ÇѱÛÁ¦¸ñ(Korean Title) |
¿ÂÅç·ÎÁö ±¸Ãà ¹× ´Ü¾î ÀÇ¹Ì ÁßÀǼº Çؼҿ¡ÀÇ È°¿ë |
¿µ¹®Á¦¸ñ(English Title) |
Ontology Construction and Its Application to Disambiguate Word Senses |
ÀúÀÚ(Author) |
°½ÅÀç
|
¿ø¹®¼ö·Ïó(Citation) |
VOL 11-B NO. 04 PP. 0491 ~ 0500 (2004. 08) |
Çѱ۳»¿ë (Korean Abstract) |
º» ³í¹®Àº ±âÁ¸ÀÇ ´Ù¾çÇÑ ¾ð¾îÀÚ¿øµéÀ» ÀÌ¿ëÇÏ¿© ¿ÂÅç·ÎÁö¸¦ ±¸ÃàÇÏ°í, À̸¦ ´Ü¾îÀÇ¹Ì ÁßÀǼº Çؼҿ¡ È°¿ëÇÏ´Â ¹æ¹ýÀ» Á¦½ÃÇÏ°í ÀÖ´Ù. ¿ÂÅç·ÎÁö¸¦ ½Ç¿ëÀûÀ¸·Î ±¸ÃàÇϱâ À§Çؼ´Â °¡µµÄ«¿Í ½Ã¼Ò·¯½ºÀÇ °³³ä ü°è¿¡ °Ý °ü°è¿Í ±âŸ Àǹ̰ü°è¿Í °°Àº ´Ù¸¥ Àǹ̰ü°è¸¦ Ãß°¡ÇÏ¿© È®ÀåÇÏ´Â ¹æ¹ýÀ» ¼±ÅÃÇÏ¿´´Ù. ±¸ÃàµÈ ¿ÂÅç·ÎÁö¸¦ ´Ü¾î ÀÇ¹Ì ÁßÀǼº Çؼҿ¡ È°¿ëÇϱâ À§Çؼ´Â, °áÇÕ°¡ Á¤º¸¸¦ Æ÷ÇÔÇÏ°í ÀÖ´Â ÀüÀÚ»çÀüÀ» ¸ÕÀú ÀÌ¿ëÇÏ¿© ´Ü¾îÀÇ Àǹ̸¦ °áÁ¤ÇÏ°í, °áÁ¤ÇÏÁö ¸øÇÑ ´Ü¾îÀÇ Àǹ̴ ¿ÂÅç·ÎÁö¸¦ ÀÌ¿ëÇÏ¿© °áÁ¤ÇÏ´Â ÀýÂ÷¸¦ °ÅÄ£´Ù. À̸¦ À§ÇØ ¿ÂÅç·ÎÁö ³» °³³äµé°£ÀÇ »óÈ£Á¤º¸°¡ ¸»¹¶Ä¡ÀÇ Åë°è Á¤º¸¿¡ ±Ù°ÅÇÏ¿© °è»êµÇ´Âµ¥, À̸¦ °¡ÁßÄ¡·Î °£ÁÖÇÏ¸é ¿ÂÅç·ÎÁö´Â °¡ÁßÄ¡ ±×·¡ÇÁ·Î »ý°¢ÇÒ ¼ö ÀÖÀ¸¹Ç·Î, °³³ä°£ °æ·Î¸¦ ÅëÇÏ¿© °³³ä°£ ¿¬°üµµ¸¦ ¾Ë¾Æ º¼ ¼ö ÀÖ´Ù. ½ÇÁ¦ ±â°è¹ø¿ª ½Ã½ºÅÛ¿¡¼ º» ¹æ¹ýÀº ¿ÂÅç·ÎÁö¸¦ »ç¿ëÇÏÁö ¾ÊÀº ¹æ¹ýº¸´Ù 9%ÀÇ ¼º´É Çâ»óÀ» °¡Á®¿À´Â °á°ú¸¦ ¾òÀ» ¼ö ÀÖ¾ú´Ù. |
¿µ¹®³»¿ë (English Abstract) |
This paper presents an ontology construction method using various computational language resources, and an ontology-based word sense disambiguation method. In order to acquire a reasonably practical ontology, the Kadokawa thesaurus is extended by inserting additional semantic relations into its hierarchy, which are classified as case relations and other semantic relations. To apply the ontology to disambiguate word senses, we apply the previously-secured dictionary information to select the correct senses of some ambiguous words with high precision, and then use the ontology to disambiguate the remaining ambiguous words. The mutual information between concepts in the ontology was calculated before using the ontology as knowledge for disambiguating word senses. If mutual information is regarded as a weight between ontology concepts, the ontology can be treated as a graph with weighted edges, and then we locate the weighted path from one concept to the other concept. In our practical machine translation system, our word sense disambiguation method achieved a 9% improvement over methods which do not use ontology for Korean translation., , |
Å°¿öµå(Keyword) |
¿ÂÅç·ÎÁö
Ontology
´Ü¾îÀÇ¹Ì ÁßÀǼº ÇؼÒ
Word Sense Disambiguation
¸»¹¶Ä¡ ºÐ¼®
Corpus Analysis
±â°è¹ø¿ª
Machine Translation
¼¼Á¾ ÀüÀÚ»çÀü
Sejong Electronic Lexicon of Korean
|
ÆÄÀÏ÷ºÎ |
PDF ´Ù¿î·Îµå
|