• 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 : 6 / 6 ÀÌÀü°Ç ÀÌÀü°Ç

ÇѱÛÁ¦¸ñ(Korean Title) Çѱ¹¾î ¹®Àå »ý¼ºÀ» À§ÇÑ Variational Recurrent Auto-Encoder °³¼± ¹× È°¿ë
¿µ¹®Á¦¸ñ(English Title) Application of Improved Variational Recurrent Auto-Encoder for Korean Sentence Generation
ÀúÀÚ(Author) ÇÑ»óö   È«¼®Áø   ÃÖÈñ¿­   Sangchul Hahn   Seokjin Hong   Heeyoul Choi  
¿ø¹®¼ö·Ïó(Citation) VOL 45 NO. 02 PP. 0157 ~ 0164 (2018. 02)
Çѱ۳»¿ë
(Korean Abstract)
µö·¯´×ÀÇ ±Þ¼ÓÇÑ ¹ßÀüÀº ÆÐÅÏÀÎ½Ä ºÐ¾ßÀÇ ¼º´ÉÀ» Çõ½ÅÇßÀ¸¸ç ¸î¸î ¹®Á¦¿¡¼­´Â Àΰ£ ¼öÁØÀ» ³Ñ¾î¼­´Â °á°úµéÀ» º¸¿©ÁÖ°í ÀÖ´Ù. µ¥ÀÌŸ¸¦ ºÐ·ùÇÏ´Â ÆÐÅÏÀνİú ´Þ¸® º» ³í¹®¿¡¼­´Â ÁÖ¾îÁø ¸î°³ÀÇ Çѱ¹¾î ¹®ÀåÀ¸·ÎºÎÅÍ ºñ½ÁÇÑ ¹®ÀåµéÀ» »ý¼ºÇÏ´Â ¹®Á¦¸¦ ´Ù·é´Ù. À̸¦À§ÇØ »ý¼º¸ðµ¨ ÁßÀÇ ÇϳªÀÎ Variational Auto-Encoder ±â¹ÝÀÇ ¸ðµ¨À» Çѱ¹¾î »ý¼º¿¡ ¸Â°Ô °³¼±ÇÏ°í Àû¿ëÇÏ´Â ¹æ¹ýµéÀ» ³íÀÇÇÑ´Ù. ù°, ±³Âø¾îÀÎ Çѱ¹¾îÀÇ Æ¯¼º»ó ¶ç¾î¾²±â¸¦ ±âÁØÀ¸·Î ´Ü¾î »ý¼º½Ã ´Ü¾îÀÇ °³¼ö°¡ ³Ê¹« ¸¹¾Æ À̸¦ ÁÙÀ̱â À§ÇØ Á¶»ç ¹× ¾î¹ÌµéÀ» ºÐ¸®ÇÒ ÇÊ¿ä°¡ ÀÖ´Ù. µÑ°, Çѱ¹¾î´Â ¾î¼øÀÌ ºñ±³Àû ÀÚÀ¯·Ó°í ÁÖ¾î ¸ñÀû¾î µîÀÌ »ý·«µÇ´Â °æ¿ì°¡ ¸¹¾Æ ±âÁ¸ÀÇ ´Ü¹æÇâ ÀÎÄÚ´õ¸¦ ¾ç¹æÇâÀ¸·Î È®ÀåÇÑ´Ù. ¸¶Áö¸·À¸·Î, ÁÖ¾îÁø ¹®ÀåµéÀ» ±â¹ÝÀ¸·Î ºñ½ÁÇÏÁö¸¸ »õ·Î¿î ¹®ÀåµéÀ» »ý¼ºÇϱâ À§ÇØ ±âÁ¸ ¹®ÀåµéÀÇ ÀÎÄÚµùµÈ º¤ÅÍÇ¥Çöµé·ÎºÎÅÍ »õ·Î¿î º¤Å͸¦ ã¾Æ³»°í, ÀÌ º¤Å͸¦ µðÄÚµùÇÏ¿© ¹®ÀåÀ» »ý¼ºÇÑ´Ù. ½ÇÇè °á°ú¸¦ ÅëÇØ Á¦¾ÈÇÑ ¹æ¹ýÀÇ ¼º´ÉÀ» È®ÀÎÇÑ´Ù.
¿µ¹®³»¿ë
(English Abstract)
Due to the revolutionary advances in deep learning, performance of pattern recognition has increased significantly in many applications like speech recognition and image recognition, and some systems outperform human-level intelligence in specific domains. Unlike pattern recognition, in this paper, we focus on generating Korean sentences based on a few Korean sentences. We apply variational recurrent auto-encoder (VRAE) and modify the model considering some characteristics of Korean sentences. To reduce the number of words in the model, we apply a word spacing model. Also, there are many Korean sentences which have the same meaning but different word order, even without subjects or objects; therefore we change the unidirectional encoder of VRAE into a bidirectional encoder. In addition, we apply an interpolation method on the encoded vectors from the given sentences, so that we can generate new sentences which are similar to the given sentences. In experiments, we confirm that our proposed method generates better sentences which are semantically more similar to the given sentences.
Å°¿öµå(Keyword) µö·¯´×   »ý¼º¸ðµ¨   º¯ºÐ¼øȯ¿ÀÅäÀÎÄÚ´õ   Çѱ¹¾î ¹®Àå »ý¼º   º¸°£¹ý   deep learning   generative models   variational recurrent auto-encoder   Korean sentence generation   interpolation  
ÆÄÀÏ÷ºÎ PDF ´Ù¿î·Îµå