• 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 : 8 / 17 ÀÌÀü°Ç ÀÌÀü°Ç   ´ÙÀ½°Ç ´ÙÀ½°Ç

ÇѱÛÁ¦¸ñ(Korean Title) Áö½Ä ±×·¡ÇÁ ÀÓº£µù ¹× ÀûÀÀÇü Ŭ·¯½ºÅ͸µÀ» È°¿ëÇÑ ¿À·ù Æ®¸®Çà °ËÃâ
¿µ¹®Á¦¸ñ(English Title) Incorrect Triple Detection Using Knowledge Graph Embedding and Adaptive Clustering
ÀúÀÚ(Author) ½Å¿øö   ³ëÀç½Â   ¹Ú¿µÅà  Won-Chul Shin   Jea-Seung Roh   Young-Tack Park  
¿ø¹®¼ö·Ïó(Citation) VOL 47 NO. 10 PP. 0958 ~ 0964 (2020. 10)
Çѱ۳»¿ë
(Korean Abstract)
ÃÖ±Ù ÀÎÅͳÝÀÇ ¹ßÀüÀ¸·Î Á¤º¸ÀÇ ¾çÀÌ ´Ã¾î³ª¸é¼­ ´ë¿ë·® Áö½Ä ±×·¡ÇÁ¸¦ ÀÌ¿ëÇÑ ¿¬±¸°¡ È°¹ßÈ÷ ÀÌ·ç¾îÁö°í ÀÖ´Ù. ¶ÇÇÑ Áö½Ä ±×·¡ÇÁ°¡ ´Ù¾çÇÑ ¿¬±¸¿Í ¼­ºñ½º¿¡ È°¿ëµÊ¿¡ µû¶ó ¾çÁúÀÇ Áö½Ä ±×·¡ÇÁ¸¦ È®º¸ÇØ¾ß ÇÏ´Â Çʿ伺ÀÌ ´ëµÎµÇ°í ÀÖ´Ù. ÇÏÁö¸¸ ¾çÁúÀÇ Áö½Ä ±×·¡ÇÁ¸¦ ¾ò±â À§ÇØ Áö½Ä ±×·¡ÇÁ ³» ¿À·ù¸¦ °ËÃâÇÏ´Â ¿¬±¸°¡ ºÎÁ·ÇÏ´Ù. ¿À·ù Æ®¸®Çà °ËÃâÀ» À§ÇØ ÀÓº£µù°ú Ŭ·¯½ºÅ͸µÀ» »ç¿ëÇÑ ÀÌÀü ¿¬±¸°¡ ÁÁÀº ¼º´ÉÀ» ³ªÅ¸³Â´Ù. ÇÏÁö¸¸ Ŭ·¯½ºÅÍ ÃÖÀûÈ­ °úÁ¤¿¡¼­ ÀÏ°ýÀûÀ¸·Î µ¿ÀÏÇÑ ÀÓ°è°ªÀ» »ç¿ëÇÏ¿© °¢ Ŭ·¯½ºÅÍÀÇ Æ¯¼ºÀ» °í·ÁÇÏÁö ¸øÇÏ´Â ¹®Á¦°¡ Á¸ÀçÇÏ¿´´Ù. º» ³í¹®¿¡¼­´Â ÀÌ·¯ÇÑ ¹®Á¦¸¦ ÇØ°áÇÏ°íÀÚ Áö½Ä ±×·¡ÇÁ ³» ¿À·ù Æ®¸®Çà °ËÃâÀ» À§ÇØ Áö½Ä ±×·¡ÇÁ¿¡ ´ëÇÑ ÀÓº£µù°ú ÇÔ²² °¢ Ŭ·¯½ºÅÍ¿¡ ´ëÇÑ ÃÖÀûÀÇ Threshold¸¦ ã¾Æ Àû¿ëÇÔÀ¸·Î½á Ŭ·¯½ºÅ͸µÀ» ÁøÇàÇÏ´Â ÀûÀÀÇü Ŭ·¯½ºÅ͸µ ¸ðµ¨À» Á¦¾ÈÇÑ´Ù. º» ³í¹®¿¡¼­ Á¦¾ÈÇÏ´Â ¹æ¹ýÀÇ ¼º´ÉÀ» Æò°¡Çϱâ À§ÇØ DBpeida, Freebase¿Í WiseKB ¼¼ °¡Áö µ¥ÀÌÅͼÂÀ» ´ë»óÀ¸·Î ±âÁ¸ ¿À·ù Æ®¸®Çà °ËÃâ ¿¬±¸¿Í ºñ±³ ½ÇÇèÀ» ÁøÇàÇÏ¿´À¸¸ç F1-Score¸¦ ±âÁØÀ¸·Î Æò±Õ 5.3% ³ôÀº ¼º´ÉÀ» È®ÀÎÇÏ¿´´Ù.
¿µ¹®³»¿ë
(English Abstract)
Recently, with the increase in the amount of information from the development of the Internet, research using large-capacity knowledge graphs is being actively conducted. Additionally, as knowledge graphs are used for various research and services, there is a need to secure quality knowledge graphs. However, there is a lack of research to detect errors within the knowledge graphs to obtain quality knowledge graphs. Previous studies using the embedding and clustering for error triple detection showed good performance. However, in the process of the cluster optimization, there was a problem that the characteristics of each cluster could not be factored using the same threshold collectively. In this paper, to resolve these problems, we propose an adaptive clustering model in which clustering is conducted by finding and applying the optimum threshold for each cluster with the embedding for knowledge graph for error triple detection in the knowledge graph. To evaluate the performance of the method proposed in this paper, the existing error triple detection studies and comparative experiments were conducted on three datasets, DBpeida, Frebase and WiseKB, and the high performance was confirmed by an average of 5.3% based on the F1-Score.
Å°¿öµå(Keyword) Áö½Ä ±×·¡ÇÁ   ÀÓº£µù   Ŭ·¯½ºÅ͸µ   µö·¯´×   knowledge graphs   embedding   clustering   deep learning  
ÆÄÀÏ÷ºÎ PDF ´Ù¿î·Îµå