• 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) Explanation segments ±â¹Ý ¼³¸í °¡´ÉÇÑ Áö½Ä ¿Ï¼º ¸ðµ¨
¿µ¹®Á¦¸ñ(English Title) An Explainable Knowledge Completion Model Using Explanation Segments
ÀúÀÚ(Author) À̹ÎÈ£   ÀÌ¿Ï°ï   ¹ÙÆ®¼¿·½   ¹Ú¿µÅà  Min-Ho Lee   Wan-Gon Lee   Batselem Jagvaral   Young-Tack Park  
¿ø¹®¼ö·Ïó(Citation) VOL 48 NO. 06 PP. 0680 ~ 0687 (2021. 06)
Çѱ۳»¿ë
(Korean Abstract)
ÃÖ±Ù µö·¯´×À» È°¿ëÇÏ¿© ºÒ¿ÏÀüÇÑ Áö½Ä ±×·¡ÇÁ¸¦ ´ë»óÀ¸·Î »õ·Î¿î ¸µÅ©¸¦ ¿¹ÃøÇÏ´Â ¿¬±¸°¡ ¸¹ÀÌ ÁøÇàµÇ°í ÀÖÁö¸¸, µö·¯´×À» È°¿ëÇÑ ¸µÅ© ¿¹ÃøÀº Ãß·Ð °á°ú¿¡ ´ëÇÑ ¼³¸íÀÌ ºÒ°¡´ÉÇÏ´Ù´Â ÇÑ°èÁ¡ÀÌ ÀÖ´Ù. µû¶ó¼­ º» ³í¹®¿¡¼­´Â ¸µÅ© ¿¹Ãø ÈÄ, Ãß·Ð °á°ú¸¦ µÞ¹ÞħÇÏ´Â Áõ°Å·Î¼­ ¼³¸í °¡´ÉÇÑ Ãß·Ð °æ·Î¸¦ Á¦°øÇÏ¿© Áö½Ä ¿Ï¼ºÀÇ È¿¿ë¼ºÀÌ ³ôÀº ¸ðµ¨À» Á¦¾ÈÇÑ´Ù. À̸¦ À§ÇØ ¿ì¼± Áö½Ä ±×·¡ÇÁÀÇ Á־ ½ÃÀÛÀ¸·Î ¸ñÀû¾î·Î µµ´ÞÇÏ´Â ¶Ç ´Ù¸¥ °æ·Î¸¦ Path Ranking Algorithm È°¿ëÇÏ¿© »ý¼ºÇϸç, À̸¦ explanation segment¶ó Á¤ÀÇÇÏ¿´´Ù. ÀÌ ÈÄ »ý¼ºµÈ explanation segment¸¦ CNN°ú ¾ç¹æÇâ LSTMÀ» °áÇÕÇÑ ¹æ½ÄÀ» Àû¿ëÇÏ¿© ÀÓº£µù ÇÑ´Ù. ¸¶Áö¸·À¸·Î ÀÓº£µù µÈ explanation segmentµé°ú Ãß·ÐÇÒ Èĺ¸ ¼ú¾î¿ÍÀÇ ÀǹÌÀû À¯»ç¼º °è»êÀ» ±â¹ÝÀ¸·Î ÇÑ ¾îÅÙ¼Ç ¸ÞÄ¿´ÏÁòÀ» Àû¿ëÇÏ¿©, ¸µÅ© ¿¹Ãø ¸ðµ¨À» ÇнÀÇÏ¿´´Ù. ¸ðµ¨ ÇнÀ ÈÄ ¸µÅ© ¿¹Ãø ¼³¸í¿¡ ÀûÇÕÇÑ explanation segment¸¦ ¾îÅÙ¼Ç Á¡¼ö¿¡ ±â¹ÝÀ¸·Î ¼±Á¤ÇÏ¿© Á¦°øÇÑ´Ù. Á¦¾ÈÇÏ´Â ¹æ¹ýÀÇ ¼º´ÉÀ» ÃøÁ¤Çϱâ À§ÇØ ¸µÅ© ¿¹Ãø ºñ±³ ½ÇÇè ¹× ¸µÅ© ¿¹Ãø °á°ú¿¡ ´ëÇÑ ¼³¸íÀ¸·Î ÀûÇÕÇÑ explanation segmentÀÇ ºñÀ²À» ÃøÁ¤ÇÏ´Â Á¤È®¼º °ËÁõ ½ÇÇèÀ» ÁøÇàÇÏ¿´´Ù. ½ÇÇè µ¥ÀÌÅÍ´Â º¥Ä¡¸¶Å© µ¥ÀÌÅÍÀÎ NELL-995, FB15K-237, Countries¸¦ ´ë»óÀ¸·Î ÁøÇàÇÏ¿´À¸¸ç, Á¤È®¼º °ËÁõ ½ÇÇè¿¡¼­ Æò±Õ 89%. 44%, 97% Á¤È®¼ºÀ» º¸¿´°í, ±âÁ¸ ¿¬±¸¿Í ºñ±³ÇßÀ» ¶§, NELL-995´Â Æò±Õ 35%p, FB15K-237Àº Æò±Õ 21%p ³ôÀº ¼º´ÉÀ» º¸¿´´Ù.
¿µ¹®³»¿ë
(English Abstract)
Recently, a large number of studies that used deep learning have been conducted to predict new links in incomplete knowledge graphs. However, link prediction using deep learning has a major limitation as the inferred results cannot be explained. We propose a high-utility knowledge graph prediction model that yields explainable inference paths supporting the inference results. We define paths to the object from the knowledge graph using a path ranking algorithm and define them as the explanation segments. Then, the generated explanation segments are embedded using a Convolutional neural network (CNN) and a Bidirectional Long short-term memory (BiLSTM). The link prediction model is then trained by applying an attention mechanism, based on the calculation of the semantic similarity between the embedded explanation segments and inferred candidate predicates to be inferred. The explanation segment suitable for link prediction explanation is selected based on the measured attention scores. To evaluate the performance of the proposed method, a link prediction comparison experiment and an accuracy verification experiment are performed to measure the proportion of the explanation segments suitable to explain the link prediction results. We used the benchmark datasets NELL-995, FB15K-237, and countries for the experiment, and accuracy verification experiments showed the accuracies of 89%, 44%, and 97%, respectively. Compared with the existing method, the NELL-995, FB15K-237 data exhibited 35%p and 21%p higher performance on average.
Å°¿öµå(Keyword) Áö½Ä ±×·¡ÇÁ   ¼³¸í °¡´ÉÇÑ Áö½Ä ¿Ï¼º   ÀÓº£µù   ¾îÅÙ¼Ç ¸ÞÄ¿´ÏÁò   knowledge graph   explainable knowledge completion   embedding   attention mechanism  
ÆÄÀÏ÷ºÎ PDF ´Ù¿î·Îµå