• 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 : 4 / 13 ÀÌÀü°Ç ÀÌÀü°Ç   ´ÙÀ½°Ç ´ÙÀ½°Ç

ÇѱÛÁ¦¸ñ(Korean Title) ºÎºÐ ÀÓº£µù ±â¹ÝÀÇ Áö½Ä ¿Ï¼º ±â¹ý
¿µ¹®Á¦¸ñ(English Title) Partial Embedding Approach for Knowledge Completion
ÀúÀÚ(Author) ÀÌ¿Ï°ï   ¹ÙÆ®¼¿·½   È«ÁöÈÆ   ÃÖÇö¿µ   ¹Ú¿µÅà  Wan-Gon Lee   Batselem Jagvaral   Ji-Hun Hong   Hyun-Young Choi   Young-Tack Park  
¿ø¹®¼ö·Ïó(Citation) VOL 45 NO. 11 PP. 1168 ~ 1175 (2018. 11)
Çѱ۳»¿ë
(Korean Abstract)
Áö½Ä ±×·¡ÇÁ´Â ½Ç¼¼°èÀÇ °³Ã¼µé°ú °³Ã¼ »çÀÌÀÇ °ü°è·Î ±¸¼ºµÈ ³×Æ®¿öÅ©¸¦ ÀǹÌÇϸç, ÃÖ±Ù¿¡´Â ´ë¿ë·® µ¥ÀÌÅ͸¦ ±â¹ÝÀ¸·Î ±¸ÃàµÇ°í ÀÖ´Ù. ´ëºÎºÐÀÇ Áö½Ä ±×·¡ÇÁµéÀº ´©¶ôµÈ ¿£Æ¼Æ¼ ¶Ç´Â °ü°èµé·Î ÀÎÇØ ºÒ¿ÏÀü¼º¿¡ ´ëÇÑ ¹®Á¦Á¡ÀÌ Á¸ÀçÇÑ´Ù. À̸¦ ÇØ°áÇϱâ À§ÇØ Áö³­ ¿¬±¸µéÀº Áö½Ä ±×·¡ÇÁ¸¦ ´ÙÂ÷¿ø °ø°£»ó¿¡ ÀÓº£µùÇÏ´Â ¹æ¹ýÀ» Àû¿ëÇß´Ù. ±×·¯³ª ÀÌ·¯ÇÑ ¿¬±¸µéÀº Áö½Ä ±×·¡ÇÁ°¡ º¯È­ÇÏÁö ¾Ê´Â´Ù´Â °¡Á¤À» ÇÏ°í ÀÖ´Ù. ÀÌ·Î ÀÎÇØ »õ·Î¿î Æ®¸®ÇÃÀÌ Ãß°¡µÇ¾î ºü¸£°Ô ÁøÈ­ÇÏ´Â ½Ç¼¼°èÀÇ Áö½Ä ±×·¡ÇÁ¿¡ Àû¿ëÇϱâ À§ÇØ ¹Ýº¹ÀûÀÎ ÀÓº£µù ¸ðµ¨ÀÇ ÀçÇнÀÀº °íºñ¿ëÀÇ ¿¬»êÀÌ ¿ä±¸µÇ¸ç, ½Ç¿ëÀûÀÌÁö ¸øÇÏ´Ù. µû¶ó¼­ º» ³í¹®¿¡¼­´Â º¯È­ÇÏ´Â Áö½Ä ±×·¡ÇÁ¸¦ ´ë»óÀ¸·Î ÇÏ´Â ºÎºÐ ÀÓº£µù ±â¹ÝÀÇ Áö½Ä ¿Ï¼º ¹æ¹ýÀ» Á¦¾ÈÇÑ´Ù. Áö½Ä ¿Ï¼ºÀÇ ´ë»óÀÌ µÇ´Â °ü½É °ü°èµéÀ» ÃßÃâÇϱâ À§ÇØ ¿ÂÅç·ÎÁöÀÇ °ø¸®¿Í ¹®¸Æ Á¤º¸¸¦ È°¿ëÇßÀ¸¸ç, À̸¦ ±â¹ÝÀ¸·Î ¿£Æ¼Æ¼¿Í °ü°èµéÀ» ÀÓº£µùÇÏ°í ÇнÀÇÏ¿© Áö½Ä ¿Ï¼ºÀ» ¼öÇàÇß´Ù. Á¦¾ÈÇÏ´Â ¹æ¹ýÀÇ ¼º´ÉÀ» ÃøÁ¤Çϱâ À§ÇØ Freebase¿Í WiseKB µ¥ÀÌÅͼÂÀ» ´ë»óÀ¸·Î ÃֽŠÁö½Ä ¿Ï¼º ¿¬±¸µé°úÀÇ ºñ±³ ½ÇÇèÀ» ÁøÇàÇÏ¿´°í, Æò±ÕÀûÀ¸·Î ÇнÀ½Ã°£ÀÌ ¾à 49%¡­90% °¨¼ÒÇßÀ¸¸ç, ÀüüÀûÀÎ ¼º´ÉÀÌ ¾à 6.7% Áõ°¡ÇÏ´Â °ÍÀ» È®ÀÎÇß´Ù.
¿µ¹®³»¿ë
(English Abstract)
Knowledge graphs are large networks that describe real world entities and their relationships with triples. Most of the knowledge graphs are far from being complete, and many previous studies have addressed this problem using low dimensional graph embeddings. Such methods assume that knowledge graphs are fixed and do not change. However, real-world knowledge graphs evolve at a rapid pace with the addition of new triples.Repeated retraining of embedding models for the entire graph is computationally expensive and impractical. In this paper, we propose a partial embedding method for partial completion of evolving knowledge graphs. Our method employs ontological axioms and contextual information to extract relations of interest and builds entity and relation embedding models based on instances of such relations. Our experiments demonstrated that the proposed partial embedding method can produce comparable results on knowledge graph completion with state-of-the-art methods while significantly reducing the computation time of entity and relation embeddings by 49%–90% for the Freebase and WiseKB datasets.
Å°¿öµå(Keyword) Áö½Ä ±×·¡ÇÁ   Áö½Ä ¿Ï¼º   ÀÓº£µù   µö·¯´×   knowledge graph   knowledge completion   embedding   deep learning  
ÆÄÀÏ÷ºÎ PDF ´Ù¿î·Îµå