Àüü
ÀüÀÚ/Àü±â
Åë½Å
ÄÄÇ»ÅÍ
·Î±×ÀÎ
ȸ¿ø°¡ÀÔ
About Us
ÀÌ¿ë¾È³»
¿¬±¸¹®Çå
±¹³» ³í¹®Áö
¿µ¹® ³í¹®Áö
±¹³» ÇÐȸÁö
Çмú´ëȸ ÇÁ·Î½Ãµù
±¹³» ÇÐÀ§ ³í¹®
³í¹®Á¤º¸
¹é¼
±³À°Á¤º¸
¿¬±¸ ù°ÉÀ½
ÇаúÁ¤º¸
°ÀÇÁ¤º¸
µ¿¿µ»óÁ¤º¸
E-Learning
¿Â¶óÀÎ Àú³Î
½ÉÈÁ¤º¸
¿¬±¸ ¹× ±â¼úµ¿Çâ
Áֿ俬±¸ÅäÇÈ
ÁÖ¿ä°úÁ¦ ¹× ±â°ü
Çؿܱâ°ü °ü·ÃÀÚ·á
¹ÙÀÌ¿À Á¤º¸±â¼ú
ÁÖ¿ä Archive Site
Æ÷Ä¿½ºiN
¿¬±¸ÀÚ Á¤º¸
¶óÀÌ¡½ºÅ¸
ÆÄ¿öiNÅͺä
¼¼ÁßÇÑ
¿¬±¸ÀÚ·á
¹®ÀÚ DB
¿ë¾î»çÀü
¾Ë¸²¸¶´ç
ºÎ½Ç ÇмúÈ°µ¿ ¿¹¹æ
³í¹®¸ðÁý
´ëȸ¾È³»
What's New
¿¬±¸ºñÁ¤º¸
±¸ÀÎÁ¤º¸
°øÁö»çÇ×
CSERIC ±¤Àå
Post-Conference
¿¬±¸ÀÚ Ä«Æä
ÀÚÀ¯°Ô½ÃÆÇ
Q&A
´Ý±â
»çÀÌÆ®¸Ê
¿¬±¸¹®Çå
±¹³» ³í¹®Áö
¿µ¹® ³í¹®Áö
±¹³» ÇÐȸÁö
Çмú´ëȸ ÇÁ·Î½Ãµù
±¹³» ÇÐÀ§ ³í¹®
³í¹®Á¤º¸
¹é¼
±³À°Á¤º¸
¿¬±¸ ù°ÉÀ½
ÇаúÁ¤º¸
°ÀÇÁ¤º¸
µ¿¿µ»óÁ¤º¸
E-Learning
¿Â¶óÀÎ Àú³Î
½ÉÈÁ¤º¸
¿¬±¸ ¹× ±â¼úµ¿Çâ
Áֿ俬±¸ÅäÇÈ
ÁÖ¿ä°úÁ¦ ¹× ±â°ü
Çؿܱâ°ü °ü·ÃÀÚ·á
¹ÙÀÌ¿À Á¤º¸±â¼ú
ÁÖ¿ä Archive Site
ÄÄÇ»ÅÍiN
¿¬±¸ÀÚ Á¤º¸
¿¬±¸ÀÚ·á
¹®ÀÚ DB
Ȧ·Î±×·¥ DB
¿ë¾î»çÀü
¾Ë¸²¸¶´ç
ºÎ½Ç ÇмúÈ°µ¿ ¿¹¹æ
³í¹®¸ðÁý
´ëȸ¾È³»
What's New
¿¬±¸ºñ Á¤º¸
±¸ÀÎÁ¤º¸
°øÁö»çÇ×
IT Daily
CSERIC ±¤Àå
Post-Conference
¿¬±¸ÀÚ Ä«Æä
ÀÚÀ¯°Ô½ÃÆÇ
Q&A
¼ºñ½º ¹Ù·Î°¡±â
¼³¹®Á¶»ç
¿¬±¸À±¸®
°ü·Ã±â°ü
Please wait....
¿¬±¸¹®Çå
±¹³» ³í¹®Áö
¿µ¹® ³í¹®Áö
±¹³» ÇÐȸÁö
Çмú´ëȸ ÇÁ·Î½Ãµù
±¹³» ÇÐÀ§ ³í¹®
³í¹®Á¤º¸
¹é¼
±¹³» ³í¹®Áö
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)
ÅؽºÆ® ¹Ù²ã ¾²±â °úÁ¦¸¦ À§ÇÑ ºÐ·ù ¸ðµ¨ ±â¹ÝÀÇ ¼Õ½Ç ÇÔ¼ö ¼³°è¿Í Æò°¡
¿µ¹®Á¦¸ñ(English Title)
Design and Evaluation of Loss Functions based on Classification Models
ÀúÀÚ(Author)
±è°æÈÆ
¹ÚÁø¿í
ÀÌÁöÀº
¹Ú»óÇö
Kyeonghun Kim
Jinuk Park
Jieun Lee
Sanghyun Park
ÀüÇö±Ô
Á¤À±°æ
Hyun-Kyu Jeon
Yun-Gyung Cheong
¿ø¹®¼ö·Ïó(Citation)
VOL 48 NO. 10 PP. 1132 ~ 1141 (2021. 10)
Çѱ۳»¿ë
(Korean Abstract)
¹Ù²ã ¾²±â(paraphrase generation)´Â ÀÔ·Â ¹®Àå¿¡ ´ëÇÏ¿© Àǹ̴ °°Áö¸¸, ´Ü¾î³ª Åë»ç ±¸Á¶¿Í °°Àº Ç¥ÇöÀÌ ´Ù¸¥ ¹®ÀåÀ» »ý¼ºÇÏ´Â °úÁ¦ÀÌ´Ù. ÃÖ±Ù À̸¦ ±¸ÇöÇϱâ À§ÇØ Àΰø ½Å°æ¸Á ±â¹ÝÀÇ ¸ðµ¨ÀÌ ³Î¸® »ç¿ëµÇ¸ç, ÇнÀ ¹æ¹ýÀ¸·Î¼ Áöµµ ÇнÀÀÌ ÁÖ·Î »ç¿ëµÈ´Ù. ±×·¯³ª »ý¼ºµÈ ¹®Àå°ú ·¹ÀÌºí ¹®Àå °£ÀÇ Â÷À̸¦ ÁÙÀÌ´Â Áöµµ ÇнÀ ¹æ¹ýÀº ¸ðµ¨¿¡ Á¦ÇÑµÈ ÀÇ¹Ì Á¤º¸¸¸À» Á¦°øÇÑ´Ù. µû¶ó¼ º» ³í¹®¿¡¼´Â ºÐ·ù °úÁ¦¸¦ ÇнÀÇÑ º°µµÀÇ ¸ðµ¨À» È°¿ëÇÏ¿©, ¹Ù²ã ¾²±â ¸ðµ¨ ÇнÀ ½Ã ÀÇ¹Ì Á¤º¸¸¦ ÃßÃâÇÏ°í À̸¦ È°¿ëÇÏ´Â ¹æ¹ýÀ» Á¦¾ÈÇÏ°í ½ÇÇèÇÏ¿´À¸¸ç, ±× °á°ú ±âÁ¸ ¹æ¹ý°ú ºñ±³ÇÏ¿© ´õ ÁÁÀº ¼º´ÉÀ» º¸¿´´Ù.
¿µ¹®³»¿ë
(English Abstract)
Paraphrase generation is a task in which the model generates an output sentence conveying the same meaning as the given input text but with a different representation. Recently, paraphrase generation has been widely used for solving the task of using artificial neural networks with supervised learning between the model¡¯s prediction and labels. However, this method gives limited information because it only detects the representational difference. For that reason, we propose a method to extract semantic information with classification models and use them for the training loss function. Our evaluations showed that the proposed method outperformed baseline models.
Å°¿öµå(Keyword)
ÀÚ¿¬¾î ó¸®
¸ÖƼ ¸ð´Þ
°¨¼º ºÐ¼®
°¨Á¤ ŽÁö
´ÜÀÏ ÀÔÃâ·Â Æ®·£½ºÆ÷¸Ó
BERT
natural language processing
multimodal
sentiment analysis
emotion detection
singlestream transformer
BERT
¹Ù²ã ¾²±â
ºÐ·ù ¸ðµ¨
¸ðµ¨±â¹Ý ÇнÀ
¼Õ½Ç ÇÔ¼ö
paraphrase generation
classification model
model-based learning
loss function
ÆÄÀÏ÷ºÎ
PDF ´Ù¿î·Îµå
¸ñ·Ï
Copyright(c)
Computer Science Engineering Research Information Center
. All rights reserved.