• 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 : 4 / 4 ÀÌÀü°Ç ÀÌÀü°Ç

ÇѱÛÁ¦¸ñ(Korean Title) »çÀüÇнÀ ¾ð¾î¸ðµ¨ ±â¹Ý Æ®·£½ºÆ÷¸Ó¸¦ È°¿ëÇÑ ÀǹÌÀ¯»çµµ±â¹Ý ÀÚ¿¬¾îÀÌÇØ ÀǵµÆÄ¾Ç ¹æ¹ý
¿µ¹®Á¦¸ñ(English Title) Semantic Similarity-based Intent Analysis using Pre-trained Transformer for Natural Language Understanding
ÀúÀÚ(Author) Á¤»ó±Ù   ¼­ÇýÀΠ  ±èÇöÁö   ȲÅÂ¿í   Sangkeun Jung   Hyein Seo   Hyunji Kim   Taewook Hwang  
¿ø¹®¼ö·Ïó(Citation) VOL 47 NO. 08 PP. 0748 ~ 0760 (2020. 08)
Çѱ۳»¿ë
(Korean Abstract)
ÀÚ¿¬¾îÀÌÇØ´Â ·Îº¿, ¸Þ½ÅÀú, ÀÚ¿¬¾î ÀÎÅÍÆäÀ̽º µî¿¡ È°¿ëµÇ´Â ±Ù°£ ±â¼ú Áß ÇϳªÀÌ´Ù. º» ¿¬±¸¿¡¼­´Â ÀÚ¿¬¾îÀÌÇØ ¹®Á¦ Áß ¹®ÀåÀÇ Àǵµ¸¦ ÆľÇÇÏ´Â ÀǵµÆľDZâ¼ú¿¡ ÀÖ¾î, ÀüÅëÀûÀÎ ºÐ·ù±â¼úÀ» È°¿ëÇÏ´Â °ÍÀÌ ¾Æ´Ñ, ¹®ÀåÀÇ Àǹ̸¦ º¤ÅÍ ÇüÅ·Π°¡°øÇÒ ¼ö ÀÖ´Â ¹®Àå ¹× ÀǹÌƲ ÀбâÀåÄ¡¸¦ ÇнÀ½ÃÅ°°í, ÈƷù®Àå°ú ÁúÀǹ®ÀåÀÇ º¤ÅÍ °ø°£»óÀÇ Àǹ̰Ÿ®¸¦ ÃøÁ¤ÇÏ¿©, °¡Àå °¡±î¿î ÈƷù®ÀåÀÇ Àǵµ¸¦ ÁúÀǹ®ÀåÀÇ Àǵµ·Î ºÎÂøÇÏ´Â ¹æ¹ýÀ» Á¦¾ÈÇÑ´Ù. À̸¦ À§ÇØ, »çÀüÇнÀ ¾ð¾î¸ðµ¨ ±â¹Ý Æ®·£½ºÆ÷¸Ó¸¦ È°¿ëÇÏ¿© ±âÈ£ ÇüÅÂÀÇ ¹®Àå ¹× ÀǹÌƲÀ» º¤ÅÍ ÇüÅ·Πº¯È¯ÇÏ´Â ¹æ¹ýÀ» ¼Ò°³ÇÑ´Ù. Çѱ¹¾î ±â¹Ý ³¯¾¾ ¹× ³»ºñ°ÔÀÌ¼Ç ¿µ¿ªÀÇ ¸»¹¶Ä¡¿Í ¿µ¾î ±â¹Ý Ç×°ø±³Åë ¿¹¾à ¿µ¿ª, À½¼º ¾ð¾î ÀÌÇØ ½Ã½ºÅÛ ¿µ¿ªÀÇ ÀÚ¿¬¾î ¸»¹¶Ä¡µîÀ» È°¿ëÇÑ ´Ù¾çÇÑ ½ÇÇèÀ» ÅëÇÏ¿© Á¦¾ÈÇÑ ¹æ¹ýÀÌ ¼º°øÀûÀ¸·Î Àǹ̺¤Å͸¦ ¹è¿òÀ» º¸ÀÌ°í, ±âÁ¸ ÀǵµÆÄ¾Ç ±â¼ú ´ëºñ ³ôÀº ¼º´ÉÀ» °¡ÁüÀ» º¸ÀδÙ.
¿µ¹®³»¿ë
(English Abstract)
Natural language understanding (NLU) is a central technique applied to developing robot, smart messenger, and natural interface. In this study, we propose a novel similarity-based intent analysis method instead of the typical classification methods for intent analysis problems in the NLU. To accomplish this, the neural network-based text and semantic frame readers are introduced to learn semantic vectors using pairwise text-semantic frame instances. The text to vector and the semantic frame to vector projection methods using the pre-trained transformer are proposed. Then, we propose a method of attaching the intention tag of the nearest training sentence to the query sentence by measuring the semantic vector distances in the vector space. Four experiments on the natural language learning suggest that the proposed method demonstrates superior performance compared to the existing intention analysis techniques. These four experiments use natural language corpora in Korean and English. The two experiments in Korean are weather and navigation language corpora, and the two English-based experiments involve air travel information systems and voice platform language corpora.
Å°¿öµå(Keyword) ½ÉÃþ½Å°æ¸Á   ÀÚ¿¬¾îÀÌÇØ   ÀǵµºÐ¼®   ÀǵµÆľǠ  ÀǹÌÀ¯»çµµ   Æ®·£½ºÆ÷¸Ó   deep neural network   natural language understanding   intention analysis   semantic similarity   transformer  
ÆÄÀÏ÷ºÎ PDF ´Ù¿î·Îµå