Morphology Project: StateMorph

Research:

We develop information-theoretic methods for modeling morphology. The methods are based on the information-theoretic Minimum Description Length Principle (MDL), tested on several languages:

Resources:

Unsupervised Learning of Morphology:

Transliteration:

People:

Collaboration:

Supported by:

Publications: conference and journal papers, book chapters, dissertations

  1. Learning Morphology of Natural Language as a Finite-State Grammar
    Javad Nouri, Roman Yangarber
    In Proceedings of SLSP: the 5th International Conference on Statistical Language and Speech Processing
    (2017) Le Mans, France

  2. Minimum Description Length Models for Unsupervised Learning of Morphology   (Master's Thesis)
    Javad Nouri
    (2016) University of Helsinki, Department of Computer Science

  3. A novel method for evaluation of morphological segmentation
    Javad Nouri, Roman Yangarber
    In Proceedings of LREC: 10th International Conference on Language Resources and Evaluation
    (2016) Portorož, Slovenia

  4. MDL-based Models for Transliteration Generation
    Javad Nouri, Lidia Pivovarova, Roman Yangarber
    In SLSP: International Conference on Statistical Language and Speech Processing
    Springer Verlag, Lecture Notes in Artificial Intelligence (LNAI) Volume 7978,
    (2013) Tarragona, Spain

  5. Hidden Markov models for induction of morphological structure of natural language   
    Hannes Wettig, Suvi Hiltunen, Roman Yangarber.
    WITMSE-2010: Workshop on Information Theoretic Methods in Science and Engineering
    (2010) Tampere, Finland