• 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 :

ÇѱÛÁ¦¸ñ(Korean Title) µ¶¼Ò Á¶Ç× ºÐ·ù¸¦ À§ÇÑ µö·¯´× ±â¹Ý ÅؽºÆ® ºÐ·ù ¸ðµ¨
¿µ¹®Á¦¸ñ(English Title) Deep Learning-based Text Classification Model for Poisonous Clauses Classification
ÀúÀÚ(Author) ÃÖ±âÇö   À念Áø   ±èÇмö   ±è°ü¿ì   Gihyeon Choi   Youngjin Jang   Harksoo Kim   Kwanwoo Kim  
¿ø¹®¼ö·Ïó(Citation) VOL 47 NO. 11 PP. 1054 ~ 1060 (2020. 11)
Çѱ۳»¿ë
(Korean Abstract)
¿©·¯ ±â¾÷µéÀº °úÁ¦¸¦ ¼öÇàÇϱ⿡ ¾Õ¼­ °è¾à¼­¸¦ ¹ÙÅÁÀ¸·Î °è¾àÀ» ü°áÇÑ´Ù. ÇÏÁö¸¸ °è¾àÀ» ü°áÇϱâ Àü¿¡ °è¾à¼­ ³»ÀÇ µ¶¼Ò Á¶Ç×À» ¹ß°ßÇÏÁö ¸øÇÏ°í °è¾àÀ» ÁøÇàÇÏ°Ô µÉ °æ¿ì ¿©·¯ ¹®Á¦°¡ ¹ß»ýÇÒ ¼ö ÀÖ´Ù. À̸¦ ¹æÁöÇϱâ À§ÇÏ¿© Àü¹®°¡¸¦ ÅëÇØ °è¾à¼­¸¦ °ËÅäÇÏ´Â °úÁ¤ÀÌ ¼öÇàµÇÁö¸¸ ¸¹Àº ½Ã°£°ú ºñ¿ëÀ» ¿ä±¸ÇÑ´Ù. ¸¸¾à °è¾à¼­ÀÇ »çÀü °ËÅ並 ÅëÇØ µ¶¼Ò Á¶Ç×À» ÆǺ° ÇÒ ¼ö ÀÖ´Â ½Ã½ºÅÛÀÌ Á¸ÀçÇÑ´Ù¸é, °è¾à¼­¸¦ °ËÅäÇÏ´Â °úÁ¤¿¡¼­ ¹ß»ýÇÏ´Â ³ôÀº ºñ¿ë°ú ½Ã°£À» Àý¾àÇÒ ¼ö ÀÖ´Ù. µû¶ó¼­ º» ³í¹®¿¡¼­´Â °è¾à¼­ ³»ÀÇ °¢ ´Ü¶ôÀ» ÀÔ·ÂÀ¸·Î ÇÏ¿© µ¶¼Ò Á¶Ç× ¿©ºÎ¸¦ ºÐ·ùÇÏ´Â ÅؽºÆ® ºÐ·ù ¸ðµ¨À» Á¦¾ÈÇÑ´Ù. Á¦¾È ¸ðµ¨ÀÇ ºÐ·ù ¼º´ÉÀ» ³ôÀ̱â À§ÇÏ¿© ´Ü¶ô ³» ¹®Àå°ú ºÐ·ùÇÒ Å¬·¡½º »çÀÌÀÇ À¯»çµµ Á¤º¸¸¦ ¹ÙÅÁÀ¸·Î ¹®Àå º° Áß¿äµµ¸¦ °è»êÇÏ°í À̸¦ °¢ ¹®Àå¿¡ ¹Ý¿µÇÏ¿© ºÐ·ù¸¦ ¼öÇàÇÑ´Ù. Á¦¾È ¸ðµ¨Àº ½ÇÁ¦ °è¾à¼­ µ¥ÀÌÅ͸¦ »ç¿ëÇÑ ½ÇÇè¿¡¼­ F1 Á¡¼ö 84.51%pÀÇ ¼º´ÉÀ» º¸¿´À¸¸ç ±âÁ¸ ÅؽºÆ® ºÐ·ù ¸ðµ¨°úÀÇ ¼º´É ºñ±³¸¦ À§ÇØ WOS-5736 µ¥ÀÌÅͼÂÀ» ÀÌ¿ëÇÑ ½ÇÇè¿¡¼­ F1 Á¡¼ö 93.64%p·Î °¡Àå ³ôÀº ¼º´ÉÀ» º¸¿´´Ù.
¿µ¹®³»¿ë
(English Abstract)
Most companies sign contracts based on the contract prior to executing the task. However, several problems can occur if the poisonous clauses are not identified before the contract is concluded. To prevent this problem, companies have an expert review the contract, but the service requires much time and money. If there is a system in which the poisonous clauses can be identified through prior review of the contract, the high cost and time incurred in reviewing the contract can be mitigated. Thus, this paper proposes a text classification model that identifies any poisonous clause in the contract by inputing each paragraph in the contract. To improve the classification performance of the proposed model, the importance of each sentence is calculated based on the relationship information between the sentence in the paragraph and the class to be classified, and classification is performed by reflecting it in each sentence. The proposed model showed the performance of the F1 score 84.51%p in experiments using actual contract data and the highest performance with the F1 score 93.64%p in experiments using the WOS-5736 dataset for the performance comparison with the existing text classification models.
Å°¿öµå(Keyword) ÅؽºÆ® ºÐ·ù   ALBERT   Ŭ·¡½º ÀÓº£µù °èÃþ   °ÔÀÌÆ® °èÃþ   text classification   ALBERT   class embedding layer  
ÆÄÀÏ÷ºÎ PDF ´Ù¿î·Îµå