• 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¸Ã³¸®ÇÐȸ ³í¹®Áö > Á¤º¸Ã³¸®ÇÐȸ ³í¹®Áö ¼ÒÇÁÆ®¿þ¾î ¹× µ¥ÀÌÅÍ °øÇÐ

Á¤º¸Ã³¸®ÇÐȸ ³í¹®Áö ¼ÒÇÁÆ®¿þ¾î ¹× µ¥ÀÌÅÍ °øÇÐ

Current Result Document : 4 / 10 ÀÌÀü°Ç ÀÌÀü°Ç   ´ÙÀ½°Ç ´ÙÀ½°Ç

ÇѱÛÁ¦¸ñ(Korean Title) ½Å°æ ÅÙ¼­¸ÁÀ» ÀÌ¿ëÇÑ ÄÁ¼Á³Ý ÀÚµ¿ È®Àå
¿µ¹®Á¦¸ñ(English Title) Automatic Expansion of ConceptNet by Using Neural Tensor Networks
ÀúÀÚ(Author) ÃÖ¿ë¼®   ÀÌ°æÈ£   ÀÌ°øÁÖ   Yong Seok Choi   Gyoung Ho Lee   Kong Joo Lee  
¿ø¹®¼ö·Ïó(Citation) VOL 05 NO. 11 PP. 0549 ~ 0554 (2016. 11)
Çѱ۳»¿ë
(Korean Abstract)
ÄÁ¼Á³ÝÀº ÀϹݻó½ÄÀ» ³ëµå(°³³ä)¿Í ¿¡Áö(°ü°è)·Î Ç¥ÇöÇØ ³õÀº ±×·¡ÇÁ ÇüÅÂÀÇ Áö½Ä º£À̽ºÀÌ´Ù. ¿ÏÀüÇÑ Áö½Ä º£À̽º¸¦ ±¸ÃàÇÏ´Â °ÍÀº ¸Å¿ì ¾î·Á¿î ¹®Á¦À̱⠶§¹®¿¡ Áö½Ä º£À̽º´Â ¹Ì¿Ï°áµÈ ÇüÅÂÀÇ µ¥ÀÌÅ͸¦ ´ã°í ÀÖ´Â °æ¿ì°¡ ¸¹´Ù. ºÒ¿ÏÀüÇÑ Áö½ÄÀ» ´ã°í ÀÖ´Â Áö½Ä º£À̽º·ÎºÎÅÍÀÇ Ãß·Ð °á°ú´Â ½Å·ÚÇϱ⠾î·Æ±â ¶§¹®¿¡ Áö½ÄÀÇ ¿Ï°á¼ºÀ» ³ôÀ̱â À§ÇÑ ¹æ¹ýÀÌ ÇÊ¿äÇÏ´Ù. º» ³í¹®¿¡¼­´Â ½Å°æ ÅÙ¼­¸ÁÀ» ÀÌ¿ëÇÏ¿© ÄÁ¼Á³ÝÀÇ Áö½Ä ¹Ì¿Ï°á¼º ¹®Á¦¸¦ ¿ÏÈ­ÇØ º¸°íÀÚ ÇÑ´Ù. ÄÁ¼Á³Ý¿¡¼­ ÃßÃâÇÑ »ç½ÇÁÖÀå(assertion)À» ÀÌ¿ëÇÏ¿© ½Å°æ ÅÙ¼­¸ÁÀ» ÇнÀ½ÃŲ´Ù. ÇнÀµÈ ½Å°æ ÅÙ¼­¸ÁÀº µÎ °³ÀÇ °³³ä Á¤º¸¸¦ ÀÔ·ÂÀ¸·Î ¹Þ°í, ±× µÎ °³³äÀÌ Æ¯Á¤ °ü°è·Î ¿¬°áµÉ ¼ö ÀÖ´ÂÁö¸¦ ³ªÅ¸³»´Â Á¡¼ö°ªÀ» Ãâ·ÂÇÑ´Ù. ÀÌ¿Í °°ÀÌ ½Å°æ ÅÙ¼­¸ÁÀº ³ëµåµéÀÇ ¿¬°á Â÷¼ö(degree)¸¦ ³ô¿©, ÄÁ¼Á³ÝÀÇ ¿Ï°á¼ºÀ» Áõ´ë½Ãų ¼ö ÀÖ´Ù. º» ¿¬±¸¿¡¼­ ÇнÀ½ÃŲ ½Å°æ ÅÙ¼­¸ÁÀº Æò°¡µ¥ÀÌÅÍ¿¡ ´ëÇؼ­ ¾à 87.7%ÀÇ Á¤È®µµ¸¦ º¸¿´´Ù. ¶ÇÇÑ ÄÁ¼Á³Ý¿¡ ¿¬°áÀÌ ¾ø´Â ³ëµå ½Ö¿¡ ´ëÇÏ¿© 85.01%ÀÇ Á¤È®µµ·Î »õ·Î¿î °ü°è¸¦ ¿¹ÃøÇÒ ¼ö ÀÖ¾ú´Ù.
¿µ¹®³»¿ë
(English Abstract)
ConceptNet is a common sense knowledge base which is formed in a semantic graph whose nodes represent concepts and edges show relationships between concepts. As it is difficult to make knowledge base integrity, a knowledge base often suffers from incompleteness problem. Therefore the quality of reasoning performed over such knowledge bases is sometimes unreliable. This work presents neural tensor networks which can alleviate the problem of knowledge bases incompleteness by reasoning new assertions and adding them into ConceptNet. The neural tensor networks are trained with a collection of assertions extracted from ConceptNet. The input of the networks is two concepts, and the output is the confidence score, telling how possible the connection between two concepts is under a specified relationship. The neural tensor networks can expand the usefulness of ConceptNet by increasing the degree of nodes. The accuracy of the neural tensor networks is 87.7% on testing data set. Also the neural tensor networks can predict a new assertion which does not exist in ConceptNet with an accuracy 85.01%.
Å°¿öµå(Keyword) ÄÁ¼Á³Ý   ½Å°æ ÅÙ¼­¸Á   Àç±Í ½Å°æ¸Á   ConceptNet   Neural Tensor Networks   Recurrent Neural Networks  
ÆÄÀÏ÷ºÎ PDF ´Ù¿î·Îµå