• Àüü
  • ÀüÀÚ/Àü±â
  • Åë½Å
  • ÄÄÇ»ÅÍ
´Ý±â

»çÀÌÆ®¸Ê

Loading..

Please wait....

±¹³» ÇÐȸÁö

Ȩ Ȩ > ¿¬±¸¹®Çå > ±¹³» ÇÐȸÁö > µ¥ÀÌÅͺ£À̽º ¿¬±¸È¸Áö(SIGDB)

µ¥ÀÌÅͺ£À̽º ¿¬±¸È¸Áö(SIGDB)

Current Result Document : 10 / 10

ÇѱÛÁ¦¸ñ(Korean Title) ½Ã¸Çƽ ÅÙ¼­°ø°£¸ðµ¨ ±â¹Ý ÅؽºÆ®µ¥ÀÌÅÍ Áõ½Ä±â¹ý
¿µ¹®Á¦¸ñ(English Title) A Text Data Augmentation Technique based on Semantic Tensor Space Model
ÀúÀÚ(Author) ±èÇÑÁØ   Han-Joon Kim   À̱æÀç   Gil-Jae Lee  
¿ø¹®¼ö·Ïó(Citation) VOL 35 NO. 03 PP. 0077 ~ 0086 (2019. 12)
Çѱ۳»¿ë
(Korean Abstract)
µ¥ÀÌÅÍ Áõ½ÄÀº ±âÁ¸ÀÇ µ¥ÀÌÅÍ¿¡¼­ ¾à°£ÀÇ º¯ÇüÀ» °®´Â »õ·Î¿î µ¥ÀÌÅ͸¦ »ý¼ºÇÏ´Â °úÁ¤ÀÌ´Ù. µ¥ÀÌÅÍ Áõ½ÄÀº µ¥ÀÌÅÍÀÇ ´Ù¾ç¼ºÀ» È®º¸ÇÔÀ¸·Î½á ±â°èÇнÀ¿¡¼­ ¸ðµ¨ÀÇ °úÀûÇÕÀ» ¹æÁöÇÏ°í ¼º´ÉÀ» Çâ»ó½ÃÅ°´Â µ¥ µµ¿òÀ» ÁØ´Ù. ÄÄÇ»ÅÍ ºñÀü ºÐ¾ß¿¡¼­ µ¥ÀÌÅÍ Áõ½ÄÀÌ È°¹ßÈ÷ È°¿ëµÇ´Â µ¥ ¹ÝÇØ, ÅؽºÆ®¸¶ÀÌ´× ºÐ¾ß¿¡¼­´Â µ¥ÀÌÅÍ Áõ½ÄÀÇ »ç¿ëÀÌ Á¦ÇÑÀûÀÌ´Ù. ÀÌ´Â ÀÓº£µùÀ» ÇÊ¿ä·Î ÇÏ´Â ÅؽºÆ®µ¥ÀÌÅÍÀÇ Æ¯¼º»ó, Áõ½Ä °úÁ¤¿¡¼­ ¿øº»°ú ÀüÇô ´Ù¸¥ Àǹ̸¦ °®´Â µ¥ÀÌÅÍ°¡ »ý¼ºµÉ À§ÇèÀÌ Àֱ⠶§¹®ÀÌ´Ù. ÀÌ¿¡ º» ³í¹®Àº ½Ã¸Çƽ ÅÙ¼­°ø°£¸ðµ¨À» È°¿ëÇÑ ÅؽºÆ®µ¥ÀÌÅÍ Áõ½Ä±â¹ýÀ» Á¦¾ÈÇÑ´Ù. Á¦¾ÈÇÏ´Â Áõ½Ä±â¹ýÀº ÅؽºÆ®µ¥ÀÌÅÍ°¡ °®´Â Áõ½Ä¹®Á¦¿¡¼­ ÀÚÀ¯·Ó°í, ±âÁ¸ÀÇ Áõ½Ä±â¹ýµé°ú ´Þ¸® °£´ÜÇÑ ¿¬»ê¸¸À» È°¿ëÇϱ⠶§¹®¿¡ °£ÆíÇÏ°Ô ¼öÇàÇÒ ¼ö ÀÖ´Â ÀåÁ¡ÀÌ ÀÖ´Ù. º» ³í¹®Àº ¹®¼­ºÐ·ù ½ÇÇèÀ» ÅëÇØ Á¦¾ÈÇÑ Áõ½Ä±â¹ýÀ¸·Î »ý¼ºÇÑ µ¥ÀÌÅ͵éÀÌ ¸ðµ¨ÀÇ ¼º´ÉÇâ»óÀ» À̲ø¾î³¿À» º¸ÀÓÀ¸·Î½á Á¦¾È±â¹ýÀÇ À¯È¿¼ºÀ» °ËÁõÇÑ´Ù.
¿µ¹®³»¿ë
(English Abstract)
Data augmentation is the process of generating new data with little variation to existing data. Data augmentation helps to prevent model's overfitting and improve performance in machine learning by ensuring data diversity. While data augmentation is actively used in computer vision, the use of data augmentation is limited in text mining. This is because, due to the nature of text data requiring embedding, there is a risk that data having a completely different meaning from the original is generated during the augmentation process. In this paper, we propose a text data augmentation technique based on semantic tensor space model. The proposed augmentation technique does not cause the augmentation problem of text data, and unlike the existing augmentation techniques, it can be easily performed because it uses only simple operations. This paper verifies the validity of the proposed augmentation technique by showing that the data generated by the proposed technique leads to the performance improvement of the model.
Å°¿öµå(Keyword) µ¥ÀÌÅÍ Áõ½Ä   ÅؽºÆ®µ¥ÀÌÅÍ   ½Ã¸Çƽ ÅÙ¼­°ø°£¸ðµ¨   ±â°èÇнÀ. ÇнÀµ¥ÀÌÅÍ   Data Augmentation   Text Data   Training Data   Semantic Tensor Space Model   Machine Learning  
ÆÄÀÏ÷ºÎ PDF ´Ù¿î·Îµå