open-tamil

open-tamil copied to clipboard

Create a video tutorial on using open-tamil

1

tshrinivasan

Provide a web interface for spell checker as Django module. 1. Post contents of a multi-text view to the server 2. Server performs spell checking and returns list of erroneous...

arcturusannamalai

Solthiruthi - framework - get_letters_elementary with attributes 1. get_letters_elementary with attributes lists the uyir + mei letters 2. tag the individual letters as kuril-nedil for uyir 3. tag mei letters...

arcturusannamalai

Solthiruthi - framework - quoted text should be ignored ``` e.g. புதுமையான திரைப் படங்களை ஆவலுடன் கண்டுகளிப்பது மல்லிகாவின் பொழுதுபோக்கு. 'பாஸ்ட் அண்ட் பியூரியஸ்' திரைப்பட குழுவினருடன், அந்த திரைப்படத்தை பார்க்க சென்றார். ``` 1. Tokenizing...

arcturusannamalai

Bad IME checking rule - additional rule

1

Add rule to detect odd letters like, குியீட்டில் ^ தெரியவில்லைை. ^ which is non-letter error.

arcturusannamalai

1. Accept with missing 'இ' (optional) இது பற்றி இன்று hackernews ல் பார்த்தேன். ^ 2. Done correctly (மேல்) 65536-மேல்

arcturusannamalai

It is possible, and legal, to have Tamil input like ொ = ெ + ா , i.e. 1-codept and 2-codept encodings convey the same letter. #grindingteeth #Tamil Ref: http://aspell.net/man-html/Unicode-Normalization.html#Unicode-Normalization ```...

arcturusannamalai

Functions in Tamil for noun-case removal (similar to #47) 1. Identify singular, plural, third person, pronoun modifications of a noun, and extract as root word. Ref: http://learning-tamil.blogspot.com/2009/12/index-of-noun-cases.html Ref: letsgrammar.org

arcturusannamalai

Understand and use Tamil rules from languagetool.org

1

Goal is to reuse the Tamil grammar contributed by Elanjelian Venugopal. 1. Write XML parser to load data from file, Ref: https://github.com/languagetool-org/languagetool/blob/master/languagetool-language-modules/ta/src/main/resources/org/languagetool/rules/ta/grammar.xml 2. Write interpreter for the rules from 1...

arcturusannamalai

With data like n-gram stats for letters of Tamil language, we may provide services for, 1. detecting words in error 2. ranking suggestions based on their letter likelihood

arcturusannamalai