• 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¸°úÇÐȸ ³í¹®Áö > Á¤º¸°úÇÐȸ³í¹®Áö (Journal of KIISE)

Á¤º¸°úÇÐȸ³í¹®Áö (Journal of KIISE)

Current Result Document : 9 / 41 ÀÌÀü°Ç ÀÌÀü°Ç   ´ÙÀ½°Ç ´ÙÀ½°Ç

ÇѱÛÁ¦¸ñ(Korean Title) L2 ÇнÀÀÚ¸¦ À§ÇÑ ÁÖÀÇ ±âÁ¦ ±â¹ý ±â¹ÝÀÇ ¹®¹ý ¿À·ù °¨Áö
¿µ¹®Á¦¸ñ(English Title) Grammatical Error Detection for L2 Learners Based on Attention Mechanism
ÀúÀÚ(Author) ¹ÚÂùÈñ   ¹ÚÁø¿í   Á¶¹Î¼ö   ¹Ú»óÇö   Chanhee Park   Jinuk Park   Minsoo Cho   Sanghyun Park  
¿ø¹®¼ö·Ïó(Citation) VOL 46 NO. 06 PP. 0554 ~ 0562 (2019. 06)
Çѱ۳»¿ë
(Korean Abstract)
¹®¹ý ¿À·ù °¨Áö´Â ÁÖ¾îÁø ¹®Àå¿¡¼­ ¹ß»ýÇÑ ¹®¹ýÀûÀÎ ¿À·ùÀÇ Á¸Àç¿Í ±× À§Ä¡¸¦ ¹ß°ßÇÏ´Â ÀÛ¾÷À¸·Î, »õ·Î¿î ¾ð¾î¸¦ ¹è¿ì´Â L2 ÇнÀÀÚÀÇ ¾ð¾î ÇнÀ°ú Æò°¡¿¡ À¯¿ëÇÏ°Ô È°¿ëµÉ ¼ö ÀÖ´Ù. ±âÁ¸¿¡´Â ¹®¹ý ¿À·ù ±³Á¤À» À§ÇÑ ½Ã½ºÅÛÀÌ È°¹ßÈ÷ ¿¬±¸µÇ°í ÀÖÀ¸³ª, ÇнÀ ¸»¹¶Ä¡ÀÇ ºÎÁ·°ú Á¦ÇÑµÈ ¿À·ù À¯Çü ±³Á¤°ú °°Àº ÇÑ°è°¡ Á¸ÀçÇÑ´Ù. µû¶ó¼­ º» ¿¬±¸¿¡¼­´Â ¼øÂ÷ ·¹ÀÌºí¸µ ¹®Á¦¸¦ ÅëÇØ ¿À·ùÀÇ À¯ÇüÀÌ »çÀü¿¡ Á¤ÇØÁöÁö ¾ÊÀº ÀϹÝÈ­µÈ ¹®¹ý ¿À·ù °¨Áö¸¦ À§ÇÑ ¸ðÇüÀ» Á¦¾ÈÇÑ´Ù. ´Ü¾î¿Í ¹®ÀÚ¸¦ µ¿ÀûÀ¸·Î È¥ÇÕÇÑ Ç¥»óÀ» »ç¿ëÇÏ¿© L2 ÇнÀÀÚÀÇ ¾²±â¿¡¼­ ³ªÅ¸³ª´Â ¿¹Ãø ºÒ°¡´ÉÇÑ ´Ü¾î¸¦ ´Ù·ç°í, ¸ÖƼ ŽºÅ© ÇнÀÀ» ÅëÇØ ºÒ±ÕÇüÇÑ µ¥ÀÌÅÍÀÇ ÇнÀ °úÁ¤¿¡¼­ ¹ß»ýÇÒ ¼ö ÀÖ´Â ÆíÇ⼺À» ¹æÁöÇÏ¿´´Ù. ¶ÇÇÑ, ÁÖÀÇ ±âÁ¦ ±â¹ýÀ» Àû¿ëÇÏ¿© ¿À·ù ¿¹Ãø¿¡ ÀÖ¾î ÆÇ´ÜÀÇ ±Ù°Å°¡ µÉ ¼ö ÀÖ´Â ´Ü¾î¿¡ ÁýÁßÇØ È¿À²ÀûÀ¸·Î ¿À·ù¸¦ ¿¹ÃøÇÏ¿´´Ù. Á¦¾ÈÇÏ´Â ¸ðÇüÀÇ °ËÁõÀ» À§ÇØ 3°³ÀÇ Æò°¡ µ¥ÀÌÅ͸¦ »ç¿ëÇÏ¿´À¸¸ç °¢ ±¸¼º¿ä¼Ò¸¦ Á¦°ÅÇØ º½À¸·Î½á ¸ðÇüÀÇ È¿¿ë¼ºÀ» °ËÁõÇÏ¿´´Ù.
¿µ¹®³»¿ë
(English Abstract)
Grammar Error Detection refers to the work of discovering the presence and location of grammatical errors in a given sentence, and is considered to be useful for L2 learners to learn and evaluate the language. Systems for grammatical error correction have been actively studied, but there still exist limitations such as lack of training corpus and limited error type correction. Therefore, this paper proposes a model for generalized grammatical error detection through the sequence labeling problem which does not require the determination of error type. The proposed model dynamically decides character-level and word-level representation to deal with unexpected words in L2 learners' writing. Also, based on the proposed model the bias which can occur during the learning process with imbalanced data can be avoided through multi-task learning. Additionally, attention mechanism is applied to efficiently predict errors by concentrating on words for judging errors. To validate the proposed model, three test data were used and the effectiveness of the model was verified through the ablation experiment.
Å°¿öµå(Keyword) ÀÚ¿¬¾î 󸮠  ¹®¹ý ¿À·ù °¨Áö   ¼øÂ÷ ·¹ÀÌºí¸µ   ´Ü¾î Ç¥»ó   ¸ÖƼ ŽºÅ© ÇнÀ   ÁÖÀÇ ±âÁ¦ ±â¹ý   natural language processing   grammar error detection   sequence labeling   word representation   multi-task learning   attention mechanism  
ÆÄÀÏ÷ºÎ PDF ´Ù¿î·Îµå