• 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) ´ë¿ë·® ÅؽºÆ® ÀÚ¿øÀ» È°¿ëÇÑ Çѱ¹¾î ÇüÅÂ¼Ò ÀÓº£µùÀÇ ¸ðµ¨º° ¼º´É ºñ±³ ºÐ¼®
¿µ¹®Á¦¸ñ(English Title) Comparative Analysis of Various Korean Morpheme Embedding Models using Massive Textual Resources
ÀúÀÚ(Author) ÀÌ´Ùºó   ÃÖ¼ºÇÊ   Da-Bin Lee   Sung-Pil Choi  
¿ø¹®¼ö·Ïó(Citation) VOL 46 NO. 05 PP. 0413 ~ 0418 (2019. 05)
Çѱ۳»¿ë
(Korean Abstract)
´Ü¾î ÀÓº£µùÀº ÄÄÇ»ÅÍ°¡ ÀÚ¿¬¾î¸¦ ÀνÄÇÒ ¼ö ÀÖµµ·Ï ÇÏ´Â º¯È¯ ±â¹ýÀ¸·Î ±â°è¹ø¿ª, °³Ã¼¸í ÀÎ½Ä µî ±â°èÇнÀÀ» ¹ÙÅÁÀ¸·Î ÇÏ´Â ÀÚ¿¬¾î ó¸® ºÐ¾ß¿¡¼­ ´Ù¾çÇÏ°Ô »ç¿ëµÇ°í ÀÖ´Ù. ´Ü¾î ÀÓº£µùÀ» »ý¼ºÇÏ´Â ´Ù¾çÇÑ ´Ü¾î ÀÓº£µù ¸ðµ¨µéÀÌ Á¸ÀçÇÏÁö¸¸ ÀÌ·¯ÇÑ ¸ðµ¨µéÀ» µ¿ÀÏÇÑ Á¶°Ç¿¡¼­ ¼º´ÉÀ» ºñ±³ ºÐ¼®ÇÑ ¿¬±¸°¡ ¹ÌºñÇÏ´Ù. º» ³í¹®¿¡¼­´Â Çѱ¹¾î ÇüÅÂ¼Ò ´ÜÀ§ ¶ç¾î¾²±â¸¦ ±â¹ÝÀ¸·Î ÇÏ¿© È°¹ßÇÏ°Ô »ç¿ëµÇ°í ÀÖ´Â ¸ðµ¨ÀÎ Word2VecÀÇ Skip-Gram°ú CBOW, GloVe, FastTextÀÇ ¼º´ÉÀ» ºñ±³ ºÐ¼®ÇÑ´Ù. ´º½º ´ë¿ë·® ¸»¹¶Ä¡ ¹× ¼¼Á¾ ¸»¹¶Ä¡¸¦ ¹ÙÅÁÀ¸·Î ½ÇÇèÇÑ °á°ú FastText°¡ °¡Àå ³ôÀº ¼º´ÉÀ» È®ÀÎÇÒ ¼ö ÀÖ¾ú´Ù.
¿µ¹®³»¿ë
(English Abstract)
Word embedding is a transformation technique that enables a computer to recognize natural language. It is used in various fields of natural language processing based on machine learning such as machine translation and named-entity recognition. Various word-embedding models are available; however, few studies have compared the performance of these models under similar conditions. In this paper, we compare and analyze the performance of Word2Vec Skip-Gram, CBOW, Glove, and FastText, which are actively used according to Korean morpheme spacing. Based on experimental results with large news corpus and Sejong corpus, FastText yielded the best performance among CBOW, Skip-gram, Glove, and FastText of Word2Vec.
Å°¿öµå(Keyword) ´Ü¾î ÀÓº£µù   ÀÚ¿¬¾î 󸮠  Word2Vec   GloVe   FastText   word embedding   NLP(Natural Language Processing)   Word2Vec   GloVe   FastText  
ÆÄÀÏ÷ºÎ PDF ´Ù¿î·Îµå