Á¤º¸°úÇÐȸ³í¹®Áö (Journal of KIISE)
Current Result Document :
ÇѱÛÁ¦¸ñ(Korean Title) |
µà¾ó Æ÷ÀÎÅÍ ³×Æ®¿öÅ©¸¦ »ç¿ëÇÑ ´ÙÁß °³Ã¼ °£ÀÇ °ü°è ÃßÃâ |
¿µ¹®Á¦¸ñ(English Title) |
Relation Extraction among Multiple Entities using Dual-Pointer Network |
ÀúÀÚ(Author) |
¹Ú¼º½Ä
±èÇмö
Seongsik Park
Harksoo Kim
|
¿ø¹®¼ö·Ïó(Citation) |
VOL 46 NO. 11 PP. 1186 ~ 1192 (2019. 11) |
Çѱ۳»¿ë (Korean Abstract) |
Á¤º¸ ÃßÃâÀº ºñÁ¤Çü ÅؽºÆ®·ÎºÎÅÍ Á¤Çü µ¥ÀÌÅ͸¦ ÀÚµ¿À¸·Î ÃßÃâÇÏ´Â ±â¼úÀÌ´Ù. ÃÖ±Ù ´ë¿ë·®ÀÇ ºñÁ¤Çü ÅؽºÆ®°¡ ±Þ°ÝÈ÷ Áõ°¡ÇÔ¿¡ µû¶ó Á¤º¸ ÃßÃâ¿¡ ´ëÇÑ ¸¹Àº ¿¬±¸°¡ ÀÌ·ç¾îÁö°í ÀÖ´Ù. Á¤º¸ ÃßÃâÀº Å©°Ô °³Ã¼ ¿¬°á°ú °ü°è ÃßÃ⠵Π°¡Áö ±â¼ú·Î ±¸¼ºµÇ¸ç °ü°è ÃßÃâÀº Á¤º¸ ÃßÃâ¿¡ ÀÖ¾î °¡Àå ÇÙ½ÉÀÌ µÇ´Â ±â¼úÀÌ´Ù. ÃÖ±Ù±îÁö ´ëºÎºÐÀÇ °ü°è ÃßÃâ ¿¬±¸´Â ¹®Àå¿¡ ÇÑ ½ÖÀÇ °³Ã¼¸¸ Á¸ÀçÇÑ´Ù°í °¡Á¤ÇÏ¸ç ´ÜÀÏ °³Ã¼ ½Ö°£ÀÇ °ü°è¸¦ ÃßÃâÇϴµ¥ ÃÊÁ¡ÀÌ ¸ÂÃçÁ® ÀÖ´Ù. ±×·¯³ª ½ÇÁ¦·Î ¹®Àå¿¡´Â ÇÑ ½Ö ÀÌ»óÀÇ °³Ã¼°¡ Á¸ÀçÇÒ ¼ö ÀÖ´Ù. º» ³í¹®Àº ÁÖ¾îÁø ¹®Àå¿¡¼ °¡´ÉÇÑ ¸ðµç °³Ã¼ ½Ö °£ÀÇ °ü°è¸¦ ÃßÃâÇÒ ¼ö ÀÖ´Â µà¾ó Æ÷ÀÎÅÍ ³×Æ®¿öÅ© ±â¹Ý °ü°è ÃßÃâ ¸ðµ¨À» Á¦¾ÈÇÑ´Ù. Á¦¾È ¸ðµ¨Àº °ü°è ÃßÃâ¿¡ ´ëÇ¥ÀûÀ¸·Î »ç¿ëµÇ´Â ¿µ¹® µ¥ÀÌÅÍ ¼ÂÀÎ ACE-2005 µ¥ÀÌÅÍ ¼Â°ú NYT µ¥ÀÌÅÍ ¼ÂÀ¸·Î ½ÇÇèÀ» ÁøÇàÇßÀ¸¸ç, ACE-2005¿¡¼ F1 Á¡¼ö 0.8050, NYT µ¥ÀÌÅÍ ¼Â¿¡¼ F1 Á¡¼ö 0.7834·Î °¡Àå ³ôÀº ¼º´ÉÀ» º¸¿´´Ù.
|
¿µ¹®³»¿ë (English Abstract) |
Information Extraction is the process of automatically extracting structured information from unstructured machine-readable texts. The rapid increase in large-scale unstructured texts in recent years has led to many studies investigating information extraction. Information extraction consists of two sub-tasks: an entity linking task and a relation extraction task. Most previous studies examining relation extraction have assumed that a single sentence contains a single entity pair mention. They have also focused on extracting a single entity pair (i.e., Subject-Relation-Object triple) per sentence. However, sentences can also contain multiple entity pairs. Therefore, in this paper, we propose a Dual-pointer network model that can entirely extract all possible entity pairs from a given text. In relation extraction experiments with two kinds of representative English datasets, NYT and ACE-2005, the proposed model achieved state-of-the-art performances with an F1-score of 0.8050 in ACE-2005 and an F1-score of 0.7834 in NYT.
|
Å°¿öµå(Keyword) |
°ü°è ÃßÃâ
Áö½Äº£À̽º
Á¤º¸ ÃßÃâ
´ÙÁß °³Ã¼ °£ÀÇ °ü°è ÃßÃâ
µà¾ó Æ÷ÀÎÅÍ ³×Æ®¿öÅ©
relation extraction
knowledge base
information extraction
relation extraction among multiple entities
dual-pointer network
|
ÆÄÀÏ÷ºÎ |
PDF ´Ù¿î·Îµå
|