Á¤º¸°úÇÐȸ³í¹®Áö (Journal of KIISE)
ÇѱÛÁ¦¸ñ(Korean Title) |
Ãß°¡ Á¤º¸¸¦ °í·ÁÇÑ »óÇ° ¸®ºä ¿ä¾à ±â¹ý |
¿µ¹®Á¦¸ñ(English Title) |
A Product Review Summarization Considering Additional Information |
ÀúÀÚ(Author) |
À±À翬
ÀÌÀÍÈÆ
ÀÌ»ó±¸
Jaeyeun Yoon
Ig-hoon Lee
Sang-goo Lee
|
¿ø¹®¼ö·Ïó(Citation) |
VOL 47 NO. 02 PP. 0180 ~ 0188 (2020. 02) |
Çѱ۳»¿ë (Korean Abstract) |
¹®¼ ¿ä¾àÀº ÁÖ¾îÁø ¹®¼·ÎºÎÅÍ Æ¯Á¤ »ç¿ëÀÚ³ª ÀÛ¾÷¿¡ ÀûÇÕÇÑ ÇüÅ·ΠÃà¾àÇÑ ¹®¼¸¦ »ý¼ºÇÏ´Â °ÍÀ» ÀǹÌÇÑ´Ù. ÀÎÅÍ³Ý »ç¿ëÀÌ Áõ°¡ÇÔ¿¡ µû¶ó, ÅؽºÆ®¸¦ Æ÷ÇÔÇÑ ´Ù¾çÇÑ µ¥ÀÌÅ͵éÀÌ Æø¹ßÀûÀ¸·Î Áõ°¡ÇÏ°í ÀÖ°í, ¹®¼ ¿ä¾à ±â¼úÀÌ Áö´Ï´Â °¡Ä¡´Â Áõ´ëµÇ°í ÀÖ´Ù. ÃֽŠµö·¯´× ±â¹Ý ¸ðµ¨µéÀÌ ÁÁÀº ¿ä¾à ¼º´ÉÀ» º¸ÀÌÁö¸¸, ÇнÀ µ¥ÀÌÅ͵éÀÇ ¾ç°ú Áú¿¡ µû¶ó ¼º´ÉÀÌ Á¿ìµÇ´Â ¹®Á¦Á¡ÀÌ ÀÖ´Ù. ¿¹¸¦ µé¾î, ¿Â¶óÀÎ ¼îÇθôÀÇ »óÇ° ¸®ºä µ¥ÀÌÅÍÀÇ °æ¿ì, ¿ÀÅ»ÀÚ¿Í ºñ¹®¹ýÀûÀÎ ÅؽºÆ® Ư¡ ¶§¹®¿¡ ±âÁ¸ ¸ðµ¨·Î ÁÁÀº ¿ä¾àÀ» »ý¼ºÇϱâ Èûµé´Ù. ÀÌ·¯ÇÑ ¹®Á¦¸¦ ÇØ°áÇÏ·Á°í ¿Â¶óÀÎ ¼îÇθô°ú Æ÷Å» ¼ºñ½º°¡ ¸¹Àº ³ë·ÂÀ» ÇÏ°í ÀÖ´Ù. µû¶ó¼ º» ¿¬±¸¿¡¼´Â ¸®ºä ÇнÀ µ¥ÀÌÅÍÀÇ ¾ç°ú ÁúÀÌ ¿¾ÇÇÏ´õ¶óµµ ÀûÀýÇÑ ¹®¼ ¿ä¾àÀ» »ý¼ºÇϱâ À§ÇØ, ÁÖ¾îÁø »óÇ° ¸®ºäÀÇ Ãß°¡ Á¤º¸¸¦ ÀÌ¿ëÇؼ »óÇ° ¸®ºä ¿ä¾àÀ» »ý¼ºÇÏ´Â ¸ðµ¨À» Á¦¾ÈÇÑ´Ù. ´õºÒ¾î, ½ÇÇèÀ» ÅëÇØ Á¦¾ÈÇÑ ±â¹ýÀÇ ¹®¼ ¿ä¾àÀÌ ±âÁ¸ ±â¹ýº¸´Ù ¿ä¾àÀÇ °ü·Ã¼º°ú °¡µ¶¼º Ãø¸é¿¡¼ Çâ»óµÇ¾úÀ½À» º¸¿´´Ù
|
¿µ¹®³»¿ë (English Abstract) |
Automatic document summarization is a task that generates the document in a suitable form from an existing document for a certain user or occasion. As use of the Internet increases, the various data including texts are exploding and the value of document summarization technology is growing. While the latest deep learning-based models show reliable performance in document summarization, the problem is that performance depends on the quantity and quality of the training data. For example, it is difficult to generate reliable summarization with existing models from the product review text of online shopping malls because of typing errors and grammatically wrong sentences. Online malls and portal web services are struggling to solve this problem. Thus, to generate an appropriate document summary in poor condition relative to quality and quantity of the product review learning data, this study proposes a model that generates product review summaries with additional information. We found through experiments that this model showed improved performances in terms of relevance and readability than the existing model for product review summaries.
|
Å°¿öµå(Keyword) |
¹®¼ ¿ä¾à
½ÃÄö½º-Åõ-½ÃÄö½º ¸ðµ¨
ÁÖÀÇ ÁýÁß ¸ÞÄ¿´ÏÁò
¸Þ¸ð¸® ³×Æ®¿öÅ©
Àΰø ½Å°æ¸Á
document summarization
sequence-to-sequence model
attention mechanism
memory network
artificial neural network
|
ÆÄÀÏ÷ºÎ |
PDF ´Ù¿î·Îµå
|