Morphology analyser based spellchecker - Web version

I prepared a web frontend for the Malayalam spellchecker based on the Malayalam morphology analyser. It is available at https://morph.smc.org.in/spellcheck.html. I had written an article about its technology two years ago. There s also an incomplete extension to LibreOffice. The spellchecker is available as an API too. If you want to use it, please refer a minimal code snippet available at codepen. The quality of spellcheck and suggestions provided depend on the completeness of mlmorph project. [Read More]

Video interviews on SMC and FOSS

While the COVID-19 pandemic is going on, Kerala free software communities started doing interview series with active contributors. The interviews were very informal and was about personal journey and the story behind the projects. And they were all in Malayalam. I gave 3 such interviews in last few weeks. I am going to list them in this blog post. Humans of SMC Series This was an initiative by Tinkerhub, a non-profit organization which promotes the creation of tech-talent focused among youth, especially students. [Read More]

ഡിജിറ്റൽ സാക്ഷരതാ പദ്ധതി

കേരളത്തിന്റെ സാക്ഷരതാപ്രസ്ഥാനത്തിന്റെ തുടർച്ചയായി സാർവത്രിക ഡിജിറ്റൽ സാക്ഷരതാ പദ്ധതിയ്ക്കായി ചില ശ്രമങ്ങൾ 2019 സെപ്റ്റംബർ മുതൽ ഞാൻ നടത്തിയിരുന്നു. സർക്കാറിന്റെയും മറ്റുസ്ഥാപനങ്ങളുടെയും ആഭിമുഖ്യത്തിൽ ആ പദ്ധതി മാർച്ചിൽ തുടങ്ങാനിരിക്കെ കോവിഡ്-19 മഹാമാരി ഗുരുതരമാകുകയും പദ്ധതിയുടെ ഭാവി അനിശ്ചിതത്തിലാവുകയും ചെയ്തു. അതേ സമയം ഇത്തരമൊരു പദ്ധതിയുടെ ആവശ്യകത ഇരട്ടിക്കുകയും ചെയ്തു. പദ്ധതിയെപ്പറ്റി സർക്കാറിന്റെ ഔദ്യോഗികപ്രഖ്യാപനങ്ങൾ വന്നോട്ടെ എന്നുകരുതി ഞാൻ ഒന്നും പബ്ലിക്ക് ആയി എഴുതിയിരുന്നില്ല. പുതിയ സാഹചര്യത്തിൽ ഈ പദ്ധതിയ്ക്കുവേണ്ടിയുള്ള ഞാനടക്കമുള്ള ഒരുപാടുപേരുടെ പ്രയത്നത്തെ രേഖപ്പെടുത്താനാണ് ഈ ലേഖനം. തുടക്കം സ്വതന്ത്ര മലയാളം കമ്പ്യൂട്ടിങ്ങിന്റെ പ്രവർത്തനഫലങ്ങൾ കൂടുതൽ ആളുകളിലേക്കെത്തുകയും അതോടൊപ്പം കമ്പ്യൂട്ടർ, മൊബൈൽ, ഇന്റർനെറ്റ് തുടങ്ങിയവ എല്ലാവരും വ്യാപകമായി ഉപയോഗിക്കാൻ തുടങ്ങുകയും ചെയ്തതോടെ കഴിഞ്ഞ കുറേ വർഷങ്ങളായി എന്റെയും സുഹൃത്തുക്കളുടെയും നല്ലൊരുഭാഗം സമയം ഇതുസംബന്ധിച്ച സംശയനിവാരണത്തിനും സഹായങ്ങൾക്കുമായി മാറ്റിവെക്കേണ്ടിവരുന്നുണ്ട്. [Read More]

Life in the time of lockdown

It has been more than a month since lockdown is announced in Kerala. The world has changed and never going to be same. I thought of leaving a write up here, mainly for future self to recollect how did I spend this time at home. Sunday, March 21st was general curfew in India. On the same day, Kavya’s grand father passed away at Thodupuzha. Since travel was not allowed on the day, we could not travel from Thiruvananthapuram to Thodupuzha. [Read More]

Manjari version 1.800 released

A new version of Manjari Malayalam typeface is available now. Version 1.800 adds tabular number and slashed zero opentype features along with bug fixes. New version of the font is available at: https://smc.org.in/fonts/#manjari Tabular numbers The Kerala health department publishes daily COVID-19 reports and they use Manjari(example). Sometimes the numbers in table in Manjari font is slightly difficult to read when you want to compare the numbers in columns across rows. [Read More]
fonts 

Chilanka font version 1.500 released

A new version of Chilanka Malayalam typeface is available now. Version 1.500 adds glyphs required to support International Alphabet of Sanskrit Transliteration New version of the font is available at: https://smc.org.in/fonts/#chilanka Chilanka was the first typeface I designed in 2014 for Malayalam. The usecase I had in mind while designing it was to use it in comic or non-serious contexts. But once it was released, contrary to my expectation, people used for serious Malayalam writing. [Read More]
fonts 

Procrustes Analysis Based Handwriting Recognition

Many months back, I started an experiment to see if Malayalam handwriting recognition can be done in a non-machine learning based approach. This blog post explains the approach, the work done so far and results. Handwriting recognition can be done while the user is writing(called online handwriting recognition) and recognizing a sample somebody wrote in the past(offline recognition). Online and offline recognition problems are different problems. This is because, in online recognition, it is possible to capture additional details such as pen up, pen down, pen movement directions and rotations. [Read More]

Professional student summit 2020

On February 15, I attended the Professional student summit organized by higher education department of Kerala. The summit aims to provide a venue to interact with professionals with the students. Around 2000 students from 2nd to 4th semesters from different colleges of law, engineering, medicine, agriculture, fisheries, veterinary and management in Kerala attended the summit. The Chief Minister and Minister for Higher Education also attended the Summit. This is the second edition of the event. [Read More]
Talks 

POS Tagging: A review of BIS POS tagset and ILCI-II Malayalam Text Corpus

The Bureau of Indian Standards(BIS) had published a Part of Speech(POS) tagset for Indian languages. POS is the process of assigning a part of speech marker to each word in a given text. In this article, I am reviewing the tag set defined in it. While developing mlmorph project I had explored a candidate POS tagging schema for Malayalam. I did not choose BIS tagset for the reasons I am going to explian in this article. [Read More]