• 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¸°úÇÐȸ ³í¹®Áö B : ¼ÒÇÁÆ®¿þ¾î ¹× ÀÀ¿ë

Á¤º¸°úÇÐȸ ³í¹®Áö B : ¼ÒÇÁÆ®¿þ¾î ¹× ÀÀ¿ë

Current Result Document : 17 / 17

ÇѱÛÁ¦¸ñ(Korean Title) Æò¸éÀû ¾îÈÖ ÀÚÁúµéÀ» È°¿ëÇÑ È®Àå È¥ÇÕ Ä¿³Î ±â¹Ý °ü°è ÃßÃâ
¿µ¹®Á¦¸ñ(English Title) Relation Extraction based on Extended Composite Kernel using Flat Lexical Features
ÀúÀÚ(Author) ÃÖ¼ºÇÊ   Á¤Ã¢ÈÄ   ÃÖÀ±¼ö   ¸Í¼ºÇö   Sung-Pil Choi   Chang-Hoo Jeong   Yun-Soo Choi   Sung-Hyon Myaeng  
¿ø¹®¼ö·Ïó(Citation) VOL 36 NO. 08 PP. 0642 ~ 0652 (2009. 08)
Çѱ۳»¿ë
(Korean Abstract)
º» ³í¹®¿¡¼­´Â ±âÁ¸ÀÇ °ü°è ÃßÃâ ¼º´ÉÀ» Çâ»ó½ÃÅ°±â À§Çؼ­ ±âÁ¸ÀÇ ÀÚÁú ±â¹Ý ¹æ¹ý¿¡¼­ Ãß±¸ÇÏ¿´´ø °³Ã¼ ÁÖº¯ ¹®¸Æ ´Ù¾ç¼º Á¤º¸ÀÇ ÃßÃâ ¹× Àû¿ë°ú Ä¿³Î ±â¹Ý ¹æ¹ýÀÇ °­Á¡ÀÎ °ü°è ÀνºÅϽº¿¡ ´ëÇÑ ±¸¹® ±¸Á¶Àû ÀÚÁú Á¤º¸ÀÇ ÅëÇÕ È°¿ëÀ» ÅëÇÑ È®ÀåµÈ È¥ÇÕ Ä¿³ÎÀ» Á¦¾ÈÇÑ´Ù. ACE RDC ÄÚÆÛ½º1)¸¦ È°¿ëÇÑ ½ÇÇè¿¡¼­, ±âÁ¸ÀÇ ÇÕ¼º°ö ±¸¹® Æ®¸® Ä¿³Î ±â¹Ý È¥ÇÕ Ä¿³ÎÀ» ±â¹ÝÀ¸·Î ÃÑ 9 Á¾·ùÀÇ Æò¸éÀû ¾îÈÖ ÀÚÁú ÁýÇÕÀ» Á¤ÀÇÇÏ°í À̸¦ Àû¿ëÇÔÀ¸·Î½á ¼º´É Çâ»ó¿¡ ±â¿©ÇÏ´Â ¾îÈÖ ÀÚÁú À¯ÇüÀ» ÆľÇÇÒ ¼ö ÀÖ¾úÀ¸¸ç, ÀûÀº ±Ô¸ðÀÇ ÇнÀ ÁýÇÕÀ¸·Îµµ ÇöÀç ÃÖ°í ¼öÁØÀÇ ¼º´É¿¡ ÇÊÀûÇÏ´Â °á°ú¸¦ ¾òÀ» ¼ö ÀÖ¾ú´Ù. °á·ÐÀûÀ¸·Î °ü°è ÃßÃâÀ» À§ÇÑ ¼¼ °¡Áö ÇÙ½É Á¤º¸, Áï °³Ã¼ ÀÚÁú, ±¸¹® ±¸Á¶Àû ÀÚÁú, ÁÖº¯ ¹®¸Æ ¾îÈÖ ÀÚÁúÀ» ÅëÇÕ Àû¿ëÇÏ¸é °ü°è ÃßÃâÀÇ ¼º´ÉÀ» Çâ»ó½Ãų ¼ö ÀÖÀ½À» ¾Ë ¼ö ÀÖ¾ú´Ù.
¿µ¹®³»¿ë
(English Abstract)
In order to improve the performance of the existing relation extraction approaches, we propose a method for combining two pivotal concepts which play an important role in classifying semantic relationships between entities in text. Having built a composite kernel-based relation extraction system, which incorporates both entity features and syntactic structured information of relation instances, we define nine classes of lexical features and synthetically apply them to the system. Evaluation on the ACE RDC corpus shows that our approach boosts the effectiveness of the existing composite kernels in relation extraction. It also confirms that by integrating the three important features (entity features, syntactic structures and contextual lexical features), we can improve the performance of a relation extraction process.
Å°¿öµå(Keyword) Á¤º¸ ÃßÃâ   °ü°è ÃßÃâ   ±â°è ÇнÀ   ÁöÁöº¤Åͱâ°è   È¥ÇÕ Ä¿³Î   ÇÕ¼º°ö ±¸¹® Æ®¸® Ä¿³Î   Æò¸éÀû ¾îÈÖ ÀÚÁú   Information Extraction   Relation Extraction   Machine Learning   Support Vector Machines   Composite Kernels   Convolution Parse Tree Kernels   Flat Lexical Features  
ÆÄÀÏ÷ºÎ PDF ´Ù¿î·Îµå