• 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¸Ã³¸®ÇÐȸ ³í¹®Áö > Á¤º¸Ã³¸®ÇÐȸ ³í¹®Áö ¼ÒÇÁÆ®¿þ¾î ¹× µ¥ÀÌÅÍ °øÇÐ

Á¤º¸Ã³¸®ÇÐȸ ³í¹®Áö ¼ÒÇÁÆ®¿þ¾î ¹× µ¥ÀÌÅÍ °øÇÐ

Current Result Document :

ÇѱÛÁ¦¸ñ(Korean Title) »ý¼ºÀû Àû´ë ³×Æ®¿öÅ©·Î ÀÚµ¿ »ý¼ºÇÑ °¨¼º ÅؽºÆ®ÀÇ ¼º´É Æò°¡
¿µ¹®Á¦¸ñ(English Title) Evaluation of Sentimental Texts Automatically Generated by a Generative Adversarial Network
ÀúÀÚ(Author) ¹Úõ¿ë   ÃÖ¿ë¼®   ÀÌ°øÁÖ   Cheon-Young Park   Yong-Seok Choi   Kong Joo Lee  
¿ø¹®¼ö·Ïó(Citation) VOL 08 NO. 06 PP. 0257 ~ 0264 (2019. 06)
Çѱ۳»¿ë
(Korean Abstract)
ÃÖ±Ù ÀÚ¿¬¾ð¾îó¸® ºÐ¾ß¿¡¼­ µö·¯´× ¸ðµ¨ÀÌ ÁÁÀº ¼º°ú¸¦ º¸ÀÌ°í ÀÖ´Ù. ÀÌ·¯ÇÑ µö·¯´× ¸ðµ¨ÀÇ ¼º´ÉÀ» Çâ»ó½ÃÅ°±â À§Çؼ­´Â ¸¹Àº ¾çÀÇ µ¥ÀÌÅÍ°¡ ÇÊ¿äÇÏ´Ù. ÇÏÁö¸¸ ¸¹Àº ¾çÀÇ µ¥ÀÌÅ͸¦ ¸ðÀ¸±â À§Çؼ­´Â ¸¹Àº Àη°ú ½Ã°£ÀÌ ¼Ò¿äµÇ±â ¶§¹®¿¡ µ¥ÀÌÅÍ È®ÀåÀ» ÅëÇØ ÀÌ¿Í °°Àº ¹®Á¦¸¦ ÇؼÒÇÒ ¼ö ÀÖ´Ù. ±×·¯³ª ¹®Àå µ¥ÀÌÅÍÀÇ °æ¿ì À̹ÌÁö µ¥ÀÌÅÍ¿¡ ºñÇØ µ¥ÀÌÅÍ º¯ÇüÀÌ ¾î·Æ±â ¶§¹®¿¡ ´Ù¾çÇÑ ¹®ÀåÀ» »ý¼ºÇÒ ¼ö ÀÖ´Â »ý¼º ¸ðµ¨À» ÅëÇØ ¹®Àå µ¥ÀÌÅÍ ÀÚµ¿ È®ÀåÀ» Çغ¸°íÀÚ ÇÑ´Ù. º» ¿¬±¸¿¡¼­´Â ÃÖ±Ù À̹ÌÁö »ý¼º ¸ðµ¨¿¡¼­ ÁÁÀº ¼º´ÉÀ» º¸ÀÌ°í ÀÖ´Â »ý¼ºÀû Àû´ë ½Å°æ¸Á Áß ÇϳªÀÎ CS-GANÀ» »ç¿ëÇÏ¿© ÇнÀ µ¥ÀÌÅͷκÎÅÍ »õ·Î¿î ¹®ÀåµéÀ» »ý¼ºÇØ º¸°í À¯¿ë¼ºÀ» ´Ù¾çÇÑ ÁöÇ¥·Î Æò°¡ÇÏ¿´´Ù. Æò°¡ °á°ú CS-GANÀÌ ±âÁ¸ÀÇ ¾ð¾î ¸ðµ¨À» »ç¿ë ÇÒ ¶§º¸´Ù ´Ù¾çÇÑ ¹®ÀåÀ» »ý¼ºÇÒ ¼ö ÀÖ¾ú°í »ý¼ºµÈ ¹®ÀåÀ» °¨¼º ºÐ·ù±â¿¡ ÇнÀ½ÃÄ×À» ¶§ °¨¼º ºÐ·ù±âÀÇ ¼º´ÉÀÌ Çâ»óµÊÀ» º¸¿´´Ù.
¿µ¹®³»¿ë
(English Abstract)
Recently, deep neural network based approaches have shown a good performance for various fields of natural language processing. A huge amount of training data is essential for building a deep neural network model. However, collecting a large size of training data is a costly and time-consuming job. A data augmentation is one of the solutions to this problem. The data augmentation of text data is more difficult than that of image data because texts consist of tokens with discrete values. Generative adversarial networks (GANs) are widely used for image generation. In this work, we generate sentimental texts by using one of the GANs, CS-GAN model that has a discriminator as well as a classifier. We evaluate the usefulness of generated sentimental texts according to various measurements. CS-GAN model not only can generate texts with more diversity but also can improve the performance of its classifier.
Å°¿öµå(Keyword) »ý¼ºÀû Àû´ë ½Å°æ¸Á   µ¥ÀÌÅÍ È®Àå   °¨¼º ÅؽºÆ®   °¨¼º ºÐ·ù±â   Generative Adversarial Network (GAN)   Data Augmentation   Sentimental Text   Sentiment Classifier  
ÆÄÀÏ÷ºÎ PDF ´Ù¿î·Îµå