Á¤º¸°úÇÐȸ ÄÄÇ»ÆÃÀÇ ½ÇÁ¦ ³í¹®Áö (KIISE Transactions on Computing Practices)
Current Result Document :
ÇѱÛÁ¦¸ñ(Korean Title) |
µµ¸ÞÀÎ ÁúÀÇÀÀ´ä ½Ã½ºÅÛ |
¿µ¹®Á¦¸ñ(English Title) |
Domain Question Answering System |
ÀúÀÚ(Author) |
À±½ÂÇö
ÀÓÀºÈñ
±è´öÈ£
Seunghyun Yoon
Eunhee Rhim
Deokho Kim
|
¿ø¹®¼ö·Ïó(Citation) |
VOL 21 NO. 02 PP. 0144 ~ 0147 (2015. 02) |
Çѱ۳»¿ë (Korean Abstract) |
Question Answering (QA) ¼ºñ½º´Â »ç¿ëÀÚÀÇ ÀÚ¿¬¾î ÁúÀÇ¿¡ ´ëÀÀÇÏ´Â Á¤È®ÇÑ ´äº¯À» Á¦°øÇÏ´Â ½Ã½ºÅÛÀÌ´Ù. º» ¿¬±¸´Â ƯÁ¤ µµ¸ÞÀο¡ °ü·ÃÇÑ »ç¿ëÀÚµéÀÇ Áú¹®¿¡ ´ëÇØ QA ¼ºñ½º°¡ ÀÚµ¿À¸·Î ´ëÀÀÇÏ´Â ¹æ¹ý¿¡ °üÇÑ ¿¬±¸ÀÌ´Ù. À̸¦ ¼öÇàÇϱâ À§ÇÏ¿© »ç¿ëÀÚÀÇ ÀÚ¿¬¾î Áú¹®À» ÀÌÇØÇÏ°í, Á¤Çü µ¥ÀÌÅÍ ¹× ºñÁ¤Çü µ¥ÀÌÅͷκÎÅÍ »ç¿ëÀÚ Áú¹®¿¡ ÀûÇÕÇÑ ´äº¯À» µµÃâÇÏ¿© Á¦°øÇÏ´Â ¹æ¹ýÀ» Á¦½ÃÇÑ´Ù. ½ÇÇè °á°ú top 1accuracy 68%, top 5 accuracy 77% °á°ú¸¦ ¾ò¾ú´Ù. ¶ÇÇÑ º» ³í¹®Àº QA ½Ã½ºÅÛ ³»ºÎ ¸ðµâÀÌ Àüü accuracy¿¡ ¹ÌÄ¡´Â ¿µÇâ¿¡ ´ëÇؼµµ ±â¼úÇÏ¿´´Ù.
|
¿µ¹®³»¿ë (English Abstract) |
Question Answering (QA) services can provide exact answers to user questions written in natural language form. This research focuses on how to build a QA system for a specific domain area. Online and offline QA system architecture of targeted domain such as domain detection, question analysis, reasoning, information retrieval, filtering, answer extraction, re-ranking, and answer generation, as well as data preparation are presented herein. Test results with an official Frequently Asked Question (FAQ) set showed 68% accuracy of the top 1 and 77% accuracy of the top 5. The contribution of each part such as question analysis system, document search engine, knowledge graph engine and re-ranking module for achieving the final answer are also presented.
|
Å°¿öµå(Keyword) |
QA ½Ã½ºÅÛ
ÀÚ¿¬¾î ÁúÀÇ
question answering system
natural language query
|
ÆÄÀÏ÷ºÎ |
PDF ´Ù¿î·Îµå
|