• Àüü
  • ÀüÀÚ/Àü±â
  • Åë½Å
  • ÄÄÇ»ÅÍ
´Ý±â

»çÀÌÆ®¸Ê

Loading..

Please wait....

±¹³» ³í¹®Áö

Ȩ Ȩ > ¿¬±¸¹®Çå > ±¹³» ³í¹®Áö > Çѱ¹Á¤º¸°úÇÐȸ ³í¹®Áö > Á¤º¸°úÇÐȸ³í¹®Áö (Journal of KIISE)

Á¤º¸°úÇÐȸ³í¹®Áö (Journal of KIISE)

Current Result Document : 27 / 29

ÇѱÛÁ¦¸ñ(Korean Title) °øÀ¯°èÃþÀ» ÀÌ¿ëÇÑ ÇüÅÂ¼Ò ºÐ¼®°ú °³Ã¼¸í ÀÎ½Ä ÅëÇÕ ¸ðµ¨
¿µ¹®Á¦¸ñ(English Title) Joint Model of Morphological Analysis and Named Entity Recognition Using Shared Layer
ÀúÀÚ(Author) ±èÈ«Áø   ¹Ú¼º½Ä   ±èÇмö   Hongjin Kim   Seongsik Park   Harksoo Kim  
¿ø¹®¼ö·Ïó(Citation) VOL 48 NO. 02 PP. 0167 ~ 0173 (2021. 02)
Çѱ۳»¿ë
(Korean Abstract)
Çѱ¹¾î ÇüÅÂ¼Ò ºÐ¼®Àº ÇüÅÂ¼Ò ºÐ¼®, Ç°»ç ÅÂ±ë °úÁ¤À¸·Î ³ª´¶´Ù. ÇüÅÂ¼Ò ºÐ¼® °úÁ¤¿¡¼­ ÇüÅÂ¼Ò¿Í Ç°»ç Èĺ¸ ½ÖÀ» ÃßÃâÇÏ°í, Ç°»ç ÅÂ±ë °úÁ¤¿¡¼­´Â ÃßÃâµÈ Èĺ¸ Áß ¹®¸Æ¿¡ ¾Ë¸ÂÀº ÇüÅÂ¼Ò¿Í Ç°»ç¸¦ °áÁ¤ÇÑ´Ù. °³Ã¼¸í ÀνÄÀº ¹®Àå ³»¿¡¼­ Àθí, Áö¸í, ±â°ü¸í, ³¯Â¥, ½Ã°£ µî°ú °°ÀÌ °íÀ¯ÇÑ Àǹ̸¦ °®´Â ´Ü¾î¸¦ ã¾Æ °³Ã¼¸íÀ» ºÎÂøÇÏ´Â ±â¼úÀÌ´Ù. °³Ã¼¸í Àνİú ÇüÅÂ¼Ò ºÐ¼® ¿¬±¸´Â ÁÖ·Î µ¶¸³ÀûÀ¸·Î ¼öÇàµÇ¸ç, ¸¹Àº °³Ã¼¸í ÀÎ½Ä ¿¬±¸¿¡¼­ Ç°»ç Á¤º¸¸¦ »ç¿ëÇÑ´Ù. ÀÌ °úÁ¤¿¡¼­ ÇüÅÂ¼Ò ºÐ¼®ÀÇ ¿À·ù°¡ °³Ã¼¸í ÀνĿ¡ Ä¡¸íÀûÀÎ ¿À·ù·Î ÀüÆĵȴÙ. º» ³í¹®¿¡¼­´Â ¿À·ù ÀüÆĸ¦ ÃÖ¼ÒÈ­Çϱâ À§ÇØ ÅëÇÕ ¸ðµ¨À» Á¦¾ÈÇÑ´Ù. ÇüÅÂ¼Ò ºÐ¼®±âÀÇ ¿À·ù¸¦ ÁÙÀ̱â À§ÇØ ¼øÂ÷Àû ·¹ÀÌºí ºÎÂø ¹®Á¦¿¡ È¿°úÀûÀÎ ·¹À̺í ÁÖÀÇ ÁýÁß ³×Æ®¿öÅ©¸¦ È°¿ëÇÑ´Ù. ½ÇÇè °á°ú, °³Ã¼¸í Àνİú ÇüÅÂ¼Ò ºÐ¼®ÀÇ ´ÜÀÏ ¸ðµ¨º¸´Ù ÅëÇÕ ¸ðµ¨ÀÇ ¼º´ÉÀÌ ´õ ³ôÀ½À» º¸¿´´Ù. ¶ÇÇÑ ±âÁ¸ÀÇ ÅëÇո𵨠º¸´Ù ·¹À̺í ÁÖÀÇ ÁýÁß ³×Æ®¿öÅ©¸¦ Àû¿ëÇÑ Á¦¾È ¸ðµ¨ÀÌ ´õ ³ôÀº ¼º´ÉÀ» º¸¿´´Ù.
¿µ¹®³»¿ë
(English Abstract)
Named entity recognition is a natural language processing technology that finds words with unique meanings such as human names, place names, organization names, dates, and time in sentences and attaches them. Morphological analysis in Korean is generally divided into morphological analysis and part-of-speech tagging. In general, named entity recognition and morphological analysis studies conducted in independently. However, in this architecture, the error of morphological analysis propagates to named entity recognition. To alleviate the error propagation problem, we propose an integrated model using Label Attention Network (LAN). As a result of the experiment, our model shows better performance than the single model of named entity recognition and morphological analysis. Our model also demonstrates better performance than previous integration models.
Å°¿öµå(Keyword) °³Ã¼¸í ÀνĠ  ÇüÅÂ¼Ò ºÐ¼®   ·¹À̺í ÁÖÀÇÁýÁß ³×Æ®¿öÅ©   ÅëÇÕ ¸ðµ¨   named entity recognition   morphological analysis   label attention network   integrated model  
ÆÄÀÏ÷ºÎ PDF ´Ù¿î·Îµå