About
Activity
-
Legos were my favorite toy and ever since then I appreciated the right building blocks :) Cue in Velox and VeloxCon end of April :). This year's…
Legos were my favorite toy and ever since then I appreciated the right building blocks :) Cue in Velox and VeloxCon end of April :). This year's…
Liked by Sameer Sonawane
-
The day I realised my H1B visa was a golden handcuff In 1995, I was working at Qualcomm in San Diego on an H1B visa. On paper, I was in the world’s…
The day I realised my H1B visa was a golden handcuff In 1995, I was working at Qualcomm in San Diego on an H1B visa. On paper, I was in the world’s…
Liked by Sameer Sonawane
-
A major milestone today! 🎓 It's been 25 years since I began my journey as a Computer Science student at the University of Michigan, Ann Arbor! I am…
A major milestone today! 🎓 It's been 25 years since I began my journey as a Computer Science student at the University of Michigan, Ann Arbor! I am…
Liked by Sameer Sonawane
Experience & Education
-
Meta
View Sameer’s full experience
See their title, tenure and more.
or
Publications
-
Automatic Text Summarization of News Articles
IEEE - 2017 International Conference on Big Data, IoT and Data Science (BID)
Text Summarization has always been an area of active interest in the academia. In recent times, even though several techniques have being developed for automatic text summarization, efficiency is still a concern. Given the increase in size and number of documents available online, an efficient automatic news summarizer is the need of the hour. In this paper, we propose a technique of text summarization which focuses on the problem of identifying the most important portions of the text and…
Text Summarization has always been an area of active interest in the academia. In recent times, even though several techniques have being developed for automatic text summarization, efficiency is still a concern. Given the increase in size and number of documents available online, an efficient automatic news summarizer is the need of the hour. In this paper, we propose a technique of text summarization which focuses on the problem of identifying the most important portions of the text and producing coherent summaries. In our methodology, we donot require full semantic interpretation of the text, instead we create a summary using a model of topic progression in the text derived from lexical chains. We present an optimized and efficient algorithm to generate text summary using lexical chains and using the WordNet thesaurus. Further, we also overcome the limitations of the lexical chain approach to generate a good summary by implementing pronoun resolution and by suggesting new scoring techniques to leverage the structure of news articles.
Other authors -
-
Recommendation Techniques for Adaptive E-learning
Advances in Computer Science and Information Technology (ACSIT) - Krishi Sanskriti Publications
The research paper includes description of all algorithms involved during the the development of adaptive prototype engine for recommending the user videos based on several parameters - history, expertise, necessity,etc. related to User-Modelling, Content-Modelling, Adaptive Engine and System-Evaluation.
Print ISSN: 2393-9907; Online ISSN: 2393-9915; Volume 2, Number 1; January-March, 2015 pp. 7-12Other authors -
Courses
-
Analysis of Algorithms
CSL313
-
Compilers
-
-
Computer Networks
-
-
Data Structures and Program Design
CSL214
-
Database Management Systems
CSL315
-
Discrete mathematics and Graph Theory
CSL202
-
Microprocessor Based Systems
CSL223
-
Neuro-Fuzzy Techniques
CSL304
-
Operating Systems
CSL312
-
Software Engineering
-
Projects
-
Image Classifier using Neural Networks
Developed an image classifier to classify a given image of a number using neural network having multiple layers.
-
Automatic Summarization of News Articles
-
Developed an automatic extractive news summarizer using lexical chains with enhancements to
inculcate the structure of news articles. Improved the traditional lexical chain summarization by implementing proper noun resolution and enhanced scoring techniques.
Tools Used : NLTK, Python, WordNetOther creators -
-
E-commerce Platform
-
Developed an e-commerce platform involving products from local sellers and customers as a semester long group project. The platform aims to deliver the products within few hours once the order is placed. The major tools used in the project include JAVA , Jersey, REST API, MySQL, HTML, CSS, AngularJS and Android.
-
Adaptive Engine for E-Learning
-
Mentored by Prof. Deepak B Phatak, IIT Bombay. Examined the data on Edx and Moodle (MOOC Platforms) and developed algorithms related to User-Modelling, Content-Modelling, Adaptive Engine and System-Evaluation. Proposed four new polynomial time algorithms for recommendation - Maximum Success Path Algorithm, User-User Collaborative Filtering Algorithm, Item-Item Collaborative Filtering and Remediation Algorithm. Developed a prototype system using Django to test the algorithms.
Other creators -
-
Alumni Interaction Platform
-
Worked as developer in a project with college batch-mates to create a platform dedicated for interaction of alumni. Worked on designing the website backend and hosting it through Django.
Other creators -
Honors & Awards
-
ACM-ICPC regional contests
ACM
Bagged 61st position in ACM-ICPC kharagpur regional contest and 225th position in ACM-ICPC Amritapuri regionals.
Languages
-
English
-
-
Hindi
-
-
Marathi
-
Other similar profiles
Explore collaborative articles
We’re unlocking community knowledge in a new way. Experts add insights directly into each article, started with the help of AI.
Explore More