Á¤º¸°úÇÐȸ³í¹®Áö (Journal of KIISE)
Current Result Document :
ÇѱÛÁ¦¸ñ(Korean Title) |
À§Å°¹é°ú·ÎºÎÅÍ ±â°èÇнÀ ±â¹Ý Çѱ¹¾î Áö½Äº£À̽º ±¸Ãà |
¿µ¹®Á¦¸ñ(English Title) |
Construction of Korean Knowledge Base Based on Machine Learning from Wikipedia |
ÀúÀÚ(Author) |
Á¤¼®¿ø
ÃָͽÄ
±èÇмö
Seok-won Jeong
Maengsik Choi
Harksoo Kim
|
¿ø¹®¼ö·Ïó(Citation) |
VOL 42 NO. 08 PP. 1065 ~ 1070 (2015. 08) |
Çѱ۳»¿ë (Korean Abstract) |
Áö½Äº£À̽º´Â ÀÚ¿¬¾î ó¸® ±â¹ÝÀÇ ´Ù¾çÇÑ ÀÀ¿ë ½Ã½ºÅÛ ¼º´É¿¡ ¿µÇâÀ» ¹ÌÄ¡´Â Áß¿äÇÑ ¿ä¼ÒÀÌ´Ù. ¿µ¾î±Ç¿¡¼´Â WordNet, YAGO, BabeINet°ú °°Àº ½ÃÁ÷º£À̽ºµéÀÌ ³Î¸® »ç¿ëµÇ°í ÀÖ´Ù. º» ³í¹®¿¡¼´Â À§Å°¹é°ú¿Í YAGO·ÎºÎÅÍ YAGO Çü½ÄÀÇ Çѱ¹¾î Áö½Äº£À̽º(ÀÌÇÏ K-YAHO)¸¦ ÀÚµ¿ ±¸ÃàÇÏ´Â ¹æ¹ýÀ» Á¦¾ÈÇÑ´Ù. Á¦¾È ½Ã½ºÅÛÀº YAGO¿Í À§Å°¹é°ú ÀÎÆ÷¹Ú½º°£ÀÇ °£´ÜÇÑ ¸ÅĪÀ» ÅëÇØ Ãʱâ K-YAHO¸¦ ±¸ÃàÇÑ µÚ, ±â°èÇнÀÀ» ÀÌ¿ëÇÏ¿© Ãʱâ K-YAHO¸¦ È®ÀåÇÑ´Ù. ½ÇÇè °á°ú, Á¦¾È ½Ã½ºÅÛÀº Ãʱâ K-YAHO ±¸Ãà ½ÇÇè¿¡¼ 0.9642ÀÇ ½Å·Úµµ¸¦ º¸¿´°í, K-YAHO È®Àå ½ÇÇè¿¡¼ 0.9468ÀÇ Á¤È®µµ¿Í 0.7596ÀÇ ¸ÞÅ©·Î F1 ôµµ¸¦ º¸¿´´Ù.
|
¿µ¹®³»¿ë (English Abstract) |
The performance of many natural language processing applications depends on the knowledge base as a major resource. WordNet, YAGO, Cyc, and BabelNet have been extensively used as knowledge bases in English. In this paper, we propose a method to construct a YAGO-style knowledge base automatically for Korean (hereafter, K-YAGO) from Wikipedia and YAGO. The proposed system constructs an initial K-YAGO simply by matching YAGO to info-boxes in Wikipedia. Then, the initial K-YAGO is expanded through the use of a machine learning technique. Experiments with the initial K-YAGO shows that the proposed system has a precision of 0.9642. In the experiments with the expanded part of K-YAGO, an accuracy of 0.9468 was achieved with an average macro F1-measure of 0.7596.
|
Å°¿öµå(Keyword) |
K-YAHO
Áö½Äº£À̽º ±¸Ãà
¾ð¾î°£ ¸ÅĪ
±â°èÇнÀ
K-YAGO
Knowledge base construction
Interlanguage matching
Machine learning
|
ÆÄÀÏ÷ºÎ |
PDF ´Ù¿î·Îµå
|