• 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) 2´Ü°è ÇнÀÀ» ÅëÇÑ Span Matrix ±â¹Ý Á¤´ä È帱º ŽÁö ¸ðµ¨
¿µ¹®Á¦¸ñ(English Title) A Span Matrix-based Answer Candidates Detection Model used 2-Step Learning
ÀúÀÚ(Author) ±èº¸Àº   À念Áø   ±èÇмö   Boeun Kim   Youngjin Jang   Harksoo Kim                          
¿ø¹®¼ö·Ïó(Citation) VOL 48 NO. 05 PP. 0539 ~ 0547 (2021. 05)
Çѱ۳»¿ë
(Korean Abstract)
µ¥ÀÌÅÍ ÀÚµ¿ ±¸ÃàÀ̶õ ¾Ë°í¸®ÁòÀ̳ª ½ÉÃþ ½Å°æ¸Á µîÀ» ÅëÇØ µ¥ÀÌÅ͸¦ ÀÚµ¿À¸·Î ±¸ÃàÇÏ´Â ±â¼úÀ» ÀǹÌÇÑ´Ù. º» ³í¹®¿¡¼­ ¸ñÇ¥·Î ÇÏ´Â ÁúÀÇÀÀ´ä µ¥ÀÌÅÍ ÀÚµ¿ ±¸Ãà ½Ã½ºÅÛÀº Áú¹® »ý¼º ¸ðµ¨À» ÅëÇØ ÁÖ·Î ¿¬±¸µÇ¾úÀ¸¸ç, ÀÌ´Â ÁÖ¾îÁø ´Ü¶ô°ú °ü·ÃµÈ Áú¹®À» »ý¼ºÇÏ´Â ¸ðµ¨À» ÀǹÌÇÑ´Ù. ±âÁ¸¿¡´Â Áú¹® »ý¼º ¸ðµ¨¿¡ ´Ü¶ô°ú Á¤´ä È常¦ ÀÔ·ÂÇÏ¿© ÀÌ¿Í °ü·ÃµÈ Áú¹®À» »ý¼ºÇßÀ¸¸ç, Áú¹® »ý¼º ¸ðµ¨¿¡ ÀԷµǴ Á¤´ä È帴 ±ÔÄ¢ ±â¹Ý ¹æ¹ýÀ̳ª ½ÉÃþ ½Å°æ¸ÁÀ» ÀÌ¿ëÇÑ ¹æ¹ý µîÀ» ÅëÇØ Å½ÁöµÇ¾ú´Ù. º» ³í¹®¿¡¼­´Â Áú¹® »ý¼ºÀÇ ÇÏÀ§ ÀÛ¾÷ÀÎ Á¤´ä ŽÁö°¡ Áú¹® »ý¼º¿¡ Å« ¿µÇâÀ» ÁÙ °ÍÀ¸·Î ÆÇ´ÜÇß°í, Span Matrix¸¦ ÀÌ¿ëÇÑ Á¤´ä È帱º ŽÁö ¸ðµ¨ ¹× 2´Ü°è ÇнÀ ¹æ¹ýÀ» Á¦¾ÈÇß´Ù. ´Ù¾çÇÑ Á¤´ä Èĺ¸ ÃßÃâ ¹æ¹ýÀ» ÅëÇØ »ý¼ºÇÑ Áú¹®ÀÌ ÁúÀÇÀÀ´ä ½Ã½ºÅÛ¿¡ ¾î¶² ¿µÇâÀ» ÁÖ´ÂÁö ¾Ë¾Æº¸±â À§ÇÑ ½ÇÇèÀ» ÁøÇàÇß´Ù. Á¦¾È ¸ðµ¨Àº ±âÁ¸ ¸ðµ¨¿¡ ºñÇØ ¸¹Àº ¼öÀÇ Á¤´äÀ» ÃßÃâÇßÀ¸¸ç, °³Ã¼¸í µ¥ÀÌÅͼÂÀ» È°¿ëÇÔÀ¸·Î½á ÇнÀ °úÁ¤ÀÇ ³ëÀÌÁ º¸¿ÏÇß´Ù. À̸¦ ÅëÇØ Á¦¾È ¸ðµ¨ÀÌ ÃßÃâÇÑ Á¤´ä È帷Π»ý¼ºÇÑ ÁúÀÇÀÀ´ä µ¥ÀÌÅÍ°¡ ÁúÀÇÀÀ´ä ½Ã½ºÅÛÀÇ ¼º´É¿¡ °¡Àå Å©°Ô ±â¿©ÇÏ´Â °ÍÀ» È®ÀÎÇß´Ù.
¿µ¹®³»¿ë
(English Abstract)
Automatic data construction refers to a technology that automatically constructs data through algorithms or deep neural networks. The automated construction system of question-answer data aimed at in this paper was mainly studied through a question generation model, which signifies a model that generates questions related to a given paragraph. Previously, paragraph and answer candidates were entered into the question generation model and related questions were generated. The answer candidates' input to the question generation model was detected through a rule-based method or a method using a deep neural network. We judged that answer detection, which is a subtask of question generation, will have a great influence on question generation. Consequently, we have proposed answer candidates detection model and 2-step learning method using Span Matrix. An experiment was conducted to find out how the questions generated through various methods of extracting answer candidates affect the question-answering system. The proposed model extracted a large number of correct answers compared to the existing model, and the noise in the learning process was supplemented by using the entity name dataset. Apparently, it was confirmed that the question- answer data generated as answer candidates extracted by the proposed model contributed the most to the performance of the question-answer system
Å°¿öµå(Keyword) Á¤´ä È帱º ŽÁö   Áú¹® »ý¼º   ÁúÀÇÀÀ´ä   µ¥ÀÌÅÍ ÀÚµ¿ ±¸Ãà   Span Matrix   2´Ü°è ÇнÀ   answer candidates detection   question generation   question-answering   automatic data construction   span matrix   2-step learning                 
ÆÄÀÏ÷ºÎ PDF ´Ù¿î·Îµå