El dt 22 de 03 de 2011 a les 03:31 -0700, en/na mirlan va escriure: > Hi, > My name is Mirlan Ipasov .gantu on IRC, Fedora Ambassador, completed > MTech Artificial Intelligence in HCU Hyderabad,India. Doing PhD in > IAAU (http://www.iaau.edu.kg),Kyrgyzstan . > > Worked as a Software Developer in BaraanSoft, India. > Programming skills: Java,python, C. > > Language Skills: > native:Kyrgyz, Russian,Turkish,near-native:English > some:Kazakh,Uzbek > > I want to create Turkish-Kyrgyz language pair in Apertium. > Kyrgyz,Kazakh and Uzbek languages are 3 from 4 major Central Asian > languages.And they have huge similarities in grammar and morphological > structure. From these 3 Central Asian languages I found only > tt(tatar)-kk(kazakh) language in incubator and it is also not > complete. > A lot of anthropological and Historical books and information about > Central Asia are available in Turkish(tr) language. If this project > could be completed successfully it will be huge help for Universities > who are working in Anthropology, History and Central Asian literature. > Because of similarities of Kyrgyz,Kazakh and Uzbek languages tr-ky > language pair could be start up for new language pairs like > tr-kk,tr-uz. > > > Thanking you, > Mirlan Ipasov > > >
Hi, I think this has great potential as a project. It will be hard though. Things you need to start thinking about: * Will you use an off-the-shelf morphological analyser for Turkish (such as trmorph), or will you work on your own ? ** If you use trmorph, how will you trim the lemmas to the contents of the bilingual dictionary ? * For the analyser/generator of Kyrgyz you will have to work from scratch. We would ideally like to see a portion of this development done before the project starts. It isn't clear to us how to make analysers for Turkic languages, and we would like to see that you can master the necessary tools. * How will you work on the disambiguation of Turkish ? Will you use a combination of constraint grammar and apertium-tagger ? * How will you make the bilingual lexicon ? I presume there are few freely-available (e.g. open-source/free software) dictionaries, so you will probably have to build your own. Someone with experience of Apertium can do ~400 words in a day, so we would like to see a start on the lexicon to make sure you understand the problems involved. * It would be a good idea to start looking at any transfer (syntactic/morphological) issues between the two languages. Here are some good places to start. As this would be the first project for Turkic languages we will want to see that the person taking it on is capable and familiar with the issues. Best regards, Fran ------------------------------------------------------------------------------ Enable your software for Intel(R) Active Management Technology to meet the growing manageability and security demands of your customers. Businesses are taking advantage of Intel(R) vPro (TM) technology - will your software be a part of the solution? Download the Intel(R) Manageability Checker today! http://p.sf.net/sfu/intel-dev2devmar _______________________________________________ Apertium-stuff mailing list [email protected] https://lists.sourceforge.net/lists/listinfo/apertium-stuff
