Tamilinayavaani - integrating tva open-source spellchecker with python
Tamilinayavaani - integrating tva open-source spellchecker with python 牀む牀逗巌 牀牀牆牀牀牆 牀牀迦牀朽逗牆牀牀巌牀牆 - 牀牆牀む牀牆牀牀 牀牀園逗朽逗牆牀牆 https://commons.wikimedia.org/wiki/File:Tamil-Virtual-Academy-Copyright-Declaration.jpg 牀む牀逗巌 牀牀牆牀牀牆 牀牀迦牀朽逗牆牀牀巌牀牆 - 牀む牀逗巌 牀牀牀逗牆牀牆 牀牀萎牀朽逗牀橿 http://www.tamilvu.org/ta/content/%E0%AE%A4%E0%AE%AE%E0%AE%BF%E0%AE%B4%E0%AF%8D%E0%AE%95%E0%AF%8D-%E0%AE%95%E0%AE%A3%E0%AE%BF%E0%AE%A9%E0%AE%BF%E0%AE%95%E0%AF%8D-%E0%AE%95%E0%AE%B0%E0%AF%81%E0%AE%B5%E0%AE%BF%E0%AE%95%E0%AE%B3%E0%AF%8D Open-Tamil Python library https://github.com/Ezhil-Language-Foundation/open-tamil Demo Applications on Open-Tamil Python library - http://tamilpesu.us Python port of TamilinaiyaVaani Spellchecker ://github.com/tshrinivasan/Tamilinaiya-Spellchecker Collected 1,53,548 unique tamil nouns https://github.com/KaniyamFoundation/all_tamil_nouns Collected 25,83,000 unique tamil words https://github.com/KaniyamFoundation/all_tamil_words 牀牀牀逗牀牆 牀牀園牆牀牀牆牀牀橿牀牀逗牆 牀牆牀牀迦牀牀鉦牆牀牀橿 https://github.com/KaniyamFoundation/ProjectIdeas/issues Series of blog posts on building an open source spellchecker for tamil - https://goinggnu.wordpress.com/category/spellchecker/
Tamilinayavaani - integrating tva open-source spellchecker with python
- 1. Tamil Internet Conference 2020 TamilInayaVaani - Integrating TVA Open- Source spellchecker with Python T. Shrinivasan, Nithya Duraisamy, Ashok Ramachandran, Manickkavasakam, Arunmozhi, and A. Muthiah
- 2. Who are we? Few Open Source Contributors from Ezhil Foundation Kaniyam Foundation Thamizha Mozilla Tamilnadu Indian Linux Users group, Chennai IndicNLP Having similar dreams in many heads
- 3. Open source Tamil Spellchecker A Dream for many years becoming real
- 4. Existing Efforts Hunspell GNU Aspell LanguageTool.org Open-Tamil Solthiruthi Bloom Filter based spellchecker
- 5. Still long way to go How long?
- 6. Problems with Tamil Spellchecker Infinity Vocabulary Rich in Morphology Agglutinative Free Word Order Sandhi ...
- 7. Few Algorithms Levenshtein distance search
- 10. Norvig Algorithm
- 11. Still not perfect Research continues...
- 12. TamilinayaVaani A Open Source Spellchecker from Tamil Virtual Academy
- 15. TN Govt announcement All the software released in GNU GPL V2 All digital content in CC-BY-SA
- 16. TamilinayaVaani Developed as Desktop Version C# based Limited version of Vaani.neechalkaran.com Cant use in Linux Cant use as command line Cant integrate with other applications
- 18. Porting to Python Python Easy to develop further Easy integration Web applications API Scalable
- 21. The beauty of Open Source More Contributions
- 22. Open-Tamil Python Library The defacto Python library for Tamil Computing Process tamil text Build Games, Tamil Utilities http://Tamilpesu.us
- 24. Integrating with sandhichecker Open-Tamil has a SandhiChecker 40+ rules Added this sandhi Checker to Tamilinayavaani
- 25. Python Packaging Easy install in any OS Pip install tamiliyavaani
- 26. Sample Usage
- 27. Web Interface with TinyMCE Added a good web interface
- 28. Web Interface
- 29. Web Interface
- 30. Web Interface
- 31. Web Interface
- 32. Web Interface
- 33. JavaScript A JavaScript port is on the way
- 34. TODO Provide API Host as a Public website Test and add more rules Set edit distance=2 Find method to yield better alternate
- 35. Word Corpus Collected 1,53,548 unique tamil nouns Collected 25,83,000 unique tamil words https://github.com/KaniyamFoundation/all_tamil_words https://github.com/KaniyamFoundation/all_tamil_nouns
- 36. TODO Clean them manually Build a golden corpus for quick lookup BloomFilter/SymSpell/LSTM and more
- 37. Please Contribute Give Tamil Rules Give Tamil Corpus Write Code Test Document Provide Hosting Donate
- 38. Thanks Muthu Annamalai Tamilnadu Government Neechalkaran Nithya Duraisamy Ashok Ramachandran Manickkavasakam Arunmozhi And All Contributors for Ezhil Foundation, Kaniyam Foundation, Thamizha, IndicNLP and all other Open Source Teams