• 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) ´ÙÁß ±â°èÇнÀ ¹æ¹ýÀ» ÀÌ¿ëÇÑ Çѱ¹¾î Ä¿¹Â´ÏƼ ±â¹Ý ÁúÀÇ-ÀÀ´ä ½Ã½ºÅÛ
¿µ¹®Á¦¸ñ(English Title) A Korean Community-based Question Answering System Using Multiple Machine Learning Methods
ÀúÀÚ(Author) ±Ç¼øÀç   ±èÁÖ¾Ö   °­»ó¿ì   ¼­Á¤¿¬   Sunjae Kwon   Juae Kim   Sangwoo Kang   Jungyun Seo  
¿ø¹®¼ö·Ïó(Citation) VOL 43 NO. 10 PP. 1085 ~ 1093 (2016. 10)
Çѱ۳»¿ë
(Korean Abstract)
Ä¿¹Â´ÏƼ ±â¹Ý ÁúÀÇ ÀÀ´ä ½Ã½ºÅÛÀº »ç¿ëÀÚ ÁúÀÇ¿¡ ´ëÇÑ Á¤´äÀ» ÀÎÅÍ³Ý Ä¿¹Â´ÏƼ¿¡ »ç¿ëÀÚµéÀÌ
°Ô½ÃÇß´ø ¹®¼­ Áß¿¡¼­ ¼±ÅÃÇÏ¿© Á¦°øÇÏ´Â ½Ã½ºÅÛÀÌ´Ù. ±âÁ¸ ¹æ¹ýµéÀº ÁúÀÇ ºÐ¼®ÀÇ ¼º´É Çâ»óÀ» À§ÇÏ¿© ¸ñÀû ¿µ¿ª¿¡ ÀûÇÕÇÑ ±ÔÄ¢À» ±¸ÃàÇϰųª ÀϺΠó¸® °úÁ¤¿¡ ±â°è ÇнÀÀ» Àû¿ëÇÏ¿´´Ù. ÇÏÁö¸¸ ±âÁ¸ ¹æ¹ýµéÀº Àû¿ë ¿µ¿ªÀ» È®ÀåÇϰųª ¼öÁ¤ÇÏ´Â °æ¿ì ¸¹Àº ºñ¿ëÀÌ ¼Ò¿äµÇ¸ç °æ¿ì¿¡ µû¶ó¼­´Â ½Ã½ºÅÛÀÌ Æ¯Á¤ ¿µ¿ª¿¡ °úÀûÇյǴ °æ¿ì°¡ ¹ß»ýÇÑ´Ù. º» ³í¹®¿¡¼­´Â Ä¿¹Â´ÏƼ ±â¹Ý ÁúÀÇ-ÀÀ´ä ½Ã½ºÅÛÀÇ È¿°úÀûÀΠ󸮸¦ À§Çؼ­ ½Ã½ºÅÛÀÇ °¢ °úÁ¤¿¡ ÀûÇÕÇÑ ±â°è ÇнÀ ¹æ¹ýÀ» Àû¿ëÇÏ¿© Àüü °úÁ¤À» ÀÚµ¿È­ÇÏ´Â ´ÙÁß ±â°èÇнÀ ¹æ¹ýÀ» Á¦¾ÈÇÑ´Ù. Á¦¾È ½Ã½ºÅÛÀº »ç¿ëÀÚ ÁúÀǸ¦ ºÐ¼®ÇÏ´Â ºÎºÐ°ú Á¤´ä ¹®¼­¸¦ ¼±ÅÃÇÏ´Â ºÎºÐÀ¸·Î ³ª´­ ¼ö ÀÖ´Ù. ÁúÀÇ ºÐ¼® °úÁ¤Àº ÁúÀÇÀÇ ÃÊÁ¡ ±¸¹®À» ºÐ¼®ÇÏ´Â ÁúÀÇ ÇٽɺΠÃßÃâ±â¿Í ÁúÀÇÀÇ ÁÖÁ¦¸¦ ºÐ·ùÇÏ´Â ÁúÀÇ À¯Çü ºÐ·ù±â·Î ±¸¼ºÇÏ¿´À¸¸ç, ÀüÀÚ´Â Á¶°ÇºÎ ¹«ÀÛÀ§ÀåÀ» »ç¿ëÇÏ°í ÈÄÀÚ´Â ÁöÁö º¤ÅÍ ±â°è¸¦ »ç¿ëÇÑ´Ù. Á¤´ä ¹®¼­ ¼±Åÿ¡¼­´Â À¯»çµµ ÃøÁ¤¿¡¼­ »ç¿ëÇÏ´Â °¡ÁßÄ¡¸¦ Àΰø ½Å°æ¸ÁÀ¸·Î ÇнÀÇÑ´Ù. ¶ÇÇÑ ÀÎÅͳݿ¡ Ä¿¹Â´ÏƼ¿¡ °Ô½ÃµÈ µ¥ÀÌÅÍ´Â ÇüÅÂ¼Ò ºÐ¼® °á°ú¸¦ ½Å·ÚÇÒ ¼ö ¾ø´Â °æ¿ì°¡ ¸¹ÀÌ ¹ß»ýÇÑ´Ù. µû¶ó¼­ À½Àý ÀÚÁúÀ» »ç¿ëÇÏ¿© ÁúÀǸ¦ ºÐ¼® ´Ü°è¿¡¼­ ÇüÅÂ¼Ò ºÐ¼®ÀÇ ¿µÇâÀ» ÃÖ¼ÒÈ­ÇÏ´Â ¹æ¹ýÀ» Á¦¾ÈÇÑ´Ù. Á¦¾ÈÇÏ´Â ½Ã½ºÅÛÀº Mean Average Precision ±âÁØÀ¸·Î 0.765, R-Precision ±âÁØÀ¸·Î 0.872ÀÇ ¼º´ÉÀ» º¸¿© ±âÁ¸ ½Ã½ºÅÛº¸´Ù ¼º´ÉÀÌ ¿ì¼öÇÏ´Ù.
¿µ¹®³»¿ë
(English Abstract)
Community-based Question Answering system is a system which provides answers for each question from the documents uploaded on web communities. In order to enhance the capacity of question analysis, former methods have developed specific rules suitable for a target region or have applied machine learning to partial processes. However, these methods incur an excessive cost for expanding fields or lead to cases in which system is overfitted for a specific field. This paper proposes
a multiple machine learning method which automates the overall process by adapting appropriate machine learning in each procedure for efficient processing of community-based Question Answering system. This system can be divided into question analysis part and answer selection part. The question analysis part consists of the question focus extractor, which analyzes the focused phrases in questions and uses conditional random fields, and the question type classifier, which classifies topics of questions and uses support vector machine. In the answer selection part, the we trains weights that are used by the similarity estimation models through an artificial neural network. Also these are a number of cases in which the results of morphological analysis are not reliable for the data uploaded on web communities. Therefore, we suggest a method that minimizes the impact of morphological analysis by using character features in the stage of question analysis. The proposed system outperforms the former system by showing a Mean Average Precision criteria of 0.765 and R-Precision criteria of 0.872.
Å°¿öµå(Keyword) community-based question answering   related document retrieval   model ensemble   document type classification   focus construction analysis   natural language processing   Ä¿¹Â´ÏƼ ±â¹Ý ÁúÀÇ-ÀÀ´ä ½Ã½ºÅÛ   °ü·Ã ¹®¼­ °Ë»ö   ¸ðµ¨ ¾Ó»óºí   ¹®¼­ À¯Çü ºÐ·ù   ÃÊÁ¡ ±¸¹® ºÐ¼®   ÀÚ¿¬¾î󸮠 
ÆÄÀÏ÷ºÎ PDF ´Ù¿î·Îµå