-archive.info. > > Thanks, > Tom > > > On Tue, 02 Aug 2011 16:24:33 +0200, Felipe Sánchez Martínez > <[email protected]> wrote: >> Hello Kaveh, >> >> You may be interested in using the software implementing the method >> described in this paper: >> >> Sánchez-Martínez, F., R.C. Carrasco. Document translation retrieval >> based on statistical machine translation techniques. In Applied >> Artificial Intelligence 25(5):329-340 >> >> The software can be downloaded from >> http://code.google.com/p/doctrans/downloads/list and you could use it >> together with Moses and the Apache Lucene Search Engine to match >> documents in one language to its translation into the other language. >> Pretty match what it was done in the experiments reported in the >> paper >> above. >> >> If you finally use that software, I will be happy to help you in >> dealing >> with problem you might encounter. >> >> Cheers >> -- >> Felipe >> >> >> >> El 02/08/11 15:04, Kaveh Taghipour escribió: >>> Hi, >>> >>> Excuse me if this is not related to the main purpose of the mailing >>> list. >>> >>> Are there any freely available software for aligning documents? I >>> have >>> two sets of documents (1500 and 2000 documents) in two different >>> languages and I need to find an alignment between these two sets. So >>> I >>> need to know which files are linked. >>> >>> In addition, documents are not exact translations of each other and >>> are >>> not parallel. >>> >>> Thanks, >>> Kaveh Taghipour >>> >>> >>> _______________________________________________ >>> Moses-support mailing list >>> [email protected] >>> http://mailman.mit.edu/mailman/listinfo/moses-support > > > _______________________________________________ > Moses-support mailing list > [email protected] > http://mailman.mit.edu/mailman/listinfo/moses-support -- Felipe Sánchez Martínez Dep. de Llenguatges i Sistemes Informàtics Universitat d'Alacant, E-03071 Alacant (Spain) Tel.: +34 965 903 400, ext: 2966 Fax: +34 965 909 326 http://www.dlsi.ua.es/~fsanchez _______________________________________________ Moses-support mailing list [email protected] http://mailman.mit.edu/mailman/listinfo/moses-support
