• 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) Çѱ¹¾î ¾îÈÖ Àǹ̸ÁÀ» È°¿ëÇÑ CRF ¸ðµ¨ ±â¹Ý °³Ã¼¸í ÀνÄ
¿µ¹®Á¦¸ñ(English Title) CRF based Named Entity Recognition Using a Korean Lexical Semantic Network
ÀúÀÚ(Author) ¹Ú¼­¿¬   ¿Áö¿µ   Seoyeon Park   Cheolyoung Ock  
¿ø¹®¼ö·Ïó(Citation) VOL 48 NO. 05 PP. 0556 ~ 0567 (2021. 05)
Çѱ۳»¿ë
(Korean Abstract)
°³Ã¼¸í ÀνÄÀº ÁÖ¾îÁø ¹®Àå ³»ÀÇ °íÀ¯ÇÑ Àǹ̰¡ ÀÖ´Â ´Ü¾îµéÀ» ¹Ì¸® Á¤ÀÇµÈ °³Ã¼ÀÇ ¹üÁÖ·Î ºÐ·ùÇÏ´Â ÀÛ¾÷ÀÌ´Ù. ÃÖ±Ù µö·¯´× ³×Æ®¿öÅ© ȤÀº ¾ð¾î ¸ðµ¨À» ÀÌ¿ëÇÑ °³Ã¼¸í ÀÎ½Ä ¿¬±¸µéÀÌ ³ôÀº ¼º´ÉÀ» º¸¿´Áö¸¸ ÀÌ·¯ÇÑ ¸ðµ¨Àº °í¼º´ÉÀÇ ÄÄÇ»Æà ÆÄ¿ö°¡ ¿ä±¸µÇ¸ç ÇнÀ ¸ðµ¨ÀÇ ¼Óµµ°¡ ´À·Á ¾ÆÁ÷Àº ½Ç¿ë¼ºÀÌ ³·´Ù´Â ¹®Á¦°¡ ÀÖ´Ù. º» ³í¹®¿¡¼­´Â ½Ç¿ë¼ºÀ» ¸ñÀûÀ¸·Î ó¸® ¼Óµµ¿Í Á¤È®·üÀ» ¸ðµÎ °í·ÁÇÏ¿© ±â°èÇнÀ ¹æ½ÄÀÇ CRF¸¦ ±â¹ÝÀ¸·Î ÇÏ¿© ÀÇ¹Ì ÀÚÁú°ú ±¸¹®Àû ÀÚÁúÀ» Ãß°¡ÇÑ °³Ã¼¸í ÀÎ½Ä ½Ã½ºÅÛÀ» Á¦¾ÈÇÑ´Ù. Çѱ¹¾î ¾îÈÖ Àǹ̸Á(UWordMap)À» È°¿ëÇÏ¿© »ç¶÷ÀÇ Áö½ÄÀ» ±â¹ÝÀ¸·Î ÇÏ¿© ÀÇ¹Ì ÀÚÁúÀÎ »óÀ§¾î, ÃÖ»óÀ§¾î Á¤º¸¿Í ±¸¹®Àû ÀÚÁúÀÎ ÀÇÁ¸°ü°è¿Í °ÝÁ¶»ç Á¤º¸¸¦ ÇнÀ ÀÚÁú·Î Ãß°¡ÇÏ°í Æò°¡ÇÏ¿´´Ù. ½ÇÇè °á°ú, F1 score ±âÁØ 90.54% Æ÷ÀÎÆ®ÀÇ ¼º´É°ú ÃÊ´ç ¾à 1,461 ¹®ÀåÀ» ó¸®ÇÏ¿´´Ù.
¿µ¹®³»¿ë
(English Abstract)
Named Entity Recognition(NER) is the process of classifying words with unique meanings that often appear as OOV within sentence into categories of predefined entities. Recently, many researches have been conducted using deep learning to synthesize the words¡¯ embedding via Convolution Neural Network(CNN), Long Short-Term Memory(LSTM) networks or training language models. However, models using these deep learning network or language model require high performance computing power and have low practicality due to slow speed. For practicality, this paper proposes Conditional Random Field(CRF) based NER model using Korean lexical network(UWordMap). By using hypernym, dependence and case particle information as training feature, our model showed 90.54% point of accuracy, 1,461 sentences/sec processing speed.
Å°¿öµå(Keyword) °³Ã¼¸í ÀνĠ  ±â°èÇнÀ   Á¶°ÇºÎ ·£´ý Çʵ堠 Çѱ¹¾î ¾îÈÖ Àǹ̸Á   named entity recognition   machine learning   conditional random fields   korean lexical semantic network  
ÆÄÀÏ÷ºÎ PDF ´Ù¿î·Îµå