Department information

 

Roman Yangarber

• My Official Department home page
• Office hours: by appointment
  • Telephone: +358 9 191 51145
  • Room A224, Exactum Building
• Calendar—for dates out of office on travel
• (Ye olde home page at New York University)

Projects

• I lead the Research Group in
  Computational Linguistics and Language Technology.

• PULS: Automatic Surveillance of News Media
• Epidemic Surveillance through Analysis of On-Line News, in collaboration with MedISys, developed at the European Commission's Joint Research Centre (EC-JRC)
• Supported by
  • The ContentFactory Project, funded by TEKES
  • Algodan: Algorithmic Data Analysis
    Finnish National Center of Excellence
• In the press
• Etymon: Computational etymology
  • Modeling genetic relationships and reconstruction in Uralic etymological data
  • Supported by the UraLink Project of the Academy of Finland
• Computational Bananas:
  • Application of methods from the area of population genetics to linguistic data, to model and investigate the genetic relationships among members of different language families.
  • Collaboration with J Corander, Dept of Mathematics and Statistics. Supported by HIIT Pump-Priming project.

Previously collaborated on:

• Clarin: European Infrastructure for Language Resources and Technology
  • European Clarin
  • Finnish National Clarin

Publications

On Google Scholar

Links to all publications

Scientific Events

Co-organizer:

• BSNLP-2013:
  The 4th Biennial Workshop on Balto-Slavic Natural Language Processing,
  at the 51st annual meeting of the Association for Computational Linguistics
  August 4-9, 2013, in Sofia, Bulgaria.
• MINUCS:
  Workshop on Mining User-Generated Content for Security,
  at UCMedia-2009: Conference on User-Centric Media
  (December 2009) Venice, Italy
• NODALIDA 2009:
  Nordic Conference on Computational Linguistics.
  (May 2009) Odense, Denmark
• HLIE:
  Workshop on High-level Information Extraction
  at ECML/PKDD-2008.
  (September 2008) Antwerp, Belgium
• MMIES-2:
  Workshop on Multi-source, Multilingual Information Extraction and Summarization,
  at the 2008 COLING Conference
  (August 2008) Manchester, UK
• ESSLLI-2007: European Summer School on Language, Logic and Information
  Course (with Mark Stevenson, University of Sheffield, UK):
  Weakly-supervised Learning for Information Extraction
  Dublin, Ireland
• Workshop on Cross-Document Analysis,
  at the 2006 ACL/COLING conference. (Proceedings on-line.)
  (July 2006) Sydney, Australia

Teaching

2013 Spring:

Models of Language Evolution and Language Change

2011 Fall:

Natural Language Processing

2010 Fall:

Natural Language Processing

2008 Fall:

Text Mining

2008 Spring:

Natural Language Processing

2007 Fall:

Information Extraction: Finding Facts in Text

2007 Summer:

ESSLLI-2007: European Summer School on Language, Logic and Information Dublin, Ireland
Weakly-supervised Learning for Information Extraction
Course, with Mark Stevenson (University of Sheffield, UK)

2007 Summer: University of Joensuu/University of Eastern Finland

Intensive course in Computational Linguistics

2006 Spring:

Introduction to Natural Language Processing

2005 Fall:

Information Extraction

2003 Fall: KIT Graduate School of Language Technology

Weakly-supervised knowledge acquisition

Thesis advisement

If you are interested in a topic for a MSc or a PhD thesis related to:

• computational linguistics, natural language processing, language technology,
• any of the Projects above,
• applying machine learning or information-teoretic methods to problems in these areas

please contact me.

Contact

Roman Yangarber

      Department of Computer Science                 Street address:
      P.O. Box 68                        Exactum Building, Room A224
      FIN-00014 University of Helsinki    Gustaf Hällstörmin katu 2B
      Finland
    

---