Àüü
ÀüÀÚ/Àü±â
Åë½Å
ÄÄÇ»ÅÍ
·Î±×ÀÎ
ȸ¿ø°¡ÀÔ
About Us
ÀÌ¿ë¾È³»
¿¬±¸¹®Çå
±¹³» ³í¹®Áö
¿µ¹® ³í¹®Áö
±¹³» ÇÐȸÁö
Çмú´ëȸ ÇÁ·Î½Ãµù
±¹³» ÇÐÀ§ ³í¹®
³í¹®Á¤º¸
¹é¼
±³À°Á¤º¸
¿¬±¸ ù°ÉÀ½
ÇаúÁ¤º¸
°ÀÇÁ¤º¸
µ¿¿µ»óÁ¤º¸
E-Learning
¿Â¶óÀÎ Àú³Î
½ÉÈÁ¤º¸
¿¬±¸ ¹× ±â¼úµ¿Çâ
Áֿ俬±¸ÅäÇÈ
ÁÖ¿ä°úÁ¦ ¹× ±â°ü
Çؿܱâ°ü °ü·ÃÀÚ·á
¹ÙÀÌ¿À Á¤º¸±â¼ú
ÁÖ¿ä Archive Site
Æ÷Ä¿½ºiN
¿¬±¸ÀÚ Á¤º¸
¶óÀÌ¡½ºÅ¸
ÆÄ¿öiNÅͺä
¼¼ÁßÇÑ
¿¬±¸ÀÚ·á
¹®ÀÚ DB
¿ë¾î»çÀü
¾Ë¸²¸¶´ç
ºÎ½Ç ÇмúÈ°µ¿ ¿¹¹æ
³í¹®¸ðÁý
´ëȸ¾È³»
What's New
¿¬±¸ºñÁ¤º¸
±¸ÀÎÁ¤º¸
°øÁö»çÇ×
CSERIC ±¤Àå
Post-Conference
¿¬±¸ÀÚ Ä«Æä
ÀÚÀ¯°Ô½ÃÆÇ
Q&A
´Ý±â
»çÀÌÆ®¸Ê
¿¬±¸¹®Çå
±¹³» ³í¹®Áö
¿µ¹® ³í¹®Áö
±¹³» ÇÐȸÁö
Çмú´ëȸ ÇÁ·Î½Ãµù
±¹³» ÇÐÀ§ ³í¹®
³í¹®Á¤º¸
¹é¼
±³À°Á¤º¸
¿¬±¸ ù°ÉÀ½
ÇаúÁ¤º¸
°ÀÇÁ¤º¸
µ¿¿µ»óÁ¤º¸
E-Learning
¿Â¶óÀÎ Àú³Î
½ÉÈÁ¤º¸
¿¬±¸ ¹× ±â¼úµ¿Çâ
Áֿ俬±¸ÅäÇÈ
ÁÖ¿ä°úÁ¦ ¹× ±â°ü
Çؿܱâ°ü °ü·ÃÀÚ·á
¹ÙÀÌ¿À Á¤º¸±â¼ú
ÁÖ¿ä Archive Site
ÄÄÇ»ÅÍiN
¿¬±¸ÀÚ Á¤º¸
¿¬±¸ÀÚ·á
¹®ÀÚ DB
Ȧ·Î±×·¥ DB
¿ë¾î»çÀü
¾Ë¸²¸¶´ç
ºÎ½Ç ÇмúÈ°µ¿ ¿¹¹æ
³í¹®¸ðÁý
´ëȸ¾È³»
What's New
¿¬±¸ºñ Á¤º¸
±¸ÀÎÁ¤º¸
°øÁö»çÇ×
IT Daily
CSERIC ±¤Àå
Post-Conference
¿¬±¸ÀÚ Ä«Æä
ÀÚÀ¯°Ô½ÃÆÇ
Q&A
¼ºñ½º ¹Ù·Î°¡±â
¼³¹®Á¶»ç
¿¬±¸À±¸®
°ü·Ã±â°ü
Please wait....
¿¬±¸¹®Çå
±¹³» ³í¹®Áö
¿µ¹® ³í¹®Áö
±¹³» ÇÐȸÁö
Çмú´ëȸ ÇÁ·Î½Ãµù
±¹³» ÇÐÀ§ ³í¹®
³í¹®Á¤º¸
¹é¼
±¹³» ³í¹®Áö
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 :
1
/ 18
´ÙÀ½°Ç
ÇѱÛÁ¦¸ñ(Korean Title)
°³Ã¼¸í »ç½Ç ÆǺ°À» ÅëÇÑ ±â°è ¿ä¾àÀÇ »ç½Ç ºÒÀÏÄ¡ ÇؼÒ
¿µ¹®Á¦¸ñ(English Title)
Solving Factual Inconsistency in Abstractive Summarization using Named Entity Fact Discrimination
ÀúÀÚ(Author)
½ÅÁ¤¿Ï
³ëÀ±¼®
¼ÛÇöÁ¦
¹Ú¼¼¿µ
Jeongwan Shin
Yunseok Noh
Hyun-Je Song
Seyoung Park
¿ø¹®¼ö·Ïó(Citation)
VOL 49 NO. 03 PP. 0231 ~ 0240 (2022. 03)
Çѱ۳»¿ë
(Korean Abstract)
±â°è ¿ä¾àÀÇ »ç½Ç ºÒÀÏÄ¡ ¹®Á¦¶õ ¿ä¾à ¸ðµ¨ÀÌ »ý¼ºÇÑ ¿ä¾à¹®ÀÌ ¿ø¹®°ú »ç½ÇÀÌ ÀÏÄ¡ÇÏÁö ¾Ê´Â ¹®Á¦´Ù. »ç½Ç ºÒÀÏÄ¡´Â °³Ã¼¸í¿¡¼ ÁÖ·Î ¹ß»ýÇϹǷΠ±âÁ¸ ¿¬±¸µéÀº ¿ä¾à¹®ÀÇ À߸øµÈ °³Ã¼¸íÀ» ±³Á¤ÇÏ¿© »ç½ÇÀû ºÒÀÏÄ¡¸¦ ÇØ°áÇÏ¿´´Ù. ÇÏÁö¸¸, ¸í½ÃÀûÀÎ °³Ã¼¸í »ç½Ç ºÒÀÏÄ¡ ÆǺ° ¾øÀÌ ¸ðµç °³Ã¼¸íÀ» ¼øÂ÷ÀûÀ¸·Î ±³Á¤Çϰųª ¸ðµÎ ¸¶½ºÅ·ÇÏ¿© ±³Á¤À» ½ÃµµÇÏ¿´´Ù. ¸ðµç °³Ã¼¸íÀ» ±³Á¤ÇÏ´Â ¿¬±¸´Â ¿ø¹®°ú ÀÏÄ¡ÇÏ´Â °³Ã¼¸íµµ ±³Á¤À» ½ÃµµÇÏ´Â ¹®Á¦Á¡°ú ¸¶½ºÅ·µÇ¾î »ç½Ç Á¤º¸ÀÓ¿¡µµ ºÒ±¸ÇÏ°í Á¤º¸¸¦ ¼Õ½Ç½ÃÅ°´Â ¹®Á¦°¡ ¹ß»ýÇÑ´Ù. º» ³í¹®¿¡¼´Â ±âÁ¸ ¿¬±¸µéÀÇ ´ÜÁ¡À» ÇØ°áÇϱâ À§ÇØ °³Ã¼¸í »ç½Ç ¿©ºÎ¸¦ ÆǺ°ÇÑ µÚ »ç½Ç ºÒÀÏÄ¡ °³Ã¼¸í¿¡ ´ëÇؼ¸¸ ±³Á¤À» ÇÏ´Â ¹æ¹ýÀ» Á¦¾ÈÇÑ´Ù. À̸¦ ÅëÇØ »ç½Ç ºÒÀÏÄ¡ °³Ã¼¸íÀÌ ¹ß»ý½ÃÅ°´Â ¿À·ù¸¦ ¹æÁöÇÒ ¼ö ÀÖÀ¸¸ç, ¹Ý´ë·Î »ç½Ç ÀÏÄ¡ °³Ã¼¸í¿¡ ´ëÇÑ Á¤º¸¸¦ ÃÖ´ëÇÑ È°¿ëÇÒ ¼ö ÀÖ´Ù. ½ÇÇèÀ» ÅëÇØ Á¦¾ÈÇÑ ¹æ¹ýÀÌ ±âÁ¸ ¿¬±¸µéº¸´Ù ¿ä¾à¹®ÀÇ »ç½Ç ºÒÀÏÄ¡¸¦ Àß ÇؼÒÇÔÀ» º¸¿´´Ù.
¿µ¹®³»¿ë
(English Abstract)
Factual inconsistency in abstractive summarization is a problem that a generated summary can be factually inconsistent with a source text. Previous studies adopted a span selection that replaced entities in the generated summary with entities in the source text because most inconsistencies are related to incorrect entities. These studies assumed that all entities in the generated summary were inconsistent and tried to replace all entities with other entities. However, this was problematic because some consistent entities could be replaced and masked, so information on consistent entities was lost. This paper proposes a method that sequentially executes a fact discriminator and a fact corrector to solve this problem. The fact discriminator determines the inconsistent entities, and the fact corrector replaces only the inconsistent entities. Since the fact corrector corrects only the inconsistent entities, it utilizes the consistent entities. Experiments show that the proposed method boosts the factual consistency of system-generated summaries and outperforms the baselines in terms of both automatic metrics and human evaluation.
Å°¿öµå(Keyword)
»ç½Ç ºÒÀÏÄ¡ ÇؼÒ
°³Ã¼¸í »ç½Ç ÆǺ°
Ãß»ó ¿ä¾à
°³Ã¼¸í ¹®¸Æ Ç¥Çö
factual inconsistency
named entity fact discrimination
abstractive summarization
contextual entity representation
ÆÄÀÏ÷ºÎ
PDF ´Ù¿î·Îµå
¸ñ·Ï
Copyright(c)
Computer Science Engineering Research Information Center
. All rights reserved.