• 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 :

ÇѱÛÁ¦¸ñ(Korean Title) ´º·²-½Éº¼¸¯ ±¸Á¶ ±â¹ÝÀÇ °ü°è ÃßÃâ
¿µ¹®Á¦¸ñ(English Title) Relation Extraction based on Neural-Symbolic Structure
ÀúÀÚ(Author) ¿ÀÁø¿µ   Â÷Á¤¿ø   Jinyoung Oh   Jeong-Won Cha  
¿ø¹®¼ö·Ïó(Citation) VOL 48 NO. 05 PP. 0533 ~ 0538 (2021. 05)
Çѱ۳»¿ë
(Korean Abstract)
µö·¯´×Àº ÀÚ¿¬¾îó¸® ºÐ¾ß¿¡¼­ ¿ì¼öÇÑ ¼º´ÉÀ» º¸ÀÌ°í ÀÖ´Ù. ÇÏÁö¸¸ ¿ì¼öÇÑ ¼º´ÉÀ» ´Þ¼ºÇÏ·Á¸é ¸¹Àº ÇнÀ µ¥ÀÌÅÍ¿Í ±ä ÇнÀ ½Ã°£ÀÌ ÇÊ¿äÇÏ´Ù. ¿ì¸®´Â °ü°è ÃßÃâ ¹®Á¦¿¡ ´ëÇÏ¿© ´º·²-½Éº¼¸¯ ¹æ¹ýÀ» ÀÌ¿ëÇÏ¿© ÀûÀº ÇнÀ µ¥ÀÌÅÍ È¯°æ¿¡¼­ µö·¯´×ÀÇ ¼º´ÉÀ» ´É°¡ÇÏ´Â ¹æ¹ýÀ» Á¦¾ÈÇÑ´Ù. ±ÔÄ¢ °á°ú¿Í µö·¯´× °á°ú¿Í ÀÇ ºÒÀÏÄ¡µµ¸¦ »ç¿ëÇÏ´Â ±¸Á¶¸¦ ¼³°èÇÏ¿´´Ù. ¶ÇÇÑ ¼ö·Å¼Óµµ¸¦ Çâ»ó½ÃÅ°±â À§Çؼ­ ³í¸® ±ÔÄ¢ ÇÊÅ͸µÀ» Á¦¾ÈÇÏ°í ±ÔÄ¢ÀÇ ¼º´ÉÀ» ³ôÀ̱â À§ÇØ ¹®¸ÆÀ» Ãß°¡ÇÏ¿´´Ù. Á¦¾È ±¸Á¶´Â ÀûÀº ÇнÀ µ¥ÀÌÅÍ¿¡ ´ëÇؼ­ ¿ì¼öÇÑ ¼º´ÉÀ» º¸¿´À¸¸ç, ºü¸¥ ¼º´É ¼ö·ÅÀÌ ÀÌ·ç¾îÁö´Â °ÍÀ» È®ÀÎÇÏ¿´´Ù.
¿µ¹®³»¿ë
(English Abstract)
Deep learning has been continually demonstrating excellent performance in the field of natural language processing. However, enormous training data and long training time are required to achieve good performance. Herein, we propose a method that exceeds deep learning performance in a small learning data environment by using a neural-symbolic method for the relationship extraction problem. We have designed a structure that uses the inconsistency between the rule results and deep learning results. In addition, logical rule filtering has been proposed to improve the convergence speed and a context has been added to improve the performance of the rule. The proposed method showed excellent performance for a small amount of training data, and we confirmed that fast performance convergence was achieved.
Å°¿öµå(Keyword) ´º·²-½Éº¼¸¯   °ü°èÃßÃâ   µö·¯´×   ÀÚ¿¬¾î󸮠  neural-symbolic   relation extraction   deep learning   natural language processing  
ÆÄÀÏ÷ºÎ PDF ´Ù¿î·Îµå