Morpho project

The goal of the Morpho project is to develop unsupervised data-driven methods that discover the regularities behind word forming in natural languages. In particular, we are focussing on the discovery of morphemes, which are the primitive units of syntax, the smallest individually meaningful elements in the utterances of a language. Morphemes are important in automatic generation and recognition of a language, especially in languages in which words may have many different inflected forms.

Read more about the problem and our methods or see the list of publications.

Demonstrations and packages

• Morfessor demonstration: Try the segmentation of words into morphs
• Morfessor Categories-MAP 0.9.2 software
  • Download Morfessor Categories-MAP (100 kB, published under GNU GPL)
  • Related article: Mathias Creutz and Krista Lagus (2005). Inducing the Morphological Lexicon of a Natural Language from Unannotated Text. In Proceedings of the International and Interdisciplinary Conference on Adaptive Knowledge Representation and Reasoning (AKRR'05), Espoo, Finland, 15-17 June.
    [ Article (PDF) ]
• Morfessor 1.0 software (Morfessor Baseline algorithm)
  • Download morfessor1.0.perl (60 kB, published under GNU GPL)
  • Related article: Mathias Creutz and Krista Lagus (2005). Unsupervised Morpheme Segmentation and Morphology Induction from Text Corpora Using Morfessor 1.0. Publications in Computer and Information Science, Report A81, Helsinki University of Technology, March.
    [ Abstract ]   [ Article (PDF) ]
• Hutmegs 1.0 evaluation package (Helsinki University of Technology Morphological Evaluation Gold Standard).
  • Download Hutmegs version 1.0 (9.6 MB)
  • Related article: Mathias Creutz and Krister Lindén (2004). Morpheme Segmentation Gold Standards for Finnish and English. Publications in Computer and Information Science, Report A77, Helsinki University of Technology, October.
    [ Abstract ]  [ Article (PDF) ]

Morpho Challenges

For overview of the Morpho Challenges, see http://research.ics.tkk.fi/events/morphochallenge/.

The previous Challenge we have organized is Morpho Challenge 2010 - Semi-supervised and Unsupervised Analysis.

Older Challenges: 2009 2008 2007 2005

Press releases (in Finnish)

• Tietokone oppii sanojen rakenneyksiköt (julkaistu 2.6.2005)

People

• Krista Lagus
• Mathias Creutz
• Sami Virpioja

The Morpho project is part of the Adaptive Natural Language Processing research activities.