• 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¸°úÇÐȸ ÄÄÇ»ÆÃÀÇ ½ÇÁ¦ ³í¹®Áö (KIISE Transactions on Computing Practices)

Á¤º¸°úÇÐȸ ÄÄÇ»ÆÃÀÇ ½ÇÁ¦ ³í¹®Áö (KIISE Transactions on Computing Practices)

Current Result Document :

ÇѱÛÁ¦¸ñ(Korean Title) ¹®Àå ·¹º§ ±×·¡ÇÁ ȸ¼± ½Å°æ¸ÁÀ» ÅëÇÑ ÅؽºÆ® ºÐ·ù
¿µ¹®Á¦¸ñ(English Title) Text Classification via Sentence-level Graph Convolutional Networks
ÀúÀÚ(Author) À̹ο젠 ±è¾çÈÆ   Á¤±³¹Î   Minwoo Lee   Yanghoon Kim   Kyomin Jung  
¿ø¹®¼ö·Ïó(Citation) VOL 25 NO. 08 PP. 0397 ~ 0401 (2019. 08)
Çѱ۳»¿ë
(Korean Abstract)
ÅؽºÆ® ºÐ·ù´Â ÀÚ¿¬¾îó¸® ºÐ¾ßÀÇ ÀüÅëÀûÀÎ ¹®Á¦ÀÌ´Ù. ±âÁ¸ÀÇ RNN ¹× CNN ±â¹Ý ÅؽºÆ® ºÐ·ù ¸ðµ¨µéÀº ¼øÂ÷ÀûÀÎ ´Ü¾î ±¸Á¶¿¡ ÀÇÁ¸Çϱ⠶§¹®¿¡ ÀÎÁ¢ÇÏÁö ¾ÊÁö¸¸ °ü·Ã¼ºÀÌ ³ôÀº ´Ü¾î °£ÀÇ °ü°è¸¦ À¯ÃßÇϱ⠾î·Æ´Ù´Â ¹®Á¦Á¡ÀÌ ÀÖ´Ù. ¹Ý¸é GCN(Graph Convolutional Network)Àº ±×·¡ÇÁÀÇ ÇüÅ·Πµ¥ÀÌÅ͸¦ ÀԷ¹ޱ⠶§¹®¿¡ ¹®ÀåÀÇ ¼øÂ÷Àû ±¸Á¶¿¡ ´ëÇÑ ÀÇÁ¸µµ¸¦ ÁÙÀÏ ¼ö ÀÖ´Ù. º» ³í¹®¿¡¼­´Â ¹®¼­ÀÇ ºñ¼øÂ÷ÀûÀÎ °ü°è¸¦ ±×·¡ÇÁ·Î ´ã¾Æ³»¾î ´õ¿í È¿°úÀûÀ¸·Î ÆľÇÇÏ°í ºÐ·ùÇÏ´Â Àΰø½Å°æ¸Á ¸ðµ¨À» Á¦¾ÈÇÑ´Ù. ¹®¼­¸¦ ±×·¡ÇÁ·Î Ç¥ÇöÇϱâ À§ÇØ °¢ ´Ü¾î¸¦ ±×·¡ÇÁÀÇ ³ëµå·Î º¯È¯ÇÏ°í, ´Ü¾î °£ÀÇ °ü°è¸¦ °è»êÇØ ¿§Áö·Î Á¤ÀÇÇÑ´Ù. ÃÖ±Ù¿¡ Á¦½ÃµÈ GCN ±¸Á¶¸¦ ÅëÇØ ´Ü¾î °£ÀÇ °ü°è°¡ ¹Ý¿µµÈ ´Ü¾î º¤Å͸¦ °è»êÇÑ µÚ, ¾îÅÙ¼Ç ±â¹Ý ¿ä¾à ÇÔ¼ö¸¦ ÅëÇØ ¹®´ÜÀ» ÁÖ¾îÁø Ŭ·¡½º·Î ºÐ·ùÇÏ´Â ¹æ¹ýÀ» Á¦½ÃÇÑ´Ù. ½ÇÇè °á°ú, »õ·Ó°Ô Á¦½ÃµÈ ¸ðµ¨ÀÌ RNN ¹× CNN ±â¹Ý ÅؽºÆ® ºÐ·ù ¸ðµ¨º¸´Ù ÁÁÀº ¼º´ÉÀ» º¸¿´´Ù.
¿µ¹®³»¿ë
(English Abstract)
Text classification is an important task in natural language processing, and most of the recent approaches employ neural networks to learn and classify the texts. RNN and CNN based models, which are widely used for solving the task, involve reading and processing the text in a sequential manner. This creates inefficiency in learning dependencies between far-apart words. On the contrary, Graph Convolutional Network (GCN) architecture is capable of processing more complex graph-structured data, thus having potential to recognize and learn from complex linguistic structures. In the present work, we transform text sequences into graphs by assigning each word in the text as a node and representing the relationship between words as edges. We then propose a method for solving text classification that uses recent GCN architectures to take the transformed text-graph as input, learn hidden representations, and output a single hidden representation for classification. In our experiments, our proposed model outperformed RNN and CNN based models with regards to various text classification tasks.
Å°¿öµå(Keyword) ÀÚ¿¬¾î 󸮠  Àΰø ½Å°æ¸Á   ±×·¡ÇÁ ȸ¼± ½Å°æ¸Á   ÅؽºÆ®±×·¡ÇÁ   ±×·¡ÇÁ ºÐ·ù   ÅؽºÆ® ºÐ·ù   natural language processing   neural networks   graph convolutional networks   textgraph   graph classification   text classification  
ÆÄÀÏ÷ºÎ PDF ´Ù¿î·Îµå