セッション概要
Understand what exactly NLP (Natural language processing) is, and what dynamic possibilities it contains, for the (near) future. We'd be also discussing the anusaaraka system, which makes the text in one Indian language accessible in another Indian language. Explore with me, how we can do this, for the Japanese language (日本人). The output can also be post-edited by a trained user to make it grammatically correct in the target language.
What the audience can bring back: Machine translation convert one language to another language, learn more about it! The audience will learn more about why Anusaaraka aims to bridge a language barrier by allowing a user to enter an English text into Anusaaraka and read it in an Indian language of their choice (Japanese). When any machine does that work they need big parallel corpus that can help for making some rules and disambiguate many senses, let's look into that!
講師
Jasveen S
セッション情報
- 担当:
- Anusaaraka Lab, LTRC (Language Technologies Research Centre), IIIT Hyderabad (International Institute of Information Technology Hyderabad)
- レベル:
- 入門編
- 対象者:
- Beginner (Learnt Python grammar and know how to use the standard libraries in Python tutorials)
- 前提知識:
- audience need knowledge of Having knowledge of Computation and Language (cs.CL) is a plus. Nothing too specific is a prerequisite. Interest in Python (MT- Machine translation) is obviously important. Audience Level of knowledge required in the field of talk: 0% (Audience has little expertise (might have heard of presentations))
- カテゴリー:
- computational linguistics/expert systems/language translation/natural language processing
