moHANA

Morphological Hangul Analyzer

Seung-hyun Seo, In-Ho Kang, and Jae-Dong Kim


Version: 0.9
Date: 11.21.2007

Overview

 

moHANA is a morphological hangul analyzer that analyzes korean words. Parts of Speech are categorized along five general dimension values: word class, morphological, syntactical, semantic, and pragmatic. In other words, the Parts of Speech in moHANA contain all information required to analyze korean words.

 

Binaries

Our beta version is free to download and use. However, you can get the first dimensional value of Part of Speech only.

 

Installation

To install moHANA you need to download moHANA.tar.gz.

 

How to use

moHANA is called with the following parameters:

        -h         - this help

        -1         - use level 1 grammar (default)
        -2         - use level 1 and 2 grammars

        -n         - show all analyzed results
        -c         - convert hanja to hangul
        -i         - show the original inflected form of a word
                     (show the root form of a word is default)

 

Some Example Analyses

    ./moHANA
      
  • Çб³´Â
  •   Çб³_{ncn} + ´Â_{j}
     
  • Çлý¹×¼±»ý
  •   Çлý_{ncn} + ¹×_{ad} + ¼±»ý_{ncn}
     
  • ¾ÈÀû´Â
  •   ¾ÈÀû´Â_{unk}
     
  • ¾ö¸¶¿Í¾ÆÀÌ
  •   ¾ö¸¶_{ncn} + ¿Í¾ÆÀÌ_{unk}

     

    Analyze grammatically incorrect expressions

        ./moHANA -2
          
  • Çб³´Â
  •   Çб³_{ncn} + ´Â_{j}
     
  • Çлý¹×¼±»ý
  •   Çлý_{ncn} + ¹×_{ad} + ¼±»ý_{ncn}
     
  • ¾ÈÀû´Â
  •   ¾È_{ad} + Àû_{pv} + ´Â_{ef}
     
  • ¾ö¸¶¿Í¾ÆÀÌ
  •   ¾ö¸¶_{ncn} + ¿Í_{j} + ¾ÆÀÌ_{ncn}

     

    Analyze common writing errors

        ./moHANA -2
          
  • À߸ԴÂ
  •   Àß_{ad} + ¸Ô_{pv} + ´Â_{ef}
     
  • ¾È¿¹»µÁö´Â
  •   ¾È_{ad} + ¿¹»µ_{pa} + ¾î_{ef} + Áö_{aux} + ´Â_{ef}
     
  • ¸øÀÚ¸£´Â
  •   ¸ø_{ad} + ÀÚ¸£_{pv} + ´Â_{ef}
     
  • ¾È¹Ì²ô·¯¿î
  •   ¾È_{ad} + ¹Ì²ô·´_{pa} + Àº_{ef}
     
     
  • ÆíÁö¿¡´ëÇÑ
  •   ÆíÁö_{ncp} + ¿¡_{j} + ´ëÇÏ_{pv} + ¤¤_{ef}
     
  • ûÁÖ¿¡°¡´Â¹æ¹ý
  •   ûÁÖ_{ncn} + ¿¡_{j} + °¡_{pv} + ´Â_{ef} + ¹æ¹ý_{ncn}
     
  • »ýÁ¸ÇϱâÀ§Çѹæ¹ý
  •   »ýÁ¸_{ncp} + ÇÏ_{vfix} + ±â_{ef} + À§ÇÏ_{pv} + ¤¤_{ef} + ¹æ¹ý_{ncn}
     
  • ÅÂdzÀ¸·ÎÀÎÇÑÇÇÇØ
  •   ÅÂdz_{ncn} + À¸·Î_{j} + ÀÎÇÏ_{pv} + ¤¤_{ef} + ÇÇÇØ_{ncp}
     
     
  • ¸ÔÁö¸øÇÏ´Â
  •   ¸Ô_{pv} + Áö_{ef} + ¸øÇÏ_{aux} + ´Â_{ef}
     
     
  • Ã¥»ó°úÀÇÀÚ
  •   Ã¥»ó_{ncn} + °ú_{j} + ÀÇÀÚ_{ncn}
     
  • ÀÌÈ¿¸®Àdz²ÀÚÄ£±¸
  •   ÀÌÈ¿¸®_{nq_per} + ÀÇ_{j} + ³²ÀÚ_{ncn} + Ä£±¸_{ncn}

     

    Analyze very long legal terms

        ./moHANA -2
          
  • Áö°¡°ø½Ã¹×ÅäÁöµîÀÇÆò°¡¿¡´ëÇѹý·ü
  •   Áö°¡°ø½Ã_{ncp} + ¹×_{ad} + ÅäÁö_{ncn} + µî_{nfix} + ÀÇ_{j} + Æò°¡_{ncp} + ¿¡_{j} + ´ëÇÏ_{pv} + ¤¤_{ef} + ¹ý·ü_{ncn}
     
  • ¼º¸Å¸Å¾Ë¼±µîÇàÀ§ÀÇó¹ú¿¡´ëÇѹý·ü
  •   ¼º¸Å¸Å_{ncn} + ¾Ë¼±_{ncp} + µî_{nfix} + ÇàÀ§_{ncn} + ÀÇ_{j} + ó¹ú_{ncp} + ¿¡_{j} + ´ëÇÏ_{pv} + ¤¤_{ef} + ¹ý·ü_{ncn}

     

    Generic affix analysis

        ./moHANA
          
  • ¼­±ÍÆ÷½Ã¸¦
  •   ¼­±ÍÆ÷_{nq_loc} + ½Ã_{nfix} + ¸¦_{j}
     
  • ¼­±ÍÆ÷¿ªÀ»
  •   ¼­±ÍÆ÷_{nq_loc} + ¿ª_{nfix} + À»_{j}
     
  • ¼­±ÍÆ÷Á¡À»
  •   ¼­±ÍÆ÷_{nq_loc} + Á¡_{nfix} + À»_{j}
     
     
  • (ÁÖ)¸¶ÀÌÅ©·Î¼ÒÇÁÆ®
  •   (ÁÖ)_{pref} + ¸¶ÀÌÅ©·Î_{nq_gro} + ¼ÒÇÁÆ®_{ncp}
     
  • (ÁÖ)Æ÷Ç×Á¦Ã¶
  •   (ÁÖ)_{pref} + Æ÷Ç×_{nq_gro} + Á¦Ã¶_{ncp}
     
  • (ÁÖ)ÄÄÇ»ÅÍ
  •   (_{ascii} + ÁÖ_{nc_one} + )_{ascii} + ÄÄÇ»ÅÍ_{ncn}

     

    Questions and Bug Reports

    If you have questions, please contact us via shsuh at wordwords.co.kr

     

    Disclaimer

    This software is free only for non-commercial use. It must not be distributed without prior permission of WordWords Corp. Korea Patent (10-2007-0024439) applied for by WordWords Corp.


    eXTReMe Tracker