Sunday, August 6, 2017

Links to resources relevant to Thai Language Processing


  • lexto program : https://github.com/telember/lexto/tree/master/src/main/java/lexto
  • RLongLexTo package for R : https://github.com/slphyx/RLongLexTo
  • R source code for RLongLexTo : https://github.com/slphyx/RLongLexTo/tree/master/R
  • SWATH https://linux.thai.net/projects/swath
  • https://github.com/pichaio/thainltk


Friday, May 13, 2016

New English parsing tool

Google just released a very accurate English text parser, SyntaxNet, as Open Source.
The Google Research Blog article below provides useful information on it.

Ref: Google research blog


Wednesday, October 21, 2015

Useful tool, NegEx

Here are some tool(s) & concept(s) I found and would like to take note.

NegEx and links to an article, and another.

(to be continued and updated)

Same 'NLP' word, but different interpretations by people in different fields

I found this useful blog by chance 'text-analytics101.com' and appreciated the author's provision of useful insights and information. I am sure I want to go back and read some more blogs there.

I want to note down this useful piece of her writing which mentioned of different interpretations of the term NLP by researchers or professionals in different fields, namely  computer science, biomedical informatics, and information systems. When I worked in bioinformatics few years back, I did not know this. Her blog gave me the clue I should have known, but I did not.

First post: purpose of Akrasom blog

I have been fascinated in words and knowledge. They are in the back of my mind for decades. Now I don't know how much I am going to delve into these fields with my limited free-time but will give it a try. I hope my note-taking of my learning of new fields may benefit someone some time later. That's why I am going to write my blogs mainly in English, although I have my eyes on applications of those into Thai language.

I chose to name this blog 'Akrasom'. It 's a combination of 2 Sanskrit words, Akra (letters / alphabets, and also means 'big', if one would think that alphabets can combine to form millions of words) and Asram (a quiet forest shelter of an ascetic). So my meaning is that this blog is a quiet place where I take note of my study, contemplation, and try to develop my idea regarding the vast domain of words and knowledge (i.e. text, and knowledge processing).