• 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 : 8 / 32 ÀÌÀü°Ç ÀÌÀü°Ç   ´ÙÀ½°Ç ´ÙÀ½°Ç

ÇѱÛÁ¦¸ñ(Korean Title) Áö½Ä ±×·¡ÇÁ¸¦ ÀÌ¿ëÇÑ ¿ÀÇ µµ¸ÞÀÎ Áú¹® ÀÀ´ä
¿µ¹®Á¦¸ñ(English Title) Open Domain Question Answering using Knowledge Graph
ÀúÀÚ(Author) À̱âÈ£   ±èÀÎö   Giho Lee   Incheol Kim  
¿ø¹®¼ö·Ïó(Citation) VOL 47 NO. 09 PP. 0853 ~ 0862 (2020. 09)
Çѱ۳»¿ë
(Korean Abstract)
º» ³í¹®¿¡¼­´Â ¿ÀÇ µµ¸ÞÀÎÀÇ º¹ÀâÇÑ Áú¹®µé¿¡ È¿°úÀûÀ¸·Î ÀÀ´äÇϱâ À§ÇÑ »õ·Î¿î Áö½Ä ±×·¡ÇÁ Ãß·Ð ¸ðµ¨ KGNetÀ» Á¦¾ÈÇÑ´Ù. º» ¸ðµ¨¿¡¼­´Â Áú¹® ÀÀ´ä¿¡ ÀÌ¿ëÇÒ Áö½Ä º£À̽ºÀÇ ºÒ¿ÏÀü¼º ¹®Á¦¿¡ ÁÖ¸ñÇÑ´Ù. À̸¦ À§ÇØ º» ¸ðµ¨¿¡¼­´Â ¼­·Î ´Ù¸¥ ÇüÅÂÀÇ µÎ °¡Áö Áö½Ä ÀÚ¿øÀÎ Áö½Ä º£À̽º¿Í ¹®¼­ ÁýÇÕ ¸ðµÎ¸¦ ÇϳªÀÇ Áö½Ä ±×·¡ÇÁ·Î ÅëÇÕÇÏ¿© ´äº¯ »ý¼º¿¡ È°¿ëÇÑ´Ù. ¶ÇÇÑ º» ¸ðµ¨¿¡¼­´Â Áö½Ä ±×·¡ÇÁ »ó¿¡¼­ º¹ÀâÇÑ ¸ÖƼ È© Áú¹®µé¿¡ °üÇÑ ´äº¯À» º¸´Ù È¿°úÀûÀ¸·Î À¯µµÇس»±â À§ÇØ, ±×·¡ÇÁ ½Å°æ¸ÁÀ» ÀÌ¿ëÇÑ »õ·Î¿î Áö½Ä ÀÓº£µù°ú Ãß·Ð ±â¹ýÀ» Àû¿ëÇÑ´Ù. º» ³í¹®¿¡¼­´Â ´ëÇ¥ÀûÀÎ Áú¹® ÀÀ´ä º¥Ä¡¸¶Å© µ¥ÀÌÅÍ ÁýÇÕÀÎ WebQuestionsSP¿Í MetaQA¸¦ ÀÌ¿ëÇÑ ´Ù¾çÇÑ ½ÇÇèµéÀ» ÅëÇØ, Á¦¾È ¸ðµ¨ÀÇ È¿°ú¿Í ¿ì¼ö¼ºÀ» ÀÔÁõÇÑ´Ù
¿µ¹®³»¿ë
(English Abstract)
In this paper, we propose a novel knowledge graph inference model called KGNet for answering the open domain complex questions. This model addresses the problem of knowledge base incompleteness. In this model, two different types of knowledge resources, knowledge base and corpus, are integrated into a single knowledge graph. Moreover, to derive answers to complex multi-hop questions effectively, this model adopts a new knowledge embedding and reasoning module based on Graph Neural Network (GNN). We demonstrate the effectiveness and performance of the proposed model through various experiments over two large question answering benchmark datasets,
Å°¿öµå(Keyword) ¿Àǵµ¸ÞÀÎ Áú¹® ÀÀ´ä   Ãß·Ð ¸ðµ¨   ¸ÖƼ È© Áú¹®   ±×·¡ÇÁ ½Å°æ¸Á   Áö½Ä ÀÓº£µù   open-domain question answering   inference model   multi-hop question   graph neural network   knowledge embedding  
ÆÄÀÏ÷ºÎ PDF ´Ù¿î·Îµå