Georgiana Ifrim Postdoc Researcher Cork Constraint Computation Centre (4C) University College Cork Western Road Cork, Ireland Phone: +353 214205374 Email: g.lastname at 4c ucc ie Office: Western Gateway Building, 4C Lab

Research Interests

• Machine Learning, Constraint Optimization
  
• Classification of Structured Data
• Statistical Models, Data Mining
• Information Extraction/Retrieval

Education

• Ph.D. (Dr.-Ing.) in Computer Science, Max-Planck Institute for Informatics, Saarbruecken, Germany (2009)
  Dissertation: Statistical Learning Techniques for Text Categorization with Sparse Labeled Data (pdf)
  Advisor: Gerhard Weikum
  Committee: Andreas Zeller (Chair), Gerhard Weikum, Thomas Hofmann and Tobias Scheffer
  
• Master's degree (M.Sc.) in Computer Science, Max-Planck Institute for Informatics, Saarbruecken, Germany (2005)
  
• Bachelor's degree (B.Sc.) in Computer Science, University of Bucharest, Bucharest, Romania (2003)

Publications

Bio-Sequence Mining


• Georgiana Ifrim, Carsten Wiuf
  Bounded Coordinate-Descent for Biological Sequence Classification in High Dimensional Predictor Space (pdf) ACM SIGKDD International Conference on Knowledge Discovery and Data Mining (KDD 2011)


• Georgiana Ifrim, Carsten Wiuf
  Bounded Coordinate-Descent for Biological Sequence Classification in High Dimensional Predictor Space (arXiv:1008.0528, 2010)


• Poul Liboriussen, Bjoern P. Pedersen, Georgiana Ifrim, Poul Nissen, Christian S. Pedersen
  Automatic classification of P-Type ATPases using SLR (poster, abstract)
  International Conference on Intelligent Systems for Molecular Biology and European Conference on Computational Biology (ISMB & ECCB 2009)


Text Mining


• Lizhen Qu, Georgiana Ifrim, Gerhard Weikum
  The Bag-of-Opinions Method for Review Rating Prediction from Sparse Text Patterns (pdf)
  International Conference on Computational Linguistics (COLING 2010)


• Georgiana Ifrim
  Statistical Learning Techniques for Text Categorization with Sparse Labeled Data (pdf)
  Ph.D. Thesis, Max-Planck Institute for Informatics, 2009


• Georgiana Ifrim, Goekhan Bakir, Gerhard Weikum
  Fast Logistic Regression for Text Categorization with Variable-Length N-grams (pdf)
  ACM SIGKDD International Conference on Knowledge Discovery and Data Mining (KDD 2008)


• Georgiana Ifrim, Gerhard Weikum
  Transductive Learning for Text Classification using Explicit Knowledge Models (pdf)
  Principles and Practice of Knowledge Discovery in Databases (PKDD 2006 )


• Georgiana Ifrim, Martin Theobald, Gerhard Weikum
  Learning Word-to-Concept Mappings for Automatic Text Classification (pdf)
  ICML-Learning in Web Search Workshop, 2005


• Georgiana Ifrim
  A Bayesian Learning Approach to Concept-Based Document Classification (pdf)
  Master Thesis, Universitaet des Saarlandes and Max-Planck Institute for Informatics, 2005


Information Extraction, Storage and Retrieval


• Gjergji Kasneci, Fabian M. Suchanek, Georgiana Ifrim, Shady Elbasuoni, Maya Ramanath, Gerhard Weikum
  NAGA: Harvesting, Searching and Ranking Knowledge (pdf)
  Demo Paper at the ACM Special Interest Group on Management Of Data (SIGMOD/PODS 2008)


• Gjergji Kasneci, Fabian M. Suchanek, Georgiana Ifrim, Maya Ramanath, Gerhard Weikum
  NAGA: Searching and Ranking Knowledge (pdf, Technical Report)
  24th IEEE International Conference on Data Engineering (ICDE 2008)


• Fabian M. Suchanek, Georgiana Ifrim, Gerhard Weikum
  Combining Linguistic and Statistical Analysis to Extract Relations from Web Documents (pdf, Technical Report)
  ACM SIGKDD International Conference on Knowledge Discovery and Data Mining (KDD 2006)


• Fabian M. Suchanek, Georgiana Ifrim, Gerhard Weikum
  LEILA: Learning to Extract Information by Linguistic Analysis (pdf)
  Workshop on Ontology Learning and Population at COLING/ACL 2006


XML Summarization


• Maya Ramanath, Kondreddi Sarath Kumar, Georgiana Ifrim
  Generating Concise and Readable Summaries of XML documents (pdf) Technical Report, Max-Planck Institute for Informatics, Campus E1 4, MPI–I–2009–5-002

Talks

• KDD 2011 (pdf)
  
• UCC-CS Seminar Talk on 14/04/2011: Sequence Classification in High Dimensional Predictor Space (slides: pdf, open source code: SEQL)
  
• Data Mining invited lecture at UCC 08/02/2011 (pdf)
  
• KDD 2008 (pdf)
• ECML/PKDD 2006 (pdf)
• ICML 2005 Workshop: Learning in Web Search (pdf)

Teaching

• Teaching Assistant for Information Retrieval and Data Mining (Winter Semester, 2007/08), given by Prof. Gerhard Weikum, Max-Planck Institute for Informatics, Saarbruecken, Germany
• Teaching Assistant for Information Retrieval and Data Mining (Winter Semester, 2005/06), given by Prof. Gerhard Weikum, Max-Planck Institute for Informatics, Saarbruecken, Germany
• Teaching Assistant for Database Systems (Summer Semester, 2005), given by Prof. Cristoph Koch, University of Saarland, Germany
• Teaching Assistant for Automated Reasoning (Summer Semester, 2004), given by Prof. Harald Ganzinger, Max-Planck Institute for Informatics, Saarbruecken, Germany

Downloads

Open source software

• SEQL: Sequence Learner (KDD11, seql-v2.0.tar.gz)
  General learning framework for discriminative sequence classification. Includes regularized SLR and linear SVM.


• SLR: Structured Logistic Regression (KDD08)
  Fast Logistic Regression for Text Categorization: learning phrase-classifiers (ngram-classifiers) with variable-length phrases (ngrams).

Text and Bio Datasets

• KDD11 datasets
• KDD08 datasets
• Reuters-21578, Ohsumed, 20 Newsgroups
• Wikipedia (a partial crawl from wikipedia.org)

Miscellanea