Educational Details

Degree : B.Sc
Year : 2000
University : Mangalore University
PG Degree : MCA
Year : 2003
University : VTU
Doctoral Degree : Phd in Computer Science
Year : 2017
University : Universidade Nova de Lisboa (UNL), Portugal

Teaching Experience

i) Period: Nov 2017 to till date
    Department: Computer Science & Engineering
    Institute: St Joseph Engineering College, Mangaluru
    Designation: Associate Professor
ii) Period: Aug 2013 to Oct 2017
    Department: Master of Computer Applications
    Institute: St Joseph Engineering College, Mangaluru
    Designation: Assistant Professor
iii) Period: Feb 2008 to Nov 2008
     Department: Computer Science & Engineering, 
     Institution: KVG College of Engineering, Sullia
     Designation: Guest Lecturer
iv) Period: Sep 2003 to Oct 2005
     Department: Master of Computer Applications
     Institution: KVG College of Engineering, Sullia
     Designation: Lecturer

Research Experience

4 Years

Industry Experience

Period: Jan 2006 to Jul 2007
Department: Structural Materials Group, Centre for Materials Research, Portugal
Institution: FCT-UNL, Portugal
Designation: Programmer

Specialization Ph.D

Computer Science

Specialization PG

Computer Applications

Subjects teaching at Under Graduate level

System software with introduction to LEX and YACC, Computer Concepts & Programming with ‘C’ language, Computer Organization and Architecture

Subjects teaching at Post Graduate level

Data structures in ‘C’, Analysis & Design of algorithms, System Simulation and Modeling, Problem Solving using C, System Programming, Software Engineering, Fundamentals of Computer Organization and Information Retrieval & Search Engines

Technical Interest

Computer-assisted Natural Language processing, Machine Learning and Knowledge Extraction, Classification, Cluster Analysis, Algorithms and Data structures for Information Retrieval, Bilingual Morphology, Data Analytics

Skill Set

C, Python, Selected Machine Learning Tools such as SVMs, CLUTO, NLTK, LaTeX

Papers Presented in International Conference

i) K. M. Kavitha, Luís Gomes and José Gabriel Pereira Lopes. Using Bilingual Segments in Generating Word-to-word Translations. In Proceedings of the Sixth Workshop on Hybrid Approaches to Translation, 26th International Conference on Computational Linguistics, COLING 2016, pp. 61-71, Osaka, Japan, December 2016. Association for Computational Linguistics (ACL). ISBN: 978-4-87974-713-6. [ACL Anthology, dblp].

ii) K. M. Kavitha, Luís Gomes and José Gabriel Pereira Lopes. Learning Clusters of Bilingual Suffixes Using Bilingual Translation Lexicon. In Prasath R., Vuppala A., Kathir- valavakumar T. (Eds.) Mining Intelligence and Knowledge Exploration, Third International Conference, MIKE 2015, Lecture Notes in Artificial Intelligence, vol 9468, pp. 607-615, Hyderabad, India. Springer International Publishing, Cham. 2015. DOI: 10.1007/978-3-319-26832-3 57. [Acceptance rate 32.43%, ACM-DL, Scopus, dblp].

iii) K. M. Kavitha, Luís Gomes and José Gabriel Pereira Lopes. Bilingually Motivated Segmentation and Generation of Word Translations using Relatively Small Translation Data Sets, In Proceedings of the 29th Pacific Asia Conference on Language, Information and Computation: Posters, (PACLIC29), pp. 187-196, Shanghai, China, October 2015. ACL. [Conference Rank - B, ACL Anthology, Scopus, dblp].

iv) K. M. Kavitha, Luís Gomes, José Aires and José Gabriel Pereira Lopes. Classification and Selection of Translation Candidates for Parallel Corpora Alignment. In Pereira F., Machado P., Costa E., Cardoso A. (Eds.) Progress in Artificial Intelligence, 17th Por- tuguese Conference on Artificial Intelligence, EPIA 2015, Lecture Notes in Artificial Intelligence, vol 9273, pp. 723-734, Coimbra, Portugal. Springer International Publishing, Cham. 2015. DOI: 10.1007/978-3-319-23485-4 73. [Conference Rank - B, Acceptance rate: 34%, ISI-WOS, Scopus, dblp].

v) Karimbi Mahesh Kavitha, Luís Gomes and José Gabriel Pereira Lopes. Identification of Bilingual Suffix Classes for Classification and Translation Generation. In: Bazzan A., Pichara K. (Eds.) Advances in Artificial Intelligence – IBERAMIA 2014, 14th Ibero-American Conference on AI, Lecture Notes in Artificial Intelligence, vol 8864, pp. 154-166, Santiago de Chile, Chile. Springer, Cham. 2014. DOI: 10.1007/978-3- 319-12027-0 13. [Acceptance rate (NLP): 26%, ISI-WOS, Scopus, dblp].

vi) Kavitha Karimbi Mahesh, Luís Gomes and José Gabriel Pereira Lopes. Identification of Bilingual Segments for Translation Generation. In: Blockeel H., van Leeuwen M., Vinciotti V. (Eds.) Advances in Intelligent Data Analysis XIII, 13th International Symposium, IDA 2014, Lecture Notes in Computer Science, vol 8819, pp. 167-178, Leuven, Belgium. Springer, Cham. DOI: 10.1007/978-3-319-12571-8 15. (Poster) [Conference Rank - A, Scopus, dblp].

vii) K. M. Kavitha, Luís Gomes and Gabriel Pereira Lopes. Using SVMs for Filtering Translation Tables for Parallel Corpora Alignment, In: Luis Antunes, H. Sofia Pinto, Rui Prada, Paulo Trigo (Eds.) Proceedings of the 15th Portuguese Conference on Artificial Intelligence, EPIA 2011, pp. 690-702, Lisboa, Portugal, October 2011. ISBN: 978-989-95618-4-7. [Conference Rank - B].

Number of academic projects guided

UG : 2
PG : 21

Research Project

i) Project Title: ISTRION - Improving Phrase-Based Statistical Machine TRanslation through supervisION
Role: Co-Investigator (Principal Investigator: Prof. Dr. José Gabriel Pereira Lopes, Department of Informatics, FCT/UNL, Lisbon, Portugal) 
Funding Agency: Portuguese National Science Foundation (Fundação para a Ciência e a Tecnologia, Ministério da Ciência, Tecnologia e Ensino Superior- FCT/MCTES)
Project Duration: Mar 2011 - Feb 2013
Project Outcomes: The goal of ISTRION project (contract PTDC/EIA-EIA/114521/2009 funded by FCT/MCTES) was to show that a machine, whose knowledge acquisition and use is adequately supervised by humans, may improve its own competence and outperform current translation systems, getting progressively closer to human competence. 
In the scope of ISTRION project, I explored the use of SVMs in filtering translation tables for parallel corpora alignment. It is based on the idea that Translation Lexicons can improve the quality of parallel corpora alignment at sub-sentence granularity, of newly extracted translations, and as a consequence, of translations produced by a machine. Bilingual pairs (entries) that are part of such translation lexicons should be correct if they are to contribute positively to the improvement of application's quality. The prototype developed classifies the bilingual entries automatically extracted from aligned parallel corpora as correct or incorrect. Experimental results demonstrate that this classification approach enabled a Micro f-measure higher than 85% for language pair English-Portuguese.


Workshop Attend

i) Name of the Workshop/Seminar: Faculty Development Programme on "Natural Language Processing and Machine Learning".
Date & Venue: March 20-22, 2017.
Organized by: NMAM Institute of Technology, Nitte.

ii) Name of the Workshop/Seminar: Spoken and Written Language Processing: A Beginning of the Research Journey.
Date & Venue: Jul 18-19, 2014.
Organized by: NMAM Institute of Technology, Nitte.

Workshops/Seminars organized

Name of the Workshop/Seminar: One Day Workshop on DELNET: Resources, Services and Facilities & Koha: An Open Source Integrated Library Management Software.
Date & Venue: May 6, 2014, St Joseph Engineering College, Mangaluru, Karnataka.
Sponsoring/Supporting Agency: DELNET, Developing Library Network, New Delhi & St Joseph Engineering College, Mangaluru, Karnataka.
Role: Organising Committee Member.

Awards and Achivements

i) Project Research Grant
Period : Jul 2009 to Feb 2010
Fellowship: Bolsa da Investigação (BI)
Institution: Research Center for Informatics and Information Technologies (Centro de Investigação em Informática e Tecnologias da Informação - CITI), Faculdade de Ciências e Tecnologia, Universidade Nova de Lisboa, Caparica, Portugal.

ii) Ph.D. Research Fellowship
Period : Mar 2010 to Jul 2013
Fellowship: Bolsa da Investigação (BI) with Ref. SFRH/BD/64371/2009 
Funding Agency: Foundation for Science & Technology, Ministry of Science, Technology and Higher Education (FCT/MCTES), Portugal.

Details of membership in Professional bodies

Organization: IEEE
Designation: Member
Year of Joining: 2014-15

Administrative Responsibilities

i) Convener - Graduation Day 2017

Details of interaction with outside world

i) Event Title: 12th Women in Machine Learning Workshop (WiML), 2017.
Role: Reviewer.

Interests / Hobbies

Drawing and Painting, Gardening, Photography, Practicing Yoga, Stamp Collection, Visiting places of natural attractions and historical importance

Other Related Info

PhD Thesis
Kavitha Karimbi Mahesh. Augmenting Translation Lexica by Learning Generalised Translation Patterns. Faculdade de Ciências e Tecnologia (FCT), Universidade Nova de Lisboa, 2017. (Supervisor: Prof. José Gabriel Pereira Lopes.)