• 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¸Ã³¸®ÇÐȸ ³í¹®Áö > Á¤º¸Ã³¸®ÇÐȸ ³í¹®Áö ¼ÒÇÁÆ®¿þ¾î ¹× µ¥ÀÌÅÍ °øÇÐ

Á¤º¸Ã³¸®ÇÐȸ ³í¹®Áö ¼ÒÇÁÆ®¿þ¾î ¹× µ¥ÀÌÅÍ °øÇÐ

Current Result Document : 1 / 6   ´ÙÀ½°Ç ´ÙÀ½°Ç

ÇѱÛÁ¦¸ñ(Korean Title) ·£´ý Æ÷·¹½ºÆ®¸¦ ÀÌ¿ëÇÑ Çѱ¹¾î »óÈ£ÂüÁ¶ ÇØ°á
¿µ¹®Á¦¸ñ(English Title) Coreference Resolution for Korean Using Random Forests
ÀúÀÚ(Author) Á¤¼®¿ø   ÃָͽĠ  ±èÇмö   Seok-Won Jeong   MaengSik Choi   HarkSoo Kim  
¿ø¹®¼ö·Ïó(Citation) VOL 05 NO. 11 PP. 0535 ~ 0540 (2016. 11)
Çѱ۳»¿ë
(Korean Abstract)
»óÈ£ÂüÁ¶ ÇØ°áÀº ¹®¼­ ³»¿¡ Á¸ÀçÇÏ´Â ¸à¼ÇµéÀ» ½Äº°ÇÏ°í, ÂüÁ¶ÇÏ´Â ¸à¼Ç³¢¸® ±ºÁýÈ­ÇÏ´Â °ÍÀ¸·Î Á¤º¸ ÃßÃâ, »ç°Ç ÃßÀû, ÁúÀÇÀÀ´ä°ú °°Àº ÀÚ¿¬¾îó¸® ÀÀ¿ë¿¡ ÇʼöÀûÀÎ °úÁ¤ÀÌ´Ù. ÃÖ±Ù¿¡´Â ±â°èÇнÀ¿¡ ±â¹ÝÇÑ ´Ù¾çÇÑ »óÈ£ÂüÁ¶ ÇØ°á ¸ðµ¨µéÀÌ Á¦¾ÈµÇ¾úÀ¸¸ç, Àß ¾Ë·ÁÁø °Íó·³ ÀÌ·± ±â°èÇнÀ ±â¹Ý ¸ðµ¨µéÀº »óÈ£ÂüÁ¶ ¸à¼Ç ű׵éÀÌ ¼öµ¿À¸·Î ºÎÂøµÈ ´ë·®ÀÇ ÇнÀ µ¥ÀÌÅ͸¦ ÇÊ¿ä·Î ÇÑ´Ù. ±×·¯³ª Çѱ¹¾î¿¡¼­´Â ±â°èÇнÀ ¸ðµ¨µéÀ» ÇнÀÇÒ °¡¿ëÇÑ °ø°³ µ¥ÀÌÅÍ°¡ Á¸ÀçÇÏÁö ¾Ê´Â´Ù. ±×·¯¹Ç·Î º» ³í¹®¿¡¼­´Â ´Ù¸¥ ±â°èÇнÀ ¸ðµ¨º¸´Ù ÀûÀº ÇнÀ µ¥ÀÌÅ͸¦ ÇÊ¿ä·Î ÇÏ´Â È¿À²ÀûÀÎ »óÈ£ÂüÁ¶ ÇØ°á ¸ðµ¨À» Á¦¾ÈÇÑ´Ù. Á¦¾È ¸ðµ¨Àº ½Ãºê-°¡À̵å ÀÚÁú ±â¹ÝÀÇ ·£´ý Æ÷·¹½ºÆ®¸¦ »ç¿ëÇÏ¿© »óÈ£ÂüÁ¶ÇÏ´Â ¸à¼ÇµéÀ» ±¸ºÐÇÑ´Ù. ¾ß±¸ ´º½º ±â»ç¸¦ ÀÌ¿ëÇÑ ½ÇÇè¿¡¼­ Á¦¾È ¸ðµ¨Àº ´Ù¸¥ ±â°èÇнÀ ¸ðµ¨º¸´Ù ³ôÀº 0.6678ÀÇ CoNLL F1-Á¡¼ö¸¦ º¸¿´´Ù.
¿µ¹®³»¿ë
(English Abstract)
Coreference resolution is to identify mentions in documents and is to group co-referred mentions in the documents. It is an essential step for natural language processing applications such as information extraction, event tracking, and question-answering. Recently, various coreference resolution models based on ML (machine learning) have been proposed, As well-known, these ML-based models need large training data that are manually annotated with coreferred mention tags. Unfortunately, we cannot find usable open data for learning ML-based models in Korean. Therefore, we propose an efficient coreference resolution model that needs less training data than other ML-based models. The proposed model identifies co-referred mentions using random forests based on sieve-guided features. In the experiments with baseball news articles, the proposed model showed a better CoNLL F1-score of 0.6678 than other ML-based models.
Å°¿öµå(Keyword) »óÈ£ÂüÁ¶ ÇØ°á   ·£´ý Æ÷·¹½ºÆ®   ½Ãºê-°¡À̵å ÀÚÁú   Coreference Resolution   Random Forest   Sieve-Guided Features  
ÆÄÀÏ÷ºÎ PDF ´Ù¿î·Îµå