Rohini U

 

 

 

 

Education

 

MS by Research in Computer Science and Engineering

International Institute of Information Technology,

Hyderabad, India, August 2007

 

CGPA: 9.62/10

B.Tech. Computer Science and Engineering 

International Institute of Information Technology,

Hyderabad, India, July 2004

 

CGPA: 7.53/10

Senior Secondary

Nalanda Junior College, Hyderabad, India, May 2000

 

Aggr: 91.7%

Secondary

Geetanjali High School, Hyderabad, India, April 1998

Aggr: 86.1%



Achievements

  • Secured All India 28th Rank in IIIT-CET 2000
  • Pratibha-2000 AP State Government Scholarship for securing AIR 28th in IIIT-CET' 2000
  • Silver Medal and Best Student of the year Award in 10th class.


  • Internships and Assistantships

  • Summer internship at COVA under the guidance of Dr. Kamalakar Karlapalem
  • Research Assistantship at Language Technologies Research Center (LTRC, IIIT ) from July 2004 August 2007
  • Summer Internship at Digital Library of India, Regional Mega Scanning Center, IIIT, ,Hyderabad (LTRC, IIIT ) from May 2004 July 2004
  • Summer Internship at Digital Library of India, Regional Mega Scanning Center, IIIT, Hyderabad (LTRC, IIIT ) from May 2006 July 2006

  • Research Interests

  • Information Retrieval, especially Adaptive Information Retrieval, Personalized Search
  • Recommendation Systems
  • Natural Language Processing


  • Experience in the Industry

    Position Held   Research Scientist
    Nature of Work  Corporate R&D work. Currently working on projects related to Personalization and Recommendation Systems.
    Name of the Organization   AOL India R&D, Bangalore
    Period   August 13 2007 - Current


    Publications

     

    • Rohini U, Vamshi Ambati and Vasudeva Varma. Statistical Machine Translation Models for Personalized Search. In Proceedings of International Joint Conference on Natural Language Processing (IJCNLP 2008), India, 2008

     

    • Rohini U and Vamshi Ambati: Extracting Keyphrases from books using language modeling approaches. In Proceedings of the 3rd ICUDL, Pittsburgh, USA, November 2007

     

    • Rohini U and Vasudeva Varma. A Novel Approach for Re-Ranking of Search results using Collaborative Filtering. In Proceedings of International Conference on Computing: Theory and Applications (ICCTA'07), India, 2007

     

    • Vamshi Ambati and Rohini U. A Hybrid Approach to Example based Machine Translation for Indian Languages. In Proceedings of 5th International Conference on Natural Language Processing (ICON 2007), India, 2007

     

    • Vamshi Ambati, Rohini U, Pramod P, Balakrishnan N, Raj Reddy. Multilingual Information Access: Information Retrieval and Translation in a Digital Library. In Proceedings of 2nd ICUDL 2006, Egypt, 2006

     

    • Vamshi Ambati, Rohini U. Using Monolingual Clickthrough data to build Cross Lingual Search Systems. In the proceedings of New Directions in Multilingual Information Access, Workshop held at SIGIR, 2006.

     

    • Rohini Uppuluri, Vamshi Ambati. Improving Search Results using Collaborative Filtering. In the proceedings of 4th ITWP, Workshop held at AAAI 2006., Boston,Massachusetts, 2006

     

     

    • Rohini U, Vamshi Ambati. Collaborative Filtering based Re ranking Strategy for search in Digital Libraries. In the proceedings of 8th International Conference on Asian Libraries,2005 (ICADL 2005), Bangkok, Thailand, 2005.

     

    • Rohini U, Vishnu P, S. M. Bendre., Rajeev Sangal. A Hybrid Approach to Single and Multiple PP Attachment using WordNet. In Proceedings of International Joint Conference on Natural Language Processing 2005, (IJCNLP-2005), Jeju Island, Korea, 2005

     

    Technical Reports

     

    • Rohini U, Vamshi Ambati and Vasudev Varma. Simulated Feedback. Technical Report, IIIT Hyderabad, India.

     

    • Rohini U, Vamshi Ambati and Vasudev Varma. Personalized Web Search without Relevance Feedback. Technical Report, IIIT Hyderabad, India

     

    • Vamshi Ambati, Rohini U, Nazeer Hussain and Raj Reddy : Autovita: A 360 degree view of Person Related Information on the WWW, Working Draft, IIIT Hyderabad, India.

     

    • Rohini U, Personalized Web Search using Clickthrough History, Masters Thesis, Technical Report IIIT Hyderabad, 2007

     

    • Rohini U, A Hybrid Approach to Single PP Attachment, Undergraduate Thesis, Technical Report IIIT Hyderabad, 2004

     

     

    Talks/Presentations

     

    • Collaborative Web Search, Guest Lecture in Search and Information Extraction Course taught at IIIT Hyderabad, India, 2006

     

    • Personalized Web Search using Clickthrough History, Presented at AOL Labs, India, 2007

     

     

    Skill Set

  • Programming Languages: C, Perl, Java
  • Operating Systems: GNU/Linux, Windows 2000/XP
  • Database Technologies: MySQL
  • Web Technologies: Html, Php, Jsp


  • Masters Course Work

    Pattern Recognition, Machine Learning, Infromation Retrieval and Extraction, Web Data and Knowledge Management


    Undergraduate Course Work

    Computer Programming, Data Structures, Computer Organization, Artificial Intelligence, Analog and Digital Circuits, Operating Systems, Computer Networks, Introduction to Databases, Discrete Mathematics, Signal Processing, Principles of Programming Languages, Programming Language Processors, Theory of Computation, Algorithms, Software Engineering.

     

    Elective Courses

    Soft Computing, Introduction to Natural Language Processing, Digital Image Processing, Cryptography and Network Security, Natural Language Dialog Systems, Building Automation and Controls

     

    Research Projects


    Masters Thesis

    Personalized Search (January 2005 June 2007)

    Advisor: Dr. Vasudeva Varma, Associate Professor, IIIT, Hyd.

     

    Most existing retrieval systems, including the web search engines, suffer from the problem of one size fits all: the decision of which documents to retrieve is made based only on the query posed, without consideration of a particular user's preferences and search context. When a query (e.g. "jaguar") is ambiguous, the search results are inevitably mixed in content (e.g. containing documents on the jaguar cat and on the jaguar car), which is certainly non-optimal for the user, who is burdened by having to sift through the mixed results. In order to optimize retrieval accuracy, we clearly need to model the user appropriately and personalize search according to each individual user. The major goal of personalized search is to accurately model a user's information need and store it in the user profile and then rerank the results to suit to the user's interests using the user profile.


    Undergraduate Thesis

    Prepositional Phrase Attachment (January 2003 - January 2004)

    Advisor: Dr. Bendre, Visiting Professor and Dr. Sangal, Director, Professor at IIIT Hyd.

    The task here is to attach a prepositional phrase in a given sentence to a noun phrase or a verb phrase in the sentence. The approach uses a combination of supervised and unsupervised methods for learning. Un supervised learning is done using Expectation Maximization algorithm. The attachment of the prepositional phrase is done using scores calculated using WordNet, a lexical database and back-off smoothing. The approach showed an improvement in performance over the start of the art approaches.


    Creating Simulated Feedback (July 2005 -November 2006)

    Advisor: Dr. Vasudeva Varma, Associate Professor, IIIT, Hyd

    Collaborative Web Search

    Advisor: Dr. Vasudeva Varma, Associate Professor, IIIT, Hyd.

    Search in Presence of Errors

    Worked with: Mr. Vamshi Ambati, Technical Director, Digital Library of India

    Digital Library Reading Assistant

    Worked with: Mr. Vamshi Ambati, Technical Director, Digital Library of India.

    Cross Lingual Information Retrieval (CLIR) (January 2005 - April 2005)

    Advisor: Dr. Vasudeva Varma, Associate Professor, IIIT, Hyd

    User profile learning for Personalized Web Search using Machine Learning

    Course: Machine Learning (Spring 2004)
    Instructor: Dr. C. V. Jawahar, Associate Professor, IIIT, Hyd.

    Other Major Projects


    Extracting Patterns and Relations using NLP

    Course: Web data and Knowledge Management (Fall 2004)

    Instructor: Dr. P. K. Reddy, Associate Professor, IIIT, Hyd.


    Text Classification using NLP

    Course: Pattern Recognition (Spring 2004)
    Instructor: Dr. P. J. Narayanan, Dean (R&D) Professor, IIIT, Hyd.

    Pronoun Co-reference resolution using the centering approach

    Course: Introduction to Natural Language Processing (Fall 2003)
    Instructor: Prof. Rajeev Sangal, Director, Professor, IIIT Hyd.

    Virus Detection System

    Semester Project
    Advisor: Dr. Ram Murthy, Associate Professor, IIIT, Hyd.

    References

     

    Dr. Vasudeva Varma

    Associate Professor,

    Head, Search and Information Extraction Lab (SIEL),

    Language Technologies Research Center (LTRC),

    Head, Software Engineering Research Lab (SERL)

    International Institute of Information Technology,

    Hyderabad, India

     

     

    Prof. Sangal

    Professor, Director,

    International Institute of Information Technology,

    Hyderabad, India

     

     

    Prof. Sreenivas Rao Meda

    Dean, Centre for Institute of Higher Learning

    Professor, Jawaharlal Nehru Technological University

    Hyderabad, India

     

     

    Mr. Vamshi Ambati,

    Technical Director, Digital Library of India,

    Faculty, MSIT Program,

    International Institute of Information Technology,

    Hyderabad, India.