Difference between revisions of "GSoC/2013/Project ideas"
(- Converting indic processing modules currently in SILPA into Jquery library)
|(2 intermediate revisions by 2 users not shown)|
Latest revision as of 05:20, 26 January 2017
- 1 Mentors
- 2 Ideas for Google Summer of Code 2013
- 2.1 A spell checker for Indic language that understands inflections
- 2.2 Indic rendering support in ConTeXt
- 2.3 SILPA BASED
- 2.3.1 Port remaining modules to the new flask based Silpa
- 2.3.2 Provide REST API for new flask based Silpa, including conversion of templates to this REST API from JSON RPC
- 2.3.3 Separate templates from SILPA and have it inside modules packaged for pypi
- 2.3.4 add Urdu/Arabic support for all modules in SILPA.
- 2.3.5 Improving cross language transliteration system.
- 2.3.6 Internationalize SILPA project with Wikimedia jquery projects , Improve the webfonts module in Silpa using jquery.webfonts and provide more Indic and complex fonts as part of it
- 2.4 Building a system and API's for accessing and upadating Malayalamgrandham Bibligiography Data
- 2.5 Adding Braille Keyboard layouts for Indian Languages to m17n Library
- 2.6 Developing Malayalam Calendar Support
- 2.7 Language model and Acoustic model for Malayalam language for speech recognition system in CMU Sphinx
- 2.8 Enhancement of Indic Language Support in Scribus
- Santhosh Thottingal (santhosh on irc.freenode.net)
- Baiju M (baijum on irc.freenode.net)
- Praveen A (j4v4m4n on irc.freenode.net)
- Rajeesh K Nambiar (rajeeshknambiar on irc.freenode.net)
- Vasudev Kammath (copyninja on irc.freenode.net)
- Jishnu Mohan (jishnu7 on irc.freenode.net)
- Hrishikesh K.B (stultus on irc.freenode.net)
- Anivar Aravind (anivar on irc.freenode.net)
- Anilkumar K V (anilkumar on irc.freenode.net)
- Sajjad Anwar (geohacker on irc.freenode.net)
- Deepa V Gopinath (deepagopinath on irc.freenode.net)
- jain Basil (jainbasil on irc.freenode.net)
Ideas for Google Summer of Code 2013
- Please Read the FAQ
Apart from the following ideas , you can propose your own ideas
If you want to propose an idea, please do it in project mailing list>
A spell checker for Indic language that understands inflections
SILPA project has a spellchecker written using python with a not so simple algorithm. But still it is not capable of handling inflection and agglutination occurring in Indian languages especially south Indian languages. The dictionary we have for Malayalam spellchecker have about 150000 words. Of course we can expand the dictionary, but that doesn't have much value since words can be formed in Malayalam or Tamil etc by joining multiple words. In addition to that, words get inflected based on grammar forms(sandhi), plural, gender etc. Hunspell has a system to handle this, but so far nobody succeeded in getting it working for multi level suffix stripping as required for Malayalam. Some times a Malayalam word can be formed by more than 5 words joining together. We will need a word splitting logic or a table taking care of all patterns. The project is to attempt solving this with hunspell. If that is not feasible(hunspell upstream is not active), develop an algorithm and implement it.
Recently Tamil attempted developing a spellchecker using Hunspell with multi level suffix stripping. You can see the result here https://github.com/thamizha/solthiruthi. Our attempt should be first to use Hunspell to achieve spellchecking with agglutination and inflection. Probably it will require lot of scripting to generate suffix patterns, we can ask help from existing language communities too. If Hunspell has limitation with multi level suffxes- sometimes Indian languages require more than 5 levels of suffix stripping, we need to document it(bug and documentation) and try to attempt python based solution on top of SILPA framework.
- Savannah Task
- Expertise required: Average level understanding of grammar system of at least one Indian language
- Complexity: Advanced
- Mentor : Santhosh Thottingal
Indic rendering support in ConTeXt
ConTeXt is another TeX macro system similar to LaTeX but much more suitable for design. To find more information about ConTeXt, see the wiki http://wiki.contextgarden.net/Main_Page. ConTeXt MKII have Indic language rendering support using XeTeX. but MKII is deprecated, and the new MKIV backend doesn't support Indic rendering yet. The aim of this project is to add support to Inidic rendering to ConTeXt MKIV. XeTeX is using Harfbuzz to do correct Indic rendering.
- Savannah Task
- Expertise required: Understanding of the TeX system, experience in either LaTeX or ConTeXt and basic understanding of Indic language rendering. MKIV uses Lua, familiarity with Lua, opentype specifications or Harfbuzz will be added advantage.
- Mentor : Rajeesh K Nambiar
- More Details: ConTeXt mkii (deprecated) can work with XeTeX backend for Indic rendering. Here is a sample file:
\usemodule[simplefonts] \definefontfeature[malayalam][script=mlym] \setmainfont[Rachana][features=malayalam] \starttext മലയാളം \TeX ഉപയോഗിച്ച് ടൈപ്പ്സെറ്റ് ചെയ്തത് \stoptext
Generate the output using command
texexec --xetex <file.tex>
Port remaining modules to the new flask based Silpa
Project: Silpa is being re-written using flask framework. Core part is almost complete. But most of the sub modules written under old framework are need to be ported to new framework.
Mentor : Vasudev/ Jishnu
Provide REST API for new flask based Silpa, including conversion of templates to this REST API from JSON RPC
Project: Silpa is now relying on JSONRPC. We need to, either completely move to REST API or provide REST API as an additional feature.
Mentor : Vasudev/Jishnu
Separate templates from SILPA and have it inside modules packaged for pypi
Project: The templates used as User Interface is part of SILPA. this should be separated and should come as a part of individual modules.
this should give more idea on it
Mentor : Vasudev/Jishnu
add Urdu/Arabic support for all modules in SILPA.
Mentor : Vasudev
Improving cross language transliteration system.
Currently only Kannada and Malayalam are perfect rest all are first converted to Malayalam then to English due to lack of language internal. Also currently for English to Indic we use CMUDict so transliteration capability is limited to words in CMUDict only probably we could develop better method for English to Indic transliteration
CLDR has transliteration data for Indic languages. We can explore it and see the feasibility. For an intermediate representation of the scripts either IPA can be used or ISO 15919 standard can be used. All these must be supplemented with exception rules and special case handling to achieve more perfect result.
Mentor : Vasudev/Jishnu
Internationalize SILPA project with Wikimedia jquery projects , Improve the webfonts module in Silpa using jquery.webfonts and provide more Indic and complex fonts as part of it
Internationalize SILPA :- SILPA project has many Indic language applications, but as of now, if somebody want to input in Indian languages, there is no built in tool in it. Similarly, the application is not internationalized. Both of these can be achieved by using the jquery.ime and jquery.i18n libraries from Wikimedia. A sample implementation is avaliable in our website. The i18n should be in the SILPA flask framework with a nice templating system. Similarly the interface should have webfonts using jquery.webfonts library.
Improve the webfonts :-
- Currently Silpa provides 36 webfonts. add more fonts to this collection.
- Rewrote webfonts module to use the features of jquery.webfonts
- reate a repo as per jquery.webfonts specification
- Provide a clean api so that other websites can use our webfonts in their websites
- Document the usage
- Provide font preview and download options
Expertise required: jQuery, css, html5, Python , flask , technical understanding about fonts
Mentor : Hrishikesh K B / Sajjad Anwar
Building a system and API's for accessing and upadating Malayalamgrandham Bibligiography Data
Malayala Grantha Vivaram is a project intended to make available reliable bibliographic information on all Malayalam books published in Kerala and elsewhere. This Open data set contains Complete bibliography data from first Impression to 1995. This project wants to add following features to Malayalagrandham DB and build it as a bibliography web service
- Facility for adding/linking copyright expired books to malaylagrandha vivaram
- Adding ISBN & ISBN based seller discovery
- Building Interface for Publishers through with they can contribute their publication bibliography .
- Similar module for Libraries . That will be added to found in library section of each book
- A module for building qr code of bibliography with a malayalagrandham link
- Crowd sourced way for input and an approval queue interface for submissions.
- MARC21 and MARCXML support
- A dynamic visualisation interface for book information browsing
- proper API , and app work flow documentation
Expertise required: Django / Ruby on Rails
Adding Braille Keyboard layouts for Indian Languages to m17n Library
Project is building support for Bharati Braille keyboard layouts in GNU/Linux systemes. Bharati Braille standard is the official Braille standard in India. A regular QWERTY keyboard is used for data entry. SDF-JKL keys are used for six dots of Braille. This support need to be built as m17n layouts. This will enable visually challenged people who studied braille layouts to use GNU/Linux systems easily with the help of Audio feedback from TTS
Mentor: Anilkumar K V
Developing Malayalam Calendar Support
This project is to build Malayalam Calendar support to KDE. Korganiser have support for many calendars like Saka, Hijri, Jalali. The project is to build support for Malayalam Calendar (Kolla Varsham)
Following tasks are part of this work .
- Building Malayalam (kollavarsham) Calendar support to KDE/KOrganiser.
- Add holidays and other special times.
- Understanding of Astronomical Algorithms
- Build KDE from source
- Familiarize with how Saka and other calendars are done.
Mentor: Praveen A, Mahesh M
Language model and Acoustic model for Malayalam language for speech recognition system in CMU Sphinx
CMU Sphinx is a large vocabulary, speaker independent speech recognition codebase and suite of tools, which can be used to develop speech recognition system in any language. To develop an automatic speech recognition system in a language, acoustic model and language model has to framed for that particular language. Acoustic models characterize how sound changes over time. It captures the characteristics of basic recognition units. The language model describes the likelihood, probability, or penalty taken when a sequence or collection of words is seen. It attempts to convey behavior of the language and tries to predict the occurrence of specific word sequences possible in the language. Once these two models are developed, it will be useful to every one doing research in speech processing. For Indian languages Hindi, Tamil, Telugu and Marati, ASR systems have been developed using sphinx engine. In this project work is aimed at developing acoustic model and language model for Malayalam.
Mentor: Deepa P. Gopinath
- 'Development of Indian Language Speech Databases for Large Vocabulary Speech Recognition Systems', Gopalakrishna Anumanchipalli, Rahul Chitturi, Sachin Joshi, Rohit Kumar, Satinder Pal Singh, R.N.V. Sitaram, S P Kishore
- "Automatic Pronunciation Evaluation And Mispronunciation Detection Using CMUSphinx", Ronanki Srikanth, James Salsman
- "HTK Based Telugu Speech Recognition", P. Vijai Bhaskar, AVNIET ,Hyderabad, Prof. Dr. S. Rama Mohan Rao, A.Gopi
- "Design and Development of an Automatic Speech Recognition System for Urdu", Agha Ali Raza, M.Sc. Thesis, FAST‐National University of Computer and Emerging Sciences
- "Investigation Arabic Speech Recognition Using CMU Sphinx System", Hassan Satori1, 2, Hussein Hiyassat3, Mostafa Harti1, 2, and Noureddine Chenfour
- "Understanding the CMU Sphinx Speech Recognition System", Chun-Feng Liao
Enhancement of Indic Language Support in Scribus
Scribus is an Open Source program that brings professional page layout to Linux/UNIX. Find more about scribus here. Indic Languages are not supported completely in Scribus as of now. As a result of the work done by a group of developers from India, there is a branch available in Scribus public git repo which supports Indic Languages. The aim of this idea is to Enhance the Indic language support solving the following issues:
- Harfbuzz is being used as a thrid party code in Scribus. Maintaining thirdparty code is a tedious task, this should be added as a dependency instead.
- Enhance hyphenation by adding hyphenation rules.
Expertise Required: Good understanding of C, C++, Qt, Harfbuz etc, cmake.
- Branch indic in scribus public git repository. Clone url: git clone git://git.scribus.net/scribus.git
- Compile scribus indic branch
Mentor : Jain Basil Aliyas (jainbasil in IRC)
Complexity : Advanced