These are chat archives for cltk/cltk

9th
Mar 2018
Gbetondji Dovonon
@jean72human
Mar 09 2018 04:19
Hello. I am a second year undergraduate student at Ashesi University, Ghana. I have experience in web development (javascript, React, Django and rest framework, GraphQL) and I am interested in nlp. I would like to contribute to the work done on the cltk-frontend and/or draftJS. Please how can I get started?
Satyarth Vaidya
@SatyarthV
Mar 09 2018 08:21
Welcome @jean72human to CLTK ! , please visit this page : https://github.com/cltk/tutorials as well as there is a "Getting Started" wiki page to help you going .
aboelhamd
@aboelhamd
Mar 09 2018 09:35
Hello , Is there any Arabic mentors in CLTK this year ?
Thanks in advance .
Kyle P. Johnson
@kylepjohnson
Mar 09 2018 14:32
@vmoutzouri I think the best thing to do now is to do the beginner's tasks (in the wiki) for the languages you know -- Greek, surely -- others too? And see how the tool works for you. We have a lot of stuff for Greek, however some of it is not as good as it could be
@vmoutzouri This is not a GSoC project, probably, however I would very much like to see our docs include instructions how to use SyntaxNet [https://github.com/dsindex/syntaxnet] and its pre-trained models based upon data from the Universal Dependencies project [http://universaldependencies.org/]. Ancient Greek and Latin are in there (as are some others, Old Church Slavonic, Old French). See this old issue for a little bit more info: cltk/cltk#505
Kyle P. Johnson
@kylepjohnson
Mar 09 2018 16:48
@/all I have just answered a question for @aboelhamd which will be helpful to most of you …

Before contacting us directly, please do the first two steps first, then we can connect you directly with the appropriate mentor:

1) Do the Beginners' exercises, with Classical Arabic: https://github.com/cltk/cltk/wiki/Beginners'-exercises
2) Write a draft proposal according to our GSoC propsosal template: https://github.com/cltk/cltk/wiki/GSoC-proposal-template . For Arabic, you'll want to focus on what NLP processing you will be able to add for classical arabic (things like word tokenization, pos tagging, etc). If training data is required, it is critical that you explain what free data you will use.
@aboelhamd I will actually move this conversation to the channel for the python project

@diyclassics and I can answer basic questions about the language projects, however we would not necessarily be the mentor to your proposed project.
aboelhamd
@aboelhamd
Mar 09 2018 18:37
Thank you Kyle , I will do the two steps and I will be back to you soon .