These are chat archives for cltk/cltk

Mar 2016
Ankush Khandelwal
Mar 01 2016 00:45
Hello, I am a computer science undergraduate student and New to this organization. I would like to work on the project "Extend CLTK core to new language" as a GSOC project under CLTK. Is there a particular Mentor for this project?
Kenji Yamauchi
Mar 01 2016 04:27
Hello, I am a 2nd grade graduate student majoring NLP and a newbie to this organization. I would like to participate in the GSoC project "Add corpora for a Classical language", especially to import a Sumerian corpus ETCSL( How should I start it?
Jiawei Wu
Mar 01 2016 10:36
Hi, I am a junior undergraduate at Tsinghua University, and my main research interests lie on natural language processing and machine learning. I have used Stanford Parser for my NLP coursework, and I think that Make dependency grammar taggers for Greek and Latin project really attracts me a lot. Hope I can contribute to it successfully. May I email you directly to discuss this project @kylepjohnson ? Thank you for your time.
Nishant Suman
Mar 01 2016 11:29
Hi, I'm very interested to contribute in this organisation. I am a junior undergraduate Computer Science student at Jaypee University of Information Technology. I would like to work on the project 'Add corpora for a Classical language'. I don't have much knowledge about NLP but I know an ancient language 'Sanskrit'. How should I start @kylepjohnson ? Thank you for your valuable time.
Kyle P. Johnson
Mar 01 2016 14:58
@Leyonce Please contact @lukehollis directly (by Gitter or ) for JavaScript and other website tasks. I recommend you send him links to some of the work you have done, to help him get an idea of good projects for you.
@ankush1995 I love to hear you're interested in helping CLTK support a new language. GSoC or not, this is very, very important work. See here our List of Classical Languages – do you have experience with any of these? Please email me directly ( ) and we can talk more.
Kyle P. Johnson
Mar 01 2016 15:03
@yustoris Same as what I just wrote to @ankush1995. Sumerian support would be simply phenomenal. About this particular corpus, we first need to make sure that we can legally repost their data on GitHub. Do you know of any other Sumerian corpora that are free? And if you are able, please contact the leaders of the project, and cc me, and we can discuss with them a way to get their data.
@wujw13 Yes! We need help with dependency parsing. Please do email me and I can explain what I have tried (and failed) to do in the past. This will perhaps be too easy for you, so we can talk about a variety of other parsing and tagging code that you could help us with.
@Nishant23 Please do contact me by email. I will want to hear from you about free Sanskrit data sets that we can host on GitHub. Here's what we currently have for Greek and Latin – . Other than data sets, I recommend looking at our code to get an idea of how to follow the pattern already in place.