• 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¸Ã³¸®ÇÐȸ ³í¹®Áö > Á¤º¸Ã³¸®ÇÐȸ ³í¹®Áö ¼ÒÇÁÆ®¿þ¾î ¹× µ¥ÀÌÅÍ °øÇÐ

Á¤º¸Ã³¸®ÇÐȸ ³í¹®Áö ¼ÒÇÁÆ®¿þ¾î ¹× µ¥ÀÌÅÍ °øÇÐ

Current Result Document :

ÇѱÛÁ¦¸ñ(Korean Title) ´ÙÁß ÀÛ¾÷, ´ÙÁß È© Áú¹® ÀÀ´äÀ» À§ÇÑ ±×·¡ÇÁ Ãß·Ð ¹× ¸Æ¶ô À¶ÇÕ
¿µ¹®Á¦¸ñ(English Title) Graph Reasoning and Context Fusion for Multi-Task, Multi-Hop Question Answering
ÀúÀÚ(Author) ÀÌ»óÀÇ   ±èÀÎö   Sangui Lee   Incheol Kim  
¿ø¹®¼ö·Ïó(Citation) VOL 10 NO. 08 PP. 0319 ~ 0330 (2021. 08)
Çѱ۳»¿ë
(Korean Abstract)
ÃÖ±Ù ¿ÀÇ µµ¸ÞÀÎ ÀÚ¿¬¾î Áú¹® ÀÀ´ä ºÐ¾ß¿¡¼­´Â ´ÙÁß ÀÛ¾÷, ´ÙÁß È© Áú¹® ÀÀ´ä¿¡ °üÇÑ ¿¬±¸µéÀÌ È°¹ßÈ÷ ÁøÇàµÇ¾î ¿À°í ÀÖ´Ù. º» ³í¹®¿¡¼­´Â ÀÌ·¯ÇÑ ´ÙÁß ÀÛ¾÷, ´ÙÁß È© Áú¹®µé¿¡ È¿°úÀûÀ¸·Î ÀÀ´äÇϱâ À§ÇØ, °èÃþÀû ±×·¡ÇÁ ±â¹ÝÀÇ »õ·Î¿î ½ÉÃþ ½Å°æ¸Á ¸ðµ¨À» Á¦¾ÈÇÑ´Ù. Á¦¾È ¸ðµ¨¿¡¼­´Â °èÃþÀû ±×·¡ÇÁ¿Í ±×·¡ÇÁ ½Å°æ¸ÁÀ» ÀÌ¿ëÇØ ¿©·¯ ¹®´Üµé·ÎºÎÅÍ ¼­·Î ´Ù¸¥ ¼öÁØÀÇ ¸Æ¶ô Á¤º¸¸¦ ¾ò¾î³½ ÈÄ, À̵éÀ» È°¿ëÇÏ¿© ´äº¯ À¯Çü, µÞ¹Þħ ¹®Àåµé°ú ´äº¯ ¿µ¿ª µîÀ» µ¿½Ã¿¡ ¿¹ÃøÇس½´Ù. º» ³í¹®¿¡¼­´Â ¿ÀÇ µµ¸ÞÀÎ ÀÚ¿¬¾î Áú¹® ÀÀ´ä µ¥ÀÌÅÍ ÁýÇÕÀÎ HotpotQA¸¦ ÀÌ¿ëÇÑ ½ÇÇèµéÀ» ÅëÇØ, Á¦¾È ¸ðµ¨ÀÇ ³ôÀº ¼º´É°ú ±àÁ¤Àû È¿°ú¸¦ ÀÔÁõÇÑ´Ù.
¿µ¹®³»¿ë
(English Abstract)
Recently, in the field of open domain natural language question answering, multi-task, multi-hop question answering has been studied extensively. In this paper, we propose a novel deep neural network model using hierarchical graphs to answer effectively such multi-task, multi-hop questions. The proposed model extracts different levels of contextual information from multiple paragraphs using hierarchical graphs and graph neural networks, and then utilize them to predict answer type, supporting sentences and answer spans simultaneously. Conducting experiments with the HotpotQA benchmark dataset, we show high performance and positive effects of the proposed model.
Å°¿öµå(Keyword) ¿ÀÇ µµ¸ÞÀÎ Áú¹® ÀÀ´ä   ´ÙÁß È© Ã߷Р  ´ÙÁß ÀÛ¾÷ Áú¹®   °èÃþÀû ±×·¡ÇÁ   ±×·¡ÇÁ ½Å°æ¸Á   Open Domain Question Answering   Multi-hop Reasoning   Multi-task Question   Hierarchical Graph   Graph Neural Network  
ÆÄÀÏ÷ºÎ PDF ´Ù¿î·Îµå