• 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) ÁúÀǹ®°ú Áö½Ä ±×·¡ÇÁ °ü°è ÇнÀÀ» ÅëÇÑ Áö½Ä ¿Ï¼º ½Ã½ºÅÛ
¿µ¹®Á¦¸ñ(English Title) Knowledge Completion System through Learning the Relationship between Query and Knowledge Graph
ÀúÀÚ(Author) ÀÌ´Ù¿µ   Á¶È¯±Ô   Da-Young Lee   Hwan-Gue Cho   ±è¹Î¼º   À̹ÎÈ£   ÀÌ¿Ï°ï   ¹Ú¿µÅà  Min-Sung Kim   Min-Ho Lee   Wan-Gon Lee   Young-Tack Park  
¿ø¹®¼ö·Ïó(Citation) VOL 48 NO. 06 PP. 0649 ~ 0656 (2021. 06)
Çѱ۳»¿ë
(Korean Abstract)
Áö½Ä ±×·¡ÇÁ´Â °³Ã¼µé »çÀÌÀÇ °ü°è·Î ±¸¼ºµÈ ³×Æ®¿öÅ©¸¦ ¶æÇÑ´Ù. ÀÌ·¯ÇÑ Áö½Ä ±×·¡ÇÁ¿¡¼­ ƯÁ¤ °³Ã¼µé¿¡ ´ëÇÑ °ü°è°¡ ´©¶ôµÇ°Å³ª À߸øµÈ °ü°è ¿¬°á°ú °°Àº ¹®Á¦·Î ºÒ¿ÏÀüÇÑ Áö½Ä ±×·¡ÇÁÀÇ ¹®Á¦Á¡ÀÌ Á¸ÀçÇÑ´Ù. ºÒ¿ÏÀüÇÑ Áö½Ä ±×·¡ÇÁÀÇ ¹®Á¦¸¦ ÇØ°áÇϱâ À§ÇÑ ¸¹Àº ¿¬±¸´Â ÀÚ¿¬¾î ÀÓº£µù ±â¹ÝÀ¸·Î Àΰø ½Å°æ¸ÁÀ» ÀÌ¿ëÇÑ ÇнÀ ¹æ¹ýµéÀ» Á¦¾ÈÇß´Ù. ÀÌ·¯ÇÑ ¹æ¹ýµé·Î ´Ù¾çÇÑ Áö½Ä ±×·¡ÇÁ ¿Ï¼º ½Ã½ºÅÛµéÀÌ ¿¬±¸µÇ°í Àִµ¥ º» ³í¹®¿¡¼­´Â ƯÁ¤ ÁúÀÇ¿Í Áö½Ä ±×·¡ÇÁ¸¦ È°¿ëÇØ ´©¶ôµÈ Áö½ÄÀ» Ãß·ÐÇÏ´Â ½Ã½ºÅÛÀ» Á¦¾ÈÇÏ¿´´Ù. ¸ÕÀú Àǹ®ÇüÀÇ Query·ÎºÎÅÍ topicÀ» ÀÚµ¿À¸·Î ÃßÃâÇÏ¿© ÇØ´ç topic ÀÓº£µùÀ» Áö½Ä ±×·¡ÇÁ ÀÓº£µù ¸ðµâ·ÎºÎÅÍ ¾ò´Â´Ù. ±× ´ÙÀ½ Query ÀÓº£µù°ú Áö½Ä ±×·¡ÇÁ ÀÓº£µùÀ» È°¿ëÇÏ¿© Áö½Ä ±×·¡ÇÁ·ÎºÎÅÍÀÇ topic°ú ÁúÀǹ® »çÀÌÀÇ °ü°è¸¦ ÇнÀÇÏ¿© »õ·Î¿î Æ®¸®ÇÃÀ» Ãß·ÐÇÑ´Ù. ÀÌ¿Í °°Àº ¹æ½ÄÀ» ÅëÇØ ´©¶ôµÈ Áö½ÄµéÀ» Ãß·ÐÇÏ°í ÁÁÀº ¼º´ÉÀ» À§ÇØ Æ¯Á¤ ÁúÀÇ¿Í °ü·ÃµÈ Áö½Ä ±×·¡ÇÁÀÇ ¼ú¾îºÎ ÀÓº£µùÀ» °°ÀÌ È°¿ëÇÏ¿´°í ±âÁ¸ ¹æ¹ýº¸´Ù ´õ ÁÁÀº ¼º´ÉÀ» º¸ÀÓÀ» Áõ¸íÇϱâ À§ÇØ MetaQA µ¥ÀÌÅͼÂÀ» »ç¿ëÇÏ¿© ½ÇÇèÀ» ÁøÇàÇÏ¿´´Ù. Áö½Ä ±×·¡ÇÁ´Â ¿µÈ­¸¦ µµ¸ÞÀÎÀ¸·Î °®´Â Áö½Ä ±×·¡ÇÁ¸¦ »ç¿ëÇÏ¿´´Ù. ½ÇÇè °á°ú·Î Áö½Ä ±×·¡ÇÁ Àüü¿Í ´©¶ôµÈ Áö½Ä ±×·¡ÇÁ¸¦ °¡Á¤ÇÏ¿© Æ®¸®ÇõéÀ» ÀÓÀÇ·Î 50% ´©¶ô½ÃŲ Áö½Ä ±×·¡ÇÁ¿¡¼­ ½ÇÇèÇÏ¿© ±âÁ¸ ¹æ¹ýº¸´Ù ´õ ÁÁÀº ¼º´ÉÀ» ¾ò¾ú´Ù.
¿µ¹®³»¿ë
(English Abstract)
The knowledge graph is a network comprising of relationships between the entities. In a knowledge graph, there exists a problem of missing or incorrect relationship connection with the specific entities. Numerous studies have proposed learning methods using artificial neural networks based on natural language embedding to solve the problems of the incomplete knowledge graph. Various knowledge graph completion systems are being studied using these methods. In this paper, a system that infers missing knowledge using specific queries and knowledge graphs is proposed. First, a topic is automatically extracted from a query, and topic embedding is obtained from the knowledge graph embedding module. Next, a new triple is inferred by learning the relationship between the topic from the knowledge graph and the query by using Query embedding and knowledge graph embedding. Through this method, the missing knowledge was inferred and the predicate embedding of the knowledge graph related to a specific query was used for good performance. Also, an experiment was conducted using the MetaQA dataset to prove the better performance of the proposed method compared with the existing methods. For the experiment, we used a knowledge graph having movies as a domain. Based on the assumption of the entire knowledge graph and the missing knowledge graph, we experimented on the knowledge graph in which 50% of the triples were randomly omitted. Apparently, better performance than the existing method was obtained.
Å°¿öµå(Keyword) äÆà ¸Þ½ÃÁö   Å©·Î½º-ÅؽºÆà  ³ôÀÓ¸» Ç¥Çö   ¹®Àå ¿Ï¼ºµµ   ¹®Àå º¤ÅÍ   chat message   cross-texting   honorifics   sentence completeness   sentence vector   Áö½Ä ¿Ï¼º   Áö½Ä ±×·¡ÇÁ   µö·¯´×   ÀΰøÁö´É   ÀÓº£µù   Äõ¸®   Æ®¸®Çà  knowledge completion   knowledge graph   deep learni   artificial intelligence   embedding   query   triple  
ÆÄÀÏ÷ºÎ PDF ´Ù¿î·Îµå