Á¤º¸Ã³¸®ÇÐȸ ³í¹®Áö ¼ÒÇÁÆ®¿þ¾î ¹× µ¥ÀÌÅÍ °øÇÐ
Current Result Document :
ÇѱÛÁ¦¸ñ(Korean Title) |
´Ü¾îÀÇ ÀÇ¹Ì¿Í ¹®¸ÆÀ» °í·ÁÇÑ ¼øȯ½Å°æ¸Á ±â¹ÝÀÇ ¹®¼ ºÐ·ù |
¿µ¹®Á¦¸ñ(English Title) |
Document Classification using Recurrent Neural Network with Word Sense and Contexts |
ÀúÀÚ(Author) |
ÁÖÁ¾¹Î
±è³²ÈÆ
¾çÇüÁ¤
¹ÚÇõ·Î
Jong-Min Joo
Nam-Hun Kim
Hyung-Jeong Yang
Hyuck-Ro Park
|
¿ø¹®¼ö·Ïó(Citation) |
VOL 07 NO. 07 PP. 0259 ~ 0266 (2018. 07) |
Çѱ۳»¿ë (Korean Abstract) |
º» ³í¹®¿¡¼´Â ´Ü¾îÀÇ ¼ø¼¿Í ¹®¸ÆÀ» °í·ÁÇϴ Ư¡À» ÃßÃâÇÏ¿© ¼øȯ½Å°æ¸Á(Recurrent Neural Network)À¸·Î ¹®¼¸¦ ºÐ·ùÇÏ´Â ¹æ¹ýÀ» Á¦¾ÈÇÑ´Ù. ´Ü¾îÀÇ Àǹ̸¦ °í·ÁÇÑ word2vec ¹æ¹ýÀ¸·Î ¹®¼³»ÀÇ ´Ü¾î¸¦ º¤ÅͷΠǥÇöÇÏ°í, ¹®¸ÆÀ» °í·ÁÇϱâ À§ÇØ doc2vecÀ¸·Î ÀÔ·ÂÇÏ¿© ¹®¼ÀÇ Æ¯Â¡À» ÃßÃâÇÑ´Ù. ¹®¼ºÐ·ù ¹æ¹ýÀ¸·Î ÀÌÀü ³ëµåÀÇ Ãâ·ÂÀ» ´ÙÀ½ ³ëµåÀÇ ÀÔ·ÂÀ¸·Î Æ÷ÇÔÇÏ´Â RNN ºÐ·ù±â¸¦ »ç¿ëÇÑ´Ù. RNN ºÐ·ù±â´Â ½Å°æ¸Á ºÐ·ù±â Áß¿¡¼µµ ½ÃÄö½º µ¥ÀÌÅÍ¿¡ ÀûÇÕÇϱ⠶§¹®¿¡ ¹®¼ ºÐ·ù¿¡ ÁÁÀº ¼º´ÉÀ» º¸ÀδÙ. RNN¿¡¼µµ ±×¶óµð¾ðÆ®°¡ ¼Ò½ÇµÇ´Â ¹®Á¦¸¦ ÇØ°áÇØÁÖ°í °è»ê¼Óµµ°¡ ºü¸¥ GRU(Gated Recurrent Unit) ¸ðµ¨À» »ç¿ëÇÑ´Ù. ½ÇÇè µ¥ÀÌÅÍ·Î ÇÑ±Û ¹®¼ ÁýÇÕ 1°³¿Í ¿µ¾î ¹®¼ ÁýÇÕ 2°³¸¦ »ç¿ëÇÏ¿´°í ½ÇÇè °á°ú GRU±â¹Ý ¹®¼ ºÐ·ù±â°¡ CNN ±â¹Ý ¹®¼ ºÐ·ù±â ´ëºñ ¾à 3.5%ÀÇ ¼º´É Çâ»óÀ» º¸¿´´Ù.
|
¿µ¹®³»¿ë (English Abstract) |
In this paper, we propose a method to classify a document using a Recurrent Neural Network by extracting features considering word sense and contexts. Word2vec method is adopted to include the order and meaning of the words expressing the word in the document as a vector. Doc2vec is applied for considering the context to extract the feature of the document. RNN classifier, which includes the output of the previous node as the input of the next node, is used as the document classification method. RNN classifier presents good performance for document classification because it is suitable for sequence data among neural network classifiers. We applied GRU (Gated Recurrent Unit) model which solves the vanishing gradient problem of RNN. It also reduces computation speed. We used one Hangul document set and two English document sets for the experiments and GRU based document classifier improves performance by about 3.5% compared to CNN based document classifier.
|
Å°¿öµå(Keyword) |
¹®¼ ºÐ·ù
Word2vec
Doc2vec ¼øȯ½Å°æ¸Á
GRU
Document Classification
Word2vec
Doc2vec
Recurrent Neural Network
Gated Recurrent Unit
|
ÆÄÀÏ÷ºÎ |
PDF ´Ù¿î·Îµå
|