• 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 : 55 / 377

ÇѱÛÁ¦¸ñ(Korean Title) À§Å°Çǵð¾Æ ±â¹ÝÀÇ È¿°úÀûÀÎ °³Ã¼ ¸µÅ·À» À§ÇÑ NIL °³Ã¼ Àνİú °³Ã¼ ¿¬°á ÁßÀǼº ÇØ¼Ò ¹æ¹ý
¿µ¹®Á¦¸ñ(English Title) A Method to Solve the Entity Linking Ambiguity and NIL Entity Recognition for efficient Entity Linking based on Wikipedia
ÀúÀÚ(Author) ÀÌÈ£°æ   ¾ÈÀçÇö   À±Á¤¹Î   ¹è°æ¸¸   °í¿µÁß   Hokyung Lee   Jaehyun An   Jeongmin Yoon   Kyoungman Bae   Youngjoong Ko  
¿ø¹®¼ö·Ïó(Citation) VOL 44 NO. 08 PP. 0813 ~ 0821 (2017. 08)
Çѱ۳»¿ë
(Korean Abstract)
°³Ã¼ ¸µÅ·Àº ÀÔ·ÂµÈ ÁúÀÇ¿¡ Á¸ÀçÇÏ´Â °³Ã¼¸¦ Ç¥ÇöÇÑ °³Ã¼ Ç¥Çö(entity mention)À» Áö½Äº£À̽º¿¡ Á¸ÀçÇÏ´Â °³Ã¼¿Í ¿¬°áÇÏ¿© Àǹ̸¦ ÆľÇÇÏ´Â ¿¬±¸ÀÌ´Ù. °³Ã¼ ¸µÅ·¿¡ °üÇÑ ¿¬±¸´Â Áö½Ä º£À̽º ±¸Ãà ¹®Á¦, ´ÙÁß Ç¥Çö ¹®Á¦, °³Ã¼ ¿¬°á ÁßÀǼº ¹®Á¦, NIL °³Ã¼ ÀÎ½Ä ¹®Á¦°¡ Á¸ÀçÇÑ´Ù. º» ¿¬±¸¿¡¼­´Â Áö½Ä º£À̽º±¸Ãà ¹®Á¦¿Í ´ÙÁß Ç¥Çö ¹®Á¦¸¦ ÇØ°áÇϱâ À§ÇØ À§Å°Çǵð¾Æ¸¦ ±â¹ÝÀ¸·Î °³Ã¼ À̸§ »çÀüÀ» ±¸ÃàÇÑ´Ù, ¶ÇÇÑ, ¹®¸Æ À¯»çµµ, ÀǹÌÀû °ü·Ã¼º, ´Ü¼­ ´Ü¾î Á¡¼ö, °³Ã¼ Ç¥ÇöÀÇ °³Ã¼¸í ŸÀÔ À¯»çµµ, °³Ã¼ À̸§ ¸ÅĪ Á¡¼ö, °³Ã¼Àα⵵ Á¡¼ö ÀÚÁúµéÀ» ±â¹ÝÀ¸·Î SVM(support vector machine)À» ÇнÀÇÏ¿©, NIL °³Ã¼¸¦ ÀνÄÇÏ´Â ¹®Á¦¿Í °³Ã¼ ¿¬°á ÁßÀǼºÀ» ÇؼÒÇÏ´Â ¹æ¹ýÀ» Á¦¾ÈÇÑ´Ù. ±¸ÃàÇÑ Áö½Ä º£À̽º¸¦ ±â¹ÝÀ¸·Î Á¦¾ÈÇÑ µÎ ¹æ¹ýÀ» ¼øÂ÷ÀûÀ¸·Î Àû¿ëÇÏ¿´À» ¶§ ÁÁÀº °³Ã¼ ¸µÅ· ¼º´ÉÀ» ¾ò¾ú´Ù. °³Ã¼ ¸µÅ· ½Ã½ºÅÛÀÇ ¼º´ÉÀº NIL °³Ã¼ ÀÎ½Ä ¼º´ÉÀÌ 83.66%, ÁßÀǼº ÇØ¼Ò ¼º´ÉÀÌ 90.81%ÀÇ F1 Á¡¼ö¸¦ º¸¿´´Ù.
¿µ¹®³»¿ë
(English Abstract)
Entity Linking find the meaning of an entity mention, which indicate the entity using different expressions, in a user¡¯s query by linking the entity mention and the entity in the knowledge base. This task has four challenges, including the difficult knowledge base construction problem, multiple presentation of the entity mention, ambiguity of entity linking, and NIL entity recognition. In this paper, we first construct the entity name dictionary based on Wikipedia to build a knowledge base and solve the multiple presentation problem. We then propose various methods for NIL entity recognition and solve the ambiguity of entity linking by training the support vector machine based on several features, including the similarity of the context, semantic relevance, clue word score, named entity type similarity of the mansion, entity name matching score, and object popularity score. We sequentially use the proposed two methods based on the constructed knowledge base, to obtain the good performance in the entity linking. In the result of the experiment, our system achieved 83.66% and 90.81% F1 score, which is the performance of the NIL entity recognition to solve the ambiguity of the entity linking.
Å°¿öµå(Keyword) °³Ã¼ ¸µÅ·   NIL °³Ã¼ ÀνĠ  °³Ã¼ ¸µÅ· ÁßÀǼº   À§Å°Çǵð¾Æ   ÁúÀÇ ÀÀ´ä ½Ã½ºÅÛ   entity linking   NIL entity recognition   ambiguity of entity linking   wikipedia   question answering system  
ÆÄÀÏ÷ºÎ PDF ´Ù¿î·Îµå