Á¤º¸°úÇÐȸ³í¹®Áö (Journal of KIISE)
Current Result Document :
ÇѱÛÁ¦¸ñ(Korean Title) |
CNN ±â¹Ý °ü°è ÃßÃâ ¸ðµ¨ÀÇ ¼º´É Çâ»óÀ» À§ÇÑ ´ÙÁß-¾îÀÇ ´Ü¾î ÀÓº£µù Àû¿ë |
¿µ¹®Á¦¸ñ(English Title) |
Multi-sense Word Embedding to Improve Performance of a CNN-based Relation Extraction Model |
ÀúÀÚ(Author) |
³²»óÇÏ
ÇѱâÁ¾
±èÀº°æ
±Ç¼º±¸
Á¤À¯¼º
Ãֱ⼱
Sangha Nam
Kijong Han
Eun-kyung Kim
Sunggoo Kwon
Yoosung Jung
Key-Sun Choi
|
¿ø¹®¼ö·Ïó(Citation) |
VOL 45 NO. 08 PP. 0816 ~ 0824 (2018. 08) |
Çѱ۳»¿ë (Korean Abstract) |
°ü°è ÃßÃâÀ̶õ ¹®Àå ³» µÎ °³Ã¼°£ÀÇ °ü°è¸¦ ºÐ·ùÇÏ´Â °ÍÀ¸·Î, ¸¹Àº ¿¬±¸µéÀÌ °ü°èÃßÃâ ¸ðµ¨À» ¼³°èÇÔ¿¡ ÀÖ¾î ¿ø°Ý ÁöµµÇнÀ ¹æ½ÄÀ» ÀÌ¿ëÇÏ°í ÀÖ´Ù. ±×¸®°í ÃÖ±Ù µö·¯´×ÀÇ ¹ßÀüÀ¸·Î ´Ù¾çÇÑ ¿¬±¸¿¡¼ °ü°è ÃßÃ⠸𵨠¼³°è ½Ã CNN ¶Ç´Â RNN µîÀÇ µö·¯´× ¸ðµ¨À» Àû¿ëÇÏ´Â °ÍÀÌ ÁÖ¿ä È帧À¸·Î ¹ßÀüÇÏ°í ÀÖ´Ù. ±×·¯³ª ±âÁ¸ ¿¬±¸µé¿¡¼´Â ¸ðµ¨ ÇнÀÀÇ ÀÔ·ÂÀ¸·Î »ç¿ëµÇ´Â ´Ü¾î ÀÓº£µùÀÇ µ¿ÇüÀÌÀÇ¾î ¹®Á¦¸¦ ÇØ°áÇÏÁö ¾Ê¾Ò´Ù´Â ´ÜÁ¡ÀÌ ÀÖ´Ù. µû¶ó¼ ¼·Î ´Ù¸¥ Àǹ̸¦ °¡Áø µ¿ÇüÀÌÀǾ ÇϳªÀÇ ÀÓº£µù °ªÀ¸·Î ¸ðµ¨ ÇнÀÀÌ ÁøÇàµÇ°í, ±×¿¡ µû¶ó ´Ü¾îÀÇ Àǹ̸¦ Á¤È®È÷ ÆľÇÇÏÁö ¸øÇÑ Ã¤ °ü°è ÃßÃâ ¸ðµ¨À» ÇнÀÇÑ´Ù°í º¼ ¼ö ÀÖ´Ù. º» ¿¬±¸¿¡¼´Â ´ÙÁß-¾îÀÇ ´Ü¾î ÀÓº£µùÀ» Àû¿ëÇÑ °ü°è ÃßÃâ ¸ðµ¨À» Á¦¾ÈÇÑ´Ù. ´ÙÁß-¾îÀÇ ´Ü¾î ÀÓº£µù ÇнÀÀ» À§ÇØ CoreNet Concept ±â¹ÝÀÇ ¾îÀÇ ÁßÀǼº ÇØ¼Ò ¸ðµâÀ» È°¿ëÇÏ¿´°í, °ü°èÃßÃâ ¸ðµ¨Àº ¹®Àå ³» ÁÖ¿ä Å°¿öµå¸¦ ½º½º·Î ÇнÀÇÏ´Â CNN ¸ðµ¨°ú PCNN ¸ðµ¨ 2°¡Áö¸¦ È°¿ëÇÏ¿´´Ù.
|
¿µ¹®³»¿ë (English Abstract) |
The relation extraction task is to classify a relation between two entities in an input sentence and is important in natural language processing and knowledge extraction. Many studies have designed a relation extraction model using a distant supervision method. Recently the deep-learning based relation extraction model became mainstream such as CNN or RNN. However, the existing studies do not solve the homograph problem of word embedding used as an input of the model. Therefore, model learning proceeds with a single embedding value of homogeneous terms having different meanings; that is, the relation extraction model is learned without grasping the meaning of a word accurately. In this paper, we propose a relation extraction model using multi-sense word embedding. In order to learn multi-sense word embedding, we used a word sense disambiguation module based on the CoreNet concept, and the relation extraction model used CNN and PCNN models to learn key words in sentences.
|
Å°¿öµå(Keyword) |
¿ø°Ý ÁöµµÇнÀ
°ü°èÃßÃâ
´Ü¾î ÀÓº£µù
ÇÕ¼º°ö ½Å°æ¸Á
distant supervision
relation extraction
word embedding
convolutional neural network
|
ÆÄÀÏ÷ºÎ |
PDF ´Ù¿î·Îµå
|