Morphological Disambiguation

The MILA Morphological Disambiguation Tool takes as input morphologically-analyzed text and uses a Hidden Markov Model (HMM) to assign scores for each analysis, considering contextual information from the rest of the sentence. For a given token, all analyses deemed impossible are given scores of 0; all n analyses deemed possible are given positive scores.


  • Online Demo
    Enter up to 100 tokens of undotted Hebrew text:

  • Online Tool
    An online version of the disambiguator allows uploading of Hebrew text files, then provides the disambiguated result for download, without requiring any software installation.
    XML output follow MILA's XML standards for corpora.
    Password-protected Password-protected. Please register to access (free for non-commercial use).
  • Full Program
    XML output follow MILA's XML standards for corpora.
    Password-protected Password-protected. Please register to access (free for non-commercial use).
  • Documentation (in English)
    PDF file, 85 KB.
  • Documentation (in Hebrew)
    PDF file, 162 KB.

Related Publications


Credits

License

For non-commercial research purposes, this tool is licensed under the GNU General Public License (GPL). Any publications resulting from the use of this tool should refer to it as "The MILA Hebrew Morphological Disambiguation Tool" and cite:

Roy Bar-Haim, Khalil Sima'an and Yoad Winter. Part-of-Speech Tagging of Modern Hebrew Text. Natural Language Engineering 14 (2):223-251. Copyright Cambridge University Press. 2008. [BibTeX]

To gain password access to this tool for non-commercial purposes, please register. For commercial usage, please contact MILA to inquire about terms.