• 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 : 3 / 20 ÀÌÀü°Ç ÀÌÀü°Ç   ´ÙÀ½°Ç ´ÙÀ½°Ç

ÇѱÛÁ¦¸ñ(Korean Title) RNNÀ» ÀÌ¿ëÇÑ µ¿ÀÛ±â·Ï ¸¶ÀÌ´× ±â¹ÝÀÇ Ãßõ ¹æ¹ý
¿µ¹®Á¦¸ñ(English Title) A Code Recommendation Method Using RNN Based on Interaction History
ÀúÀÚ(Author) Á¶ÈñÅ   À̼±¾Æ   °­¼º¿ø   Heetae Cho   Seonah Lee   Sungwon Kang  
¿ø¹®¼ö·Ïó(Citation) VOL 07 NO. 12 PP. 0461 ~ 0468 (2018. 12)
Çѱ۳»¿ë
(Korean Abstract)
°³¹ßÀÚµéÀº ¼ÒÇÁÆ®¿þ¾î °³¹ß°ú À¯Áöº¸¼ö ÀÛ¾÷ Áß ÇϳªÀÇ Äڵ带 ¼öÁ¤Çϴµ¥ µéÀÌ´Â ½Ã°£º¸´Ù À̸¦ À§ÇØ Äڵ带 Ž»öÇÏ°í ÀÌÇØÇϴµ¥ ´õ ¸¹Àº ½Ã°£À» ¼Ò¸ðÇÑ´Ù. Äڵ带 Ž»öÇÏ´Â ½Ã°£À» ÁÙÀ̱â À§ÇÏ¿© ±âÁ¸ ¿¬±¸µéÀº µ¥ÀÌÅÍ ¸¶ÀÌ´×°ú Åë°èÀû ¾ð¾î¸ðµ¨ ±â¹ýÀ» ÀÌ¿ëÇÏ¿© ¼öÁ¤ÇÒ Äڵ带 ÃßõÇÏ¿© ¿Ô´Ù. ±×·¯³ª ÀÌ °æ¿ì ¸ðµ¨ÀÇ ÇнÀ µ¥ÀÌÅÍ¿Í ÀԷµǴ µ¥ÀÌÅÍ°¡ Á¤È®ÇÏ°Ô ÀÏÄ¡ÇÏÁö ¾ÊÀ¸¸é ÃßõÀÌ ¹ß»ýÇÏÁö ¾Ê´Â´Ù. ÀÌ ³í¹®¿¡¼­ ¿ì¸®´Â µö·¯´×ÀÇ ±â¹ý Áß ÇϳªÀÎ Recurrent Neural Networks¿¡ µ¿ÀÛ±â·ÏÀ» ÇнÀ½ÃÄÑ ±âÁ¸ ¿¬±¸ÀÇ »ó±â ¹®Á¦Á¡ ¾øÀÌ ¼öÁ¤ÇÒ ÄÚµåÀÇ À§Ä¡¸¦ Ãßõ ÇÏ´Â ¹æ¹ýÀ» Á¦¾ÈÇÑ´Ù. Á¦¾È ¹æ¹ýÀº RNN°ú µ¿ÀÛ±â·ÏÀ» È°¿ëÇÑ Ãßõ ±â¹ýÀ¸·Î Æò±Õ ¾à 91%ÀÇ Á¤È®µµ¿Í 71%ÀÇ ÀçÇöÀ²À» ´Þ¼ºÇÔÀ¸·Î½á ±âÁ¸ÀÇ Ãßõ¹æ¹ýº¸´Ù ÄÚµå Ž»ö ½Ã°£À» ´õ¿í ÁÙÀÏ ¼ö ÀÖ°Ô ÇØ ÁØ´Ù.
¿µ¹®³»¿ë
(English Abstract)
Developers spend a significant amount of time exploring and trying to understand source code to find a source location to modify. To reduce such time, existing studies have recommended the source location using statistical language model techniques. However, in these techniques, the recommendation does not occur if input data does not exactly match with learned data. In this paper, we propose a code location recommendation method using Recurrent Neural Networks and interaction histories, which does not have the above problem of the existing techniques. Our method achieved an average precision of 91% and an average recall of 71%, thereby reducing time for searching and exploring code more than the existing recommendation techniques.
Å°¿öµå(Keyword) ¼ÒÇÁÆ®¿þ¾î °øÇР  µö·¯´×   µ¿ÀÛ±â·Ï   Software Engineering   Deep Learning   Interaction History  
ÆÄÀÏ÷ºÎ PDF ´Ù¿î·Îµå