• 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 : 1 / 2   ´ÙÀ½°Ç ´ÙÀ½°Ç

ÇѱÛÁ¦¸ñ(Korean Title) Convolutional Neural Network¿¡¼­ °øÀ¯ °èÃþÀÇ ºÎºÐ ÇнÀ¿¡ ±â¹Ý ÇÑ È­ÀÚ Àǵµ ºÐ¼®
¿µ¹®Á¦¸ñ(English Title) Speakers¡¯ Intention Analysis Based on Partial Learning of a Shared Layer in a Convolutional Neural Network
ÀúÀÚ(Author) ±è¹Î°æ   ±èÇмö   Minkyoung Kim   Harksoo Kim  
¿ø¹®¼ö·Ïó(Citation) VOL 44 NO. 12 PP. 1252 ~ 1257 (2017. 12)
Çѱ۳»¿ë
(Korean Abstract)
´ëÈ­¿¡¼­ È­ÀÚÀÇ Àǵµ´Â °¨Á¤, È­Çà, ±×¸®°í ¼­¼úÀڷΠǥÇöµÉ ¼ö ÀÖ´Ù. µû¶ó¼­ »ç¿ëÀÚ ÁúÀÇ¿¡ Á¤È®ÇÏ°Ô ÀÀ´äÇϱâ À§Çؼ­ ´ëÈ­ ½Ã½ºÅÛÀº ¹ßÈ­¿¡ ³»Æ÷µÈ °¨Á¤, È­Çà, ±×¸®°í ¼­¼úÀÚ¸¦ ÆľÇÇؾßÇÑ´Ù. ¸¹ÀºÀÌÀü ¿¬±¸µéÀº °¨Á¤, È­Çà, ¼­¼úÀÚ¸¦ µ¶¸³µÈ ºÐ·ù ¹®Á¦·Î ´Ù·ï¿Ô´Ù. ±×·¯³ª ¸î¸î ¿¬±¸¿¡¼­´Â °¨Á¤, È­Çà, ¼­¼úÀÚ°¡ ¼­·Î ¿¬°üµÇ¾î ÀÖÀ½À» º¸¿´´Ù. º» ³í¹®¿¡¼­´Â Convolutional Neural Netowork¸¦ ÀÌ¿ëÇÏ¿© °¨Á¤, È­Çà, ¼­¼úÀÚ¸¦ µ¿½Ã¿¡ ºÐ¼®ÇÏ´Â ÅëÇÕ ¸ðµ¨À» Á¦¾ÈÇÑ´Ù. Á¦¾È ¸ðµ¨Àº ƯÁ¤ Ãß»óÈ­ °èÃþ°ú, °øÀ¯ Ãß»óÈ­ °èÃþÀ¸·Î ±¸¼ºµÈ´Ù. ƯÁ¤ Ãß»óÈ­ °èÃþ¿¡¼­´Â °¨Á¤, È­Çà, ¼­¼úÀÚÀÇ µ¶¸³µÈ Á¤º¸°¡ ÃßÃâµÇ°í °øÀ¯ Ãß»óÈ­ °èÃþ¿¡¼­ µ¶¸³µÈ Á¤º¸µéÀÇ Á¶ÇÕÀÌ Ãß»óÈ­µÈ´Ù. ÇнÀ ½Ã °¨Á¤ÀÇ ¿À·ù, È­ÇàÀÇ ¿À·ù, ¼­¼úÀÚÀÇ ¿À·ù´Â ºÎºÐÀûÀ¸·Î ¿ª ÀüÆÄ µÈ´Ù. Á¦¾ÈÇÑ ÅëÇÕ ¸ðµ¨Àº ½ÇÇè¿¡¼­ µ¶¸³µÈ ¸ðµ¨º¸´Ù ÁÁÀº ¼º´É(°¨Á¤ +2%p, È­Çà +11%p, ¼­¼úÀÚ +3%)À» º¸¿´´Ù.
¿µ¹®³»¿ë
(English Abstract)
In dialogues, speakers¡¯ intentions can be represented by sets of an emotion, a speech act, and a predicator. Therefore, dialogue systems should capture and process these implied characteristics of utterances. Many previous studies have considered such determination as independent classification problems, but others have showed them to be associated with each other. In this paper, we propose an integrated model that simultaneously determines emotions, speech acts, and predicators using a convolution neural network. The proposed model consists of a particular abstraction layer, mutually independent informations of these characteristics are abstracted. In the shared abstraction layer, combinations of the independent information is abstracted. During training, errors of emotions, errors of speech acts, and errors of predicators are partially back-propagated through the layers. In the experiments, the proposed integrated model showed better performances (2%p in emotion determination, 11%p in speech act determination, and 3%p in predicator determination) than independent determination models.
Å°¿öµå(Keyword) °¨Á¤ ºÐ¼®   È­Çà ºÐ¼®   ¼­¼úÀÚ ºÐ¼®   ÅëÇÕ Àǵµ ºÐ¼®   ºÎºÐ ¿ª ÀüÆÄ   °øÀ¯ °èÃþ   integrated intention analysis   partial back-propag   convolution neural network   shared layer  
ÆÄÀÏ÷ºÎ PDF ´Ù¿î·Îµå