• 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) Word2vec ¸ðµ¨·Î ÇнÀµÈ ´Ü¾î º¤ÅÍÀÇ ÀÇ¹Ì °ü°è ºÐ¼®
¿µ¹®Á¦¸ñ(English Title) Analyzing Semantic Relations of Word Vectors trained by The Word2vec Model
ÀúÀÚ(Author) °­Çü¼®   ¾çÀåÈÆ   Hyungsuc Kang   Janghoon Yang  
¿ø¹®¼ö·Ïó(Citation) VOL 46 NO. 10 PP. 1088 ~ 1093 (2019. 10)
Çѱ۳»¿ë
(Korean Abstract)
ÀÚ¿¬¾î 󸮸¦ ÀÌ¿ëÇÑ Àΰø Áö´É È°¿ëÀÌ Áõ°¡Çϸ鼭 ´Ü¾î ÀÓº£µù¿¡ ´ëÇÑ Á߿伺ÀÌ Áõ°¡ÇÏ°í ÀÖ´Ù. ÀÌ ³í¹®¿¡¼­´Â ´Ü¾î ÀÓº£µù¿¡ È°¿ëµÇ´Â word2vec ¸ðµ¨ÀÌ ´Ü¾îµé °£ÀÇ ´ë¸³ ¹× »óÇÏ °ü°è¸¦ Ç¥ÇöÇÏ´Â ´É·ÂÀ» ±ºÁýÈ­ Ư¼º°ú t-SNE ºÐÆ÷¸¦ ÀÌ¿ëÇÏ¿© Á¤¼ºÀûÀ¸·Î ºÐ¼®ÇÏ¿´´Ù. À̸¦ À§ÇÏ¿© 10°¡Áö ¹üÁÖ¿¡ ¼ÓÇÏ´Â ´Ü¾îµé¿¡ ´ëÇؼ­ K-Means ¾Ë°í¸®Áò¿¡ µû¶ó¼­ ±ºÁýÈ­¸¦ ½Ç½ÃÇÏ¿´´Ù. ´Ü¾îÀÇ ´ë¸³ °ü°è´Â ÀϺΠÁ¦´ë·Î Ç¥ÇöµÇÁö ¾Ê´Â °æ¿ì°¡ ¹ß»ýÇÏ¿´´Ù. ÀÌ´Â ÀϺΠ´ë¸³ °ü°è¿¡ ÀÖ´Â ´Ü¾îµéÀÌ ´Ù¼öÀÇ °øÅëÀûÀÎ ¼Ó¼ºÀ» °®°í ÀÖÀ¸¸é¼­ ¼Ò¼öÀÇ ´ë¸³Àû ¼Ó¼º¸¸À» °®°í Àֱ⠶§¹®À¸·Î º¸ÀδÙ. ¶ÇÇÑ, ´Ü¾îÀÇ »óÇÏ °ü°è´Â word2vec ¸ðµ¨¿¡¼­ ÀüÇô ¹Ý¿µµÇÁö ¾ÊÀ½ÀÌ È®ÀεǾú´Ù. ±× ¿øÀÎÀº ´Ü¾îÀÇ »óÇÏ °ü°è°¡ ¾ð¾îÀÇ ÀÚ¿¬½º·¯¿î ½Àµæ °úÁ¤ÀÌ ¾Æ´Ï¶ó, Áö½Ä ü°èÀÇ ÇнÀ °úÁ¤À» ÅëÇØ È¹µæµÇ´Â Á¤º¸À̱⠶§¹®ÀÎ °ÍÀ¸·Î º¸ÀδÙ. µû¶ó¼­ ºÐ»ê °¡¼³¿¡ ±Ù°ÅÇÑ word2vec ¸ðµ¨Àº ÀϺΠ´Ü¾îÀÇ ´ë¸³ °ü°è¸¦ Ç¥ÇöÇÏ´Â µ¥ ÇÑ°è°¡ ÀÖ°í, ´Ü¾îÀÇ »óÇÏ °ü°è¸¦ Á¦´ë·Î Ç¥ÇöÇÏÁö ¸øÇÏ´Â °ÍÀ¸·Î ºÐ¼®µÇ¾ú´Ù.
¿µ¹®³»¿ë
(English Abstract)
As the usage of artificial intelligence (AI) in natural language processing has increased, the importance of word embedding has grown significantly. This paper qualitatively analyzes the representational capability of word2vec models to structure semantic relation in terms of antonymy and hyponymy based on clustering characteristics and t-SNE distribution. To this end, a K-means clustering algorithm was applied to a set of words drawn from 10 categories. Some words in antonymy are found not to be embedded properly. This is attributed to the fact that they typically have many common attributes with a very few opposite ones. It is also observed that words in hyponymy are not properly embedded at all. This can be attributed to the fact that the hyponymic relations of those words are based on the information gathered through a learning process of a knowledge system, as opposed to a natural process of language acquisition. Thus, it appears that word2vec models based on the distributional hypothesis are limited to representing certain antonymic relations and do not properly represent hyponymic relations at all.
Å°¿öµå(Keyword) word2vec   ´Ü¾î ÀÓº£µù   ÀÇ¹Ì °ü°è   ±ºÁýÈ­   K-means   word2vec   word embedding   semantic relation   clustering   K-means  
ÆÄÀÏ÷ºÎ PDF ´Ù¿î·Îµå