Á¤º¸°úÇÐȸ³í¹®Áö (Journal of KIISE)
ÇѱÛÁ¦¸ñ(Korean Title) |
¿µÀÛ¹® ÀÚµ¿Ã¤Á¡ ½Ã½ºÅÛ °³¹ß¿¡¼ ÇнÀµ¥ÀÌÅÍ ºÎÁ· ¹®Á¦ ÇØ°áÀ» À§ÇÑ ¾Ó»óºí ±â¹ý Àû¿ëÀÇ È¿°ú |
¿µ¹®Á¦¸ñ(English Title) |
Effect of Application of Ensemble Method on Machine Learning with Insufficient Training Set in Developing Automated English Essay Scoring System |
ÀúÀÚ(Author) |
ÀÌ°æÈ£
ÀÌ°øÁÖ
Gyoung Ho Lee
Kong Joo Lee
|
¿ø¹®¼ö·Ïó(Citation) |
VOL 42 NO. 09 PP. 1124 ~ 1132 (2015. 09) |
Çѱ۳»¿ë (Korean Abstract) |
ÀϹÝÀûÀ¸·Î, ±³»ç ÇнÀ ¾Ë°í¸®ÁòÀÌ ÀûÀýÈ÷ ÇнÀµÇ±â À§Çؼ´Â ·¹À̺íÀÇ ÆíÇâÀÌ ¾ø´Â ÃæºÐÇÑ ¾çÀÇ ÇнÀµ¥ÀÌÅÍ°¡ ÇÊ¿äÇÏ´Ù. ±×·¯³ª ¿µÀÛ¹® ÀÚµ¿Ã¤Á¡ ½Ã½ºÅÛ °³¹ßÀ» À§ÇÑ ÃæºÐÇÏ°í ÆíÇâµÇÁö ¾ÊÀº ÇнÀµ¥ÀÌÅ͸¦ ¼öÁýÇÏ´Â °ÍÀº ¾î·Á¿î ÀÏÀÌ´Ù. ¶ÇÇÑ ¿µ¾î ÀÛ¹® Æò°¡ÀÇ °æ¿ì, ÀüüÀûÀÎ ´ä¾È ¼öÁØ¿¡ ´ëÇÑ ´Ù¸éÀûÀÎ Æò°¡°¡ ÀÌ·ç¾îÁø´Ù. Àû°í ÆíÇâµÇ±â ½¬¿î ÇнÀµ¥ÀÌÅÍ¿Í À̸¦ ÀÌ¿ëÇÑ ¿©·¯ Æò°¡¿µ¿ª¿¡ ´ëÇÑ ÇнÀ¸ðµ¨À» »ý¼ºÇؾßÇϱ⠶§¹®¿¡, À̸¦ À§ÇÑ ÀûÀýÇÑ ±â°èÇнÀ ¾Ë°í¸®ÁòÀ» °áÁ¤Çϱ⠾î·Æ´Ù. º» ³í¹®¿¡¼´Â ÀÌ·¯ÇÑ ¹®Á¦¸¦ ¾Ó»óºíÇнÀÀ» ÅëÇØ ¿ÏÈÇÒ ¼ö ÀÖÀ½À» ½ÇÇè¿¡ ÅëÇØ º¸ÀÌ°íÀÚ ÇÑ´Ù. ½ÇÁ¦ Áß, °íµîÇб³ ÇлýµéÀ» ´ë»óÀ¸·Î ½ÃÇàµÈ ´Ü¹®Çü ¿µÀÛ¹® äÁ¡ °á°ú¸¦ ÇнÀµ¥ÀÌÅÍ °³¼ö¿Í ÆíÇ⼺À» Á¶ÀýÇÏ¿© ½ÇÇèÇÏ¿´´Ù. ÇнÀµ¥ÀÌÅÍÀÇ °³¼ö º¯È¿Í ÆíÇ⼺ º¯ÈÀÇ ½ÇÇè °á°ú, ¿¡À̴ٺνºÆ® ¾Ë°í¸®ÁòÀ» Àû¿ëÇÑ °á°ú¸¦ ÅõÇ¥·Î °áÇÕÇÑ ¾Ó»óºí ±â¹ýÀÌ ´Ù¸¥ ¾Ë°í¸®Áòµé º¸´Ù Àü¹ÝÀûÀ¸·Î ´õ ³ªÀº ¼º´ÉÀ» ³ªÅ¸³¿À» ½ÇÇèÀ» ÅëÇØ ³ªÅ¸³»¾ú´Ù.
|
¿µ¹®³»¿ë (English Abstract) |
In order to train a supervised machine learning algorithm, it is necessary to have non-biased labels and a sufficient amount of training data. However, it is difficult to collect the required non-biased labels and a sufficient amount of training data to develop an automatic English Composition scoring system. In addition, an English writing assessment is carried out using a multi-faceted evaluation of the overall level of the answer. Therefore, it is difficult to choose an appropriate machine learning algorithm for such work. In this paper, we show that it is possible to alleviate these problems through ensemble learning. The results of the experiment indicate that the ensemble technique exhibited an overall performance that was better than that of other algorithms.
|
Å°¿öµå(Keyword) |
ÀÚµ¿Ã¤Á¡
¾Ó»óºí
¿¡À̴ٺνºÆ®
ÅõÇ¥
automatic writing assessment
ensemble
AdaBoost
voting
|
ÆÄÀÏ÷ºÎ |
PDF ´Ù¿î·Îµå
|