@/all Instead of beginning work on tasks like adding corpora, your time is better spent doing research on available, ancient resources. If you have some answers to the 6 questions at the end of our blog post [http://cltk.org/blog/2018/12/30/under-resourced-languages-cltk.html] then you can email me and I'll put you in touch with a potential mentor.
I found this can we use this? @Seenivasanseeni , @Erikishiru
i was not able to go through
find some issues and get working
I want to participate in GSOC this summer.I have done basic tutorials and excercises. I have read the blog http://cltk.org/blog/2018/12/30/under-resourced-languages-cltk.html and I have few queries - 1. Is it necessary to add more datasets or we can work with the old datasets(like greek and latin ) and add new algorithms or make the older ones more effective ? 2. Can I work on a Language like greek/Latin/Older versions of Sanskrit/Hindi for that matter to apply NLP algorithms and do things like POS Tagging, Translation and other stuff ? 3. If I have the answer to 6 questions that the blog asks, where do i put forward those to you ?
This year, we do NOT want small contributions. We want you to focus on making very good project proposals, instead.
@Erikishiru We prefer that you not give the other students directions.
For example - I did some research about the maithili language. It is primarily spoken in Eastern parts of India and Nepal. The original script for maithili is 'Tirhuta'. But, since 20th century 'devnagiri' script is preferred by the writers. 'Tirhuta' is not digitized yet. And now all of the digitized maithili texts are in 'devnagiri' script.
@sainimohit23 no, they do not. For example, last summer's cuneiform/akkadian project was entirely done in the Latin alphabet. this is because the scholars who digitize these texts choose the Latin alphabet (and we must use what they have created).
could someone direct me to the right resources
Welcome to CLTK @apoos-maximus ! you can have a look at the beginners-excercieses and also follow up quickstart . :smile:
?
in the documentation corpus refers to a knowledge database about a particular language right ?
and corpora refers to collection of such databases ?
am i being right in the interpretation of words corpus and corpora ?
Hey CLTK society. I am a noob here! I am a B.Tech undergraduate student at National Institute of Technology Karnataka(NITK). I am a open source enthusiast and have research experience in Language Processing from IISc Bangalore. Bengali is one of the most ancient and patronized language of India and boasts of works that achieved milestones at the world stage like Nobel Prize for literature and Academy Awards at The Oscars for the film "Pather Panchali"(originally made in Bengali). A bit amazed to see that it lacks contribution in this sphere but equally enthusiastic about showcasing my desire in contributing for the same. Can anyone help me around with the way I can get a head start. I am willing to join the organisation and start the contributions with a long term motive of helping the organisation and also contribute for GSoc 19'
Hi All
I am a 4th year UG student in Economics Department at IIT Kanpur. I was always interested in the study of ancient languages and would like to contribute. But, I am not familiar with NLP but have done courses and projects on ML. I am interested in learning NLP too.
Can please someone suggest me some NLP sources, if required and show to start contributing with my current knowledge?
Thanks :)
I am a 4th year UG student in Economics Department at IIT Kanpur. I was always interested in the study of ancient languages and would like to contribute. But, I am not familiar with NLP but have done courses and projects on ML. I am interested in learning NLP too.
Can please someone suggest me some NLP sources, if required and show to start contributing with my current knowledge?
Thanks :)
@hearot Thank you for letting us know about your project! Lately a CLTK contrib has been working on readers, too, since this has been a weak spot for our project. See two recent PRs here, though we have not written docs yet:
- cltk/cltk#846 (merged)
- https://github.com/cltk/cltk/pull/854/ (not yet merged, has docs)
I am curious: What are the goals for thelatinlibrary project? Who do you imagine your users will be and how will they use it?
Thanks again @hearot please stay in touch. There are so few digital classicists that we should know each other :)
@isohamnemesis Bengali has a great pre-modern history, but if you're interested in doing a GSoC project, you need to prove to us that there exists enough data to write algorithms. Please see our latest blog post on cltk.org -- it has everything you need to know
@anshul96go I'll be honest, a GSoC proposal might be difficult for you, this year. The bar for our project is unusually high, since a student needs, at least, (a) a little NLP knowledge and (b) some understanding of an ancient/classical language. I feel that ML is of secondary importance, in particular as a way to assist doing NLP better.
I can assure you about the dataset because I have contacted one of the professor named Prasanta Kumar Ghosh of IISc Bangalore(Asia's largest science and engineering research institute) who has a significant contribution in the NLP society and has large corpuses of dataset of the Bengali Language!