• 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 : 7 / 17 ÀÌÀü°Ç ÀÌÀü°Ç   ´ÙÀ½°Ç ´ÙÀ½°Ç

ÇѱÛÁ¦¸ñ(Korean Title) ´º·Î ½Éº¼¸¯ ±â¹Ý ±ÔÄ¢ »ý¼ºÀ» ÅëÇÑ Áö½Ä ¿Ï¼º ±â¹ý
¿µ¹®Á¦¸ñ(English Title) A Knowledge Completion Approach using Rule Generation based on Neuro-Symbolic Method
ÀúÀÚ(Author) ³ëÀç½Â   ½Å¿øö   ¹ÚÇö±Ô   ¹Ú¿µÅà  Jea-Seung Roh   Won-Chul Shin   Hyun-Kyu Park   Young-Tack Park  
¿ø¹®¼ö·Ïó(Citation) VOL 48 NO. 04 PP. 0425 ~ 0433 (2021. 04)
Çѱ۳»¿ë
(Korean Abstract)
Áö½Ä ±×·¡ÇÁ´Â ½Ç¼¼°èÀÇ Áö½ÄÀ» ´Ù¾çÇÑ ¼Ò½º·ÎºÎÅÍ ¼öÁýÇÏ¿© ±¸Á¶È­µÈ ¹æ½ÄÀ¸·Î Ç¥ÇöÇÑ °ÍÀÌ´Ù. Áö½Ä ±×·¡ÇÁ´Â µ¥ÀÌÅÍµé °£ÀÇ °ü°è¸¦ Ç¥ÇöÇÑ ³×Æ®¿öÅ©·Î¼­ ÀΰøÁö´É ±â¼ú¿¡ Á¢¸ñµÇ¾î ´Ù¾çÇÏ°Ô È°¿ëµÇ°í ÀÖÁö¸¸, ¿£Æ¼Æ¼ ¶Ç´Â ¿£Æ¼Æ¼ »çÀÌÀÇ ¸µÅ©°¡ ´©¶ôµÇ¾î Áö½ÄÀÇ ºÒ¿ÏÀü¼º¿¡ ´ëÇÑ ¹®Á¦°¡ Á¸ÀçÇÑ´Ù. ÀÌ·¯ÇÑ ¹®Á¦ ÇØ°áÀ» À§ÇØ ÀÚµ¿ Áö½Ä ¿Ï¼º ±â¹ý ¿¬±¸°¡ Áß¿äÇÏ°Ô ¿ä±¸µÇ¸ç, ÀÓº£µù ±â¹ýÀ» »ç¿ëÇϰųª µö·¯´×À» È°¿ëÇÑ ¿¬±¸¿Í ¿ÂÅç·ÎÁö¸¦ ÀÌ¿ëÇÑ ½Éº¼¸¯ ±ÔÄ¢ Ãß·ÐÀ» ÅëÇÑ Áö½Ä ¿Ï¼º ¼öÇà°ú °°Àº ´Ù¾çÇÑ ¿¬±¸µéÀÌ ÁøÇàµÇ¾ú´Ù. ÀÌ·¯ÇÑ ¹æ½ÄÀ» ÅëÇØ È¿À²ÀûÀ¸·Î ÀÚµ¿ Áö½Ä ¿Ï¼ºÀ» ¼öÇàÇÏÁö¸¸ µö·¯´× ¹æ½ÄÀº µ¥ÀÌÅÍ ±â¹ÝÀÇ Ã³¸® ¹æ½ÄÀ¸·Î ÀÎÇØ ´ë·®ÀÇ ÇнÀ µ¥ÀÌÅÍ°¡ ¿ä±¸µÇ¸ç, °á°ú¿¡ ´ëÇÑ ¼³¸íÀÌ ºÒ°¡´ÉÇÑ ¹®Á¦Á¡ÀÌ ÀÖ´Ù. ±×¸®°í ¿ÂÅç·ÎÁö ±â¹ÝÀÇ ¹æ½ÄÀº Àü¹®°¡¿¡ ÀÇÇØ Á¤ÀÇµÈ ¿ÂÅç·ÎÁö ¹× ±ÔÄ¢ÀÌ ÇÊ¿äÇÏ´Ù´Â ¹®Á¦°¡ Á¸ÀçÇÑ´Ù. µû¶ó¼­ º» ³í¹®¿¡¼­´Â ´º·Î ½Éº¼¸¯ ¹æ½ÄÀ» ÀÌ¿ëÇÏ¿© µ¥ÀÌÅÍ¿¡ ³»Æ÷µÈ ±ÔÄ¢À» ¸í½ÃÀûÀ¸·Î ÃßÃâÇÏ¿© ÀÚµ¿ Áö½Ä ¿Ï¼º ¹æ¹ýÀ» Á¦¾ÈÇÑ´Ù. ±ÔÄ¢ ÃßÃâÀ» À§ÇØ ½Éº¼¸¯ ¹æ½ÄÀÇ ´ÜÀÏÈ­(unification) ±â¹ÝÀÇ ¸±·¹ÀÌ¼Ç ÀÓº£µù °æ·Î¸¦ ±¸ÇöÇÏ°í, ÀÌ¿¡ ´ëÇÑ ¼Õ½Ç ÇÔ¼ö¸¦ Á¤ÀÇÇÏ¿© ÀÚµ¿À¸·Î ±ÔÄ¢À» »ý¼ºÇÑ´Ù. ±âÁ¸ÀÇ ÀÓº£µù ±â¹ý¿¡ ºñÇÏ¿© ´º·Î ½Éº¼¸¯ ¹æ½ÄÀº ¼Óµµ¿Í ¼º´ÉÀÌ ´õ ¿ì¿ùÇÔÀ» º¸¿©ÁØ´Ù. Á¦¾ÈÇÏ´Â ¹æ¹ýÀÇ ¼º´ÉÀ» ÃøÁ¤Çϱâ À§ÇØ Nations, UMLS, Kinship µ¥ÀÌÅÍ ¼ÂÀ» ´ë»óÀ¸·Î ÃֽŠÁö½Ä ¿Ï¼º ¿¬±¸¿Í ºñ±³ ½ÇÇèÀ» ÁøÇàÇÏ¿´À¸¸ç, ÇнÀ ½Ã°£ÀÌ Å©°Ô °¨¼ÒÇß°í, Æò±ÕÀûÀ¸·Î ¼º´ÉÀÌ 37.5%p Áõ°¡ÇÑ °ÍÀ» È®ÀÎÇÏ¿´´Ù.
¿µ¹®³»¿ë
(English Abstract)
A knowledge graph is a structured representation of real-world knowledge and is designed by collecting information from various sources. These knowledge graphs are networks that represent relationships between data and are applied in various fields of artificial intelligence; however, there exists problems related to incomplete knowledge due to the omission of entities or omission links between the entities. To resolve the problems, research on automatic knowledge completion techniques is necessitated. Consequently, various studies have been examined including embedding techniques, deep learning or symbolic rule inference using ontology. Although automatic knowledge completion can be efficiently performed through the above-mentioned methods, deep learning methods require a large amount of learning data due to data-driven processing methods, and there exist problems related to the results that are hard to explain. Futhermore, ontology-based methods require ontology and rules that are defined by the experts. To overcome this limitation, in this study, we propose an automatic knowledge completion method by explicitly extracting the implicit rules from the data based on the Neuro-Symbolic method. For rule extraction, we have implemented a symbolic unification based embedding path and defined a cost function for it to automatically generate the rules. Compared with the approaches presented in previous embedding studies, the proposed method demonstrates the superiority of the Neuro-Symbolic method concerning speed and performance. To assess the performance of the proposed method, for datasets like Nations, UMLS, and Kinship, experiments were conducted in comparison with the approach of the state-of-the-art knowledge completion studies. Consequently, an immense reduction in the training time and 37.5%p increase in the average performance were observed.
Å°¿öµå(Keyword) Áö½Ä ±×·¡ÇÁ   Áö½Ä ¿Ï¼º   ÀÓº£µù. ´º·Î ½Éº¼¸¯   knowledge graph   knowledge completion   embedding   neuro-symbolic  
ÆÄÀÏ÷ºÎ PDF ´Ù¿î·Îµå