• 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 : 7 / 17 ÀÌÀü°Ç ÀÌÀü°Ç   ´ÙÀ½°Ç ´ÙÀ½°Ç

ÇѱÛÁ¦¸ñ(Korean Title) ±â°è µ¶ÇØ ¼º´É °³¼±À» À§ÇÑ µ¥ÀÌÅÍ Áõ°­ ±â¹ý
¿µ¹®Á¦¸ñ(English Title) Data Augmentation Methods for Improving the Performance of Machine Reading Comprehension
ÀúÀÚ(Author) À̼±°æ   ÃÖÀº¼º   Á¤¼±È£   ÀÌÁ¾¿í   Sunkyung Lee   Eunseong Choi   Seonho Jeong   Jongwuk Lee  
¿ø¹®¼ö·Ïó(Citation) VOL 48 NO. 12 PP. 1298 ~ 1304 (2021. 12)
Çѱ۳»¿ë
(Korean Abstract)
±â°è µ¶ÇØ(Machine Reading Comprehension)¶õ ÄÄÇ»ÅÍ°¡ ÁÖ¾îÁø ÅؽºÆ®ÀÇ Àǹ̸¦ ÀÌÇØ ¹× À̸¦ Æò°¡ÇÏ´Â ¹æ¹ýÀ¸·Î, ÀÚ¿¬¾î ÀÌÇظ¦ À§ÇÑ Áß¿äÇÑ ±â¼ú Áß ÇϳªÀÌ´Ù. ÁÖ¾îÁø ±Û¿¡ ´ëÇؼ­ ÁúÀÇ°¡ ÁÖ¾îÁ³À» ¶§, ÀÌ¿¡ ´ëÇÑ ¿Ã¹Ù¸¥ ÀÀ´äÀ» ã´Â ÁúÀÇ-ÀÀ´äÀÌ °¡Àå ´ëÇ¥ÀûÀÎ ±â°è µ¶ÇØ °úÁ¦ÀÌ´Ù. ±â°è µ¶ÇØ ±â¼úÀº ÃÖ±Ù ½ÉÃþ Àΰø½Å°æ¸Á ±â¹ÝÀÇ ÀÚ¿¬¾î ó¸® ±â¼úÀÇ ¹ß´Þ¿¡ µû¶ó ȹ±âÀûÀÎ ¼º´É °³¼±À» º¸¿´´Ù. ±×·³¿¡µµ ºÒ±¸ÇÏ°í, ÁÖ¾îÁø µ¥ÀÌÅÍ°¡ Èñ¼ÒÇÒ ¶§ ¼º´É °³¼±¿¡ ¾î·Á¿òÀÌ ÀÖÀ» ¼ö ÀÖ´Ù. À̸¦ ÇØ°áÇϱâ À§ÇØ º» ³í¹®¿¡¼­´Â ´Ü¾î ´ÜÀ§ ¹× ¹®Àå ´ÜÀ§ÀÇ ÅؽºÆ® ÆíÁýÀ» ÅëÇÑ µ¥ÀÌÅÍ Áõ°­ ±â¹ýÀ» È°¿ëÇÏ¿© ±âÁ¸ ¸ðµ¨ÀÇ º¯°æÀ» ÃÖ¼ÒÈ­ÇÏ¸ç ¼º´É °³¼±À» ÇÏ°íÀÚ ÇÑ´Ù. Áï, º» ¿¬±¸¿¡¼­´Â ¿µ¾î ÁúÀÇÀÀ´ä µ¥ÀÌÅÍ¿¡¼­ °¡Àå ³Î¸® È°¿ëµÇ°í ÀÖ´Â »çÀü ÇнÀµÈ ¾ð¾î ¸ðµ¨ ±â¹ÝÀÇ ±â°è µ¶ÇØ ¸ðµ¨¿¡ µ¥ÀÌÅÍ Áõ°­ ±â¹ýÀ» Àû¿ëÇÏ¿© ±âÁ¸ ¸ðµ¨ ´ëºñ ¼º´ÉÀÌ Çâ»óµÇ´Â °ÍÀ» È®ÀÎÇÏ¿´´Ù.
¿µ¹®³»¿ë
(English Abstract)
Machine reading comprehension is a method of understanding the meaning and performing inference over a given text by computers, and it is one of the most essential techniques for understanding natural language. The question answering task yields a way to test the reasoning ability of intelligent systems. Nowadays, machine reading comprehension techniques performance has significantly improved following the recent progress of deep neural networks. Nevertheless, there may be challenges in improving performance when data is sparse. To address this issue, we leverage word-level and sentence-level data augmentation techniques through text editing, while minimizing changes to the existing models and cost. In this work, we propose data augmentation methods for a pre-trained language model, which is most widely used in English question answering tasks, to confirm the improved performance over the existing models.
Å°¿öµå(Keyword) ±â°è µ¶ÇØ   µ¥ÀÌÅÍ Áõ°­   ÁúÀÇÀÀ´ä   ¾ð¾î ¸ðµ¨   machine reading comprehension   data augmentation   question answering   language model  
ÆÄÀÏ÷ºÎ PDF ´Ù¿î·Îµå