• 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) ´ëÈ­ ¼Ó Áú¹® À¯»ç¼º ºÐ¼®À» À§ÇÑ ¹®Àå ÀÓº£µù ÀÚÁúÀÇ ÀÚµ¿ ÃßÃâ ¹æ¹ý
¿µ¹®Á¦¸ñ(English Title) Automatic Extraction of Sentence Embedding Features for Question Similarity Analysis in Dialogues
ÀúÀÚ(Author) ¿À±³Áß   À̵¿°Ç   ÀÓä±Õ   ÃÖÈ£Áø   Kyo-Joong Oh   Dongkun Lee   Chae-Gyun Lim   Ho-Jin Choi  
¿ø¹®¼ö·Ïó(Citation) VOL 46 NO. 09 PP. 0909 ~ 0918 (2019. 09)
Çѱ۳»¿ë
(Korean Abstract)
º» ³í¹®Àº ÀÚ¿¬¾î ¹®ÀåÀÇ À¯»ç¼ºÀ» ºÐ¼®ÇÒ ¼ö ÀÖ´Â ¹®Àå ÀÓº£µù ÀÚÁúÀÇ ÀÚµ¿ ÃßÃâ ¹æ¹ý¿¡ °üÇØ ±â¼úÇÑ´Ù. Áú¹® À¯»ç¼º ºÐ¼®À̶õ ÁúÀÇ ¹®ÀåÀ» ÀÌÇØÇϱâ À§ÇÏ¿© ÀÚ¿¬¾î ÁúÀÇ ¹®ÀåÀÇ ÀǹÌÀû ±¸Á¶Àû À¯»ç¼ºÀ» ºÐ¼®ÇÏ´Â ¿¬±¸¸¦ ¸»Çϸç, À̸¦ ÀÌ¿ëÇÏ¿© ÁúÀÇÀÀ´ä (Q&A) ¹× ´ëÈ­ ½Ã½ºÅÛ¿¡¼­ ÀÔ·Â Áú¹®¿¡ ´ëÇѴ亯À» ã´Âµ¥ È°¿ëÇÒ ¼ö ÀÖ´Ù. º» ³í¹®¿¡¼­ ±â¼úÇÏ´Â ¹®ÀåÀÇ À¯»ç¼ºÀ» ºÐ¼®ÇÏ´Â ¹æ¹ýÀº µö·¯´× ¸ðµ¨À» ÅëÇØ ÃßÃâµÈ ¹®Àå ÀÓº£µù º¤Å͸¦ ÀÚÁú·Î ÀÌ¿ëÇÑ´Ù. À½Àý°ú ½ÇÁú ÇüÅÂ¼Ò¿Í °°Àº ¹®Àå ³» Ç¥ÇöÀÇ ¼øÂ÷Àû Á¤º¸¸¦ ¹Ý¿µÇϱâ À§ÇØ ¼øȯ ½Å°æ¸Á(Recurrent Neural Network)À» ÀÌ¿ëÇÏ¿© »ý¼ºÇÑ ¹®Àå º¤ÅÍ¿Í ¾î¼ø°ú °ü°è¾øÀÌ À¯»çÇÑ Ç¥ÇöÀÇ µîÀå ÆÐÅÏÀ» Ư¡À¸·Î Àâ±â À§ÇÑ º¹À⠽Űæ¸Á (CNN)À» ÀÌ¿ëÇÏ¿© »ý¼ºÇÑ ¹®Àå º¤Å͸¦ »ç¿ëÇÑ´Ù. º» ³í¹®¿¡¼­´Â ÀºÇà ¼­ºñ½º¿Í °ü·ÃµÈ ´ëÈ­ ¹®Àå¿¡¼­ ÀÚµ¿ ÃßÃâµÈ ¹®Àå ÀÓº£µù ÀÚÁúÀ» ÀÌ¿ëÇÏ¿© ¹®Àå °£ À¯»ç¼º ºÐ¼®ÇßÀ» ¶§ÀÇ Á¤È®¼º°ú Ç°ÁúÀ» Æò°¡ÇÑ´Ù.
¿µ¹®³»¿ë
(English Abstract)
This paper describes a method for the automatic extraction of feature vectors that can be used to analyze the similarity among natural language sentences. Similarity analysis among sentences is a necessary aspect of measuring semantic or structural similarity in natural language understanding. The analysis results can be used to find answers in Question and Answer (Q&A) systems and dialogue systems. The similarity analysis uses sentence vectors extracted by two deep learning models: the Recurrent Neural Network (RNN) to reflect sequential information of expressions such as syllables and semantic morphemes, and the Convolutional Neural Network (CNN) for characterizing the appearance patterns of similar expressions such as words or phrases. In this paper, we examine the accuracy and quality of the method using sentence vectors that are automatically extracted by the models from dialogues related to banking service. This method can find more similar questions and answers in FAQs than existing methods. The automatic feature extraction method can be used to analyze the similarity of Korean sentences across various application domains and systems.
Å°¿öµå(Keyword) ÀÚ¿¬¾î ÀÌÇØ   ¹®Àå ÀÓº£µù   ÀÚµ¿ ÃßÃâ ÀÚÁú   Áú¹® À¯»ç¼º ºÐ¼®   natural language understanding   sentence embedding   automatic feature extraction   question similarity analysis  
ÆÄÀÏ÷ºÎ PDF ´Ù¿î·Îµå