• 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) ºÐ·ù ¿ì¼±¼øÀ§ Àû¿ë°ú Èĺ¸Á¤ ±ÔÄ¢À» ÀÌ¿ëÇÑ È¿°úÀûÀÎ Çѱ¹¾î È­Çà ºÐ·ù
¿µ¹®Á¦¸ñ(English Title) Effective Korean Speech-act Classification Using the Classification Priority Application and a Post-correction Rules
ÀúÀÚ(Author) ¼Û³²ÈÆ   ¹è°æ¸¸   °í¿µÁß   Namhoon Song   Kyoungman Bae   Youngjoong Ko  
¿ø¹®¼ö·Ïó(Citation) VOL 43 NO. 01 PP. 0080 ~ 0086 (2016. 01)
Çѱ۳»¿ë
(Korean Abstract)
È­ÇàÀ̶õ ¹ßÈ­ ¼Ó¿¡ Æ÷ÇԵǾî ÀÖ´Â È­ÀÚ¿¡ ÀÇÇØ ÀǵµµÈ ¾ð¾îÀû ÇàÀ§ÀÌ´Ù. ´ëÈ­ ½Ã½ºÅÛ¿¡¼­ ÀÔ·ÂµÈ ¹ßÈ­¿¡ ÀûÇÕÇÑ È­ÇàÀ» ºÐ·ùÇÏ´Â °ÍÀº Áß¿äÇÏ´Ù. ±âÁ¸ÀÇ È­ÇàºÐ·ù¿¡ °üÇÑ ¿¬±¸´Â ±ÔÄ¢±â¹Ý°ú ±â°èÇнÀ±â¹ÝÀÇ ¹æ¹ýÀ» ¸¹ÀÌ »ç¿ëÇÑ´Ù. º» ³í¹®¿¡¼­´Â ´ëÇ¥ÀûÀÎ ±â°èÇнÀ ¹æ¹ýÀÎ ÁöÁöº¤Åͱâ°è(SVM)¿Í º¯È¯±â¹Ý ÇнÀ(TBL)À» Á¶ÇÕÇÑ È­Çà ºÐ·ù ¹æ¹ýÀ» Á¦¾ÈÇÑ´Ù. À̸¦ À§ÇØ, È­Çະ ÇнÀ ¹ßÈ­ÀÇ ¼ö¿¡ ±â¹ÝÇÏ¿© ºÐ·ù ¿ì¼±¼øÀ§¸¦ Á¶Á¤ÇÔÀ¸·Î½á ÁöÁöº¤Åͱâ°èÀÇ ºÐ·ù ÆíÇâ ¹®Á¦¸¦ ÇØ°áÇÏ¿´°í, ¿À´äÀÏ È®·üÀÌ ³ôÀº ºÐ·ù °á°ú¿¡ ´ëÇؼ­ º¯È¯ ±â¹Ý ÇнÀÀ» ÅëÇØ »ý¼ºµÈ º¸Á¤ ±ÔÄ¢À» Àû¿ëÇÔÀ¸·Î½á È­ÇàºÐ·ù ¼º´ÉÀ» °³¼±ÇÏ´Â ¹æ¹ýÀ» Á¦¾ÈÇÑ´Ù. º» ³í¹®¿¡¼­ È­Çະ ÇнÀ ¹ßÈ­ ¼öÀÇ Â÷À̸¦ °í·ÁÇÑ ºÐ·ù ¿ì¼±¼øÀ§ º¯È­¿Í Èĺ¸Á¤ ±ÔÄ¢À» ÀÌ¿ëÇÑ È­ÇàºÐ·ù ¹æ¹ýÀ» ½ÇÇèÀ» ÅëÇØ Æò°¡ÇÏ¿´À¸¸ç, ÀÌ´Â ÇнÀ ¹ßÈ­ ¼ö°¡ ³·Àº È­ÇàÀÇ ¿ì¼±¼øÀ§¸¦ °í·ÁÇÏÁö ¾ÊÀº ±âÁ¸ÀÇ È­Çà ºÐ·ùº¸´Ù ¼º´ÉÀÌ Çâ»óµÇ¾ú´Ù.
¿µ¹®³»¿ë
(English Abstract)
A speech-act is a behavior intended by users in an utterance. Speech-act classification is important in a dialogue system. The machine learning and rule-based methods have mainly been used for speech-act classification. In this paper, we propose a speech-act classification method based on the combination of support vector machine (SVM) and transformation-based learning (TBL). The user's utterance is first classified by SVM that is preferentially applied to categories with a low utterance rate in training data. Next, when an utterance has negative scores throughout the whole of the categories, the utterance is applied to the correction phase by rules. The results from our method were higher performance over the baseline system long with error-reduction.
Å°¿öµå(Keyword) ÇÏÀ̺긮µå   È­ÇàºÐ·ù   ÁöÁöº¤Åͱâ°è   º¯È¯±â¹Ý ÇнÀ   ensemble   speech-act classifier   support vector machine   transformation-based learning  
ÆÄÀÏ÷ºÎ PDF ´Ù¿î·Îµå