Workshop on Malayalam Computing

     
   A one-day work shop on Malayalam Computing, jointly conducted by Thunchath Ezhuthachan Malayalam University and Kerala State IT mission was held on February  8th 2013, at IMG Thiruvananthapuram. The workshop was the continuation of  university's agenda to make Malayalam language as IT savvy as possible. This workshop in that sense was a good platform for the scholars and researchers in this area. Radhika K T of fourth semester M.Tech Computational Linguistics represented SIMPLE Groups at Thiruvananthapuram and presented her paper titled "Conceptual Indexing and Compound word Splitter: For Better Information Retrieval in Malayalam".

NCILC 2013 @ CUSAT

Mr. Sathyseelan during the demonstration

Robert Jesuraj interacting with the Chair.

   The third National Conference on Indian Language Computing (NCILC), conducted by Dept. of Computer Application, CUSAT was held on 19-20 of January 2013. The Conference was inaugurated by Dr. B.B. Choudary of ISI, Kolkatha. The function was precided by Dr. Balachandran Thekkedathu, Hon. Vice Chancellor of CUSAT. The conference had invited talks by Prof. Choudary, Prof. Jathavedan, Prof. Samudra Vijaya and a panel discussion lead by Dr. Kannan. All the talks bring different facets of Indian Language Computing. The main attraction of the conference was the software demonstration by Mr. Sathyaseelan, from Kerala Federation of the Blind, on different tools and application for Visually Challenged people. About 16 papers from researchers and PG students working in NLP/CL were presented in the function. Manu Madhavan, Mujeeb Rehman and Robert Jesuraj represented SIMPLE groups there. They presented the following papers:

1. Manu Madhavan, Mujeeb Rehman O,  P. C. Reghu Raj,   " Computing Prosodic Pattern for Malayalam", in Proc. of NCILC, pp 1-4, CUSAT, Cochin, 2013.
2. Robert Jesuraj, P. C. Reghu Raj, "MBLP approach applied to POS tagging in Malayalam Language", in Proc. of NCILC, pp. 5-8, CUSAT, Cochin, 2013.  

CLEAR-March 2013-Article Invitation

 

 

Student's Innovations in Morphology, Phonology and 

Language Engineering (SIMPLE)-Groups

Dept. of Computer Science and Engineering

Govt. Engineering College, Sreekrishnapuram

Palakkad, 678633

 

 

We are inviting thought-provoking articles, interesting dialogues and healthy debates on multifaceted aspects of Computational Linguistics, for the forthcoming issue of CLEAR ( Computational Linguistics in Engineering And Research) magazine, publishing on March 2013. The topics of the articles would preferably be related to the areas of Natural Language Processing, Computational Linguistics and Information Retrieval.

The articles may be sent to the Editor on or before 20th February, 2013 through the email simplequest.in@gmail.com.

For more details visit: http://simplegec.blogspot.in

Read web invitation

    Representative                                            Editor

    SIMPLE Groups                                         CLEAR Magazine

CLEAR Dec 2012 Published

The second issue of CLEAR published on December 27, 2012. The magazine in this issue discusses applications of fuzzy logic in NLP, issues of Indian language computing, future of NLP in Human Computer interactions, and Google's driver less cars. This issue also contain an article on GNU Octave by Mr. Razee Marikar, a computer professional with Subex Banglore, and an alumnus of GEC, Sreekrishnapuram. The next issue will be on March 2013.

Read online   or download the e-version.

CLEAR Dec 2012

Open publication - Free publishing - More clear

Talk by Prof. Kalyana Krishnan

A day with "Acharya"

 Prof. Kalyana Krishnan, a retired Professor of IIT Madras and a pioneer in Indian Language Computing, delivered a talk on 28th November, 2012. During the session, he demonstrated the complexity of Natural Language Processing (NLP). The talk was a warm invitation to Indian Language Computing(ILC), and its applications.

Need for Standardization

The session started with a thought-provoking question "What computer can do?". He answered this question in the light of  NLP. Mentioning the scope of Computational Linguistics, he told that "NLP in European Languages is developing interestingly, because they have standards, and central co-ordination. India currently lacks this standardization. Different working groups and organizations in India set their own standards and they are not ready to come to an open standard".  He also gave an introduction to Indian Linguistic traditions by taking examples from Sanskrit and Malayalam.

Aksharas.. not simply characters

Because of the well-structure and well defined set of rules, Sanskrit is highly suitable for linguistic processing by computers. Since most Indian languages are rooted in Sanskrit, computing with Indian Languages is not as complex as with English. But the current state of art contradicts this observation because of  insufficient centralized co-ordination. " We are trying to follow the western NLP technology, which is based on characters. But, our tradition is different. The basic unit of all Indian languages is Akshara, which is a combination of consonants and a vowel.  Limiting our languages to character-level is inadequate", he conveyed.  While discussing the technologies for ILC, he presented the Akshara-based 16-bit encoding scheme for Indian languages developed by IIT-M students. (The details of their work can be seen at acharya website).

No programs should crash

The session concluded by mentioning the importance of good programming style. "Writing a program is not simply applying mathematical formulas. Make it as friendly as possible with the user.  No programs should crash". Professor declared. He advised the students to refer the book " Numerical recipes in C: The art of Scientific Computing ", for a better and different perspective on programming.

Enthusiastic, interactive and motivational

The simple but energetic way of presentation by the veteran teacher  inspired all the students. The talk was mixed with key technology, thought provoking questions, examples and fun, which made everybody interactive. M.Tech students and final year students of B.tech  CSE attended the class. He also had an interactive session with the B.Tech CSE first year students, which inspired them very much.

National Seminar @ Kerala University

Students from SIMPLE Groups attended the National Seminar on Relevance of Malayalam in the Field of Information Technology, jointly conducted by Dept. of Linguistics, Kerala University and KSCSTE, on 1-2 November 2012.  The seminar discusses possible ways to promote the use of Malayalam for the dissemination of information to common people. The two day sessions were chaired by dignitaries like Dr. S Rajendran, Dr. Sarathchandran Nair from the field of Computational Linguistics. In association with VRCLC, IIITM-K, participants from SIMPLE Groups presented their papers. The papers are:

1.  Christopher Augustine, Sibi S, Rajeev R R*, Suleena K**, " Feature Extraction in Malayalam Language ", (* VRCLC, IIITM-K , **SAS SNDP Yogam College, Pathanamthitta)Read
2. Divya S, Rinju O R, Sumi S Nair, *Rajeev R R, **Raja Varma Pamba, " Malayalam Morphological Analyser", (* VRCLC, IIITM-K , **MG University)Read
3. Divya Das, Radhika K, Rajeev R R*, Reghu Raj P C, "Hybrid Sandhi Splitter for Malayalam using Unicode",  (* VRCLC, IIITM-K)Read
4. Ayisha Noori V K, Renuka Babu T, Saani H, Rajeev R R*, “On-line POS Tagger for Malayalam”,         (* VRCLC, IIITM-K)
5. Athira P M, Ancy K Sunny, Pragisha K , Jithesh V.S*., Rajeev R R*, " Trilingual Dictionaries- A Generative Approach ", (* VRCLC, IIITM-K) Abstract 

Divya S and Rinju O R presenting their paper

Sibi presenting the Paper

Pragisha presenting the paper

Radhika and Divya Das presenting their paper.