• Àüü
  • ÀüÀÚ/Àü±â
  • Åë½Å
  • ÄÄÇ»ÅÍ
´Ý±â

»çÀÌÆ®¸Ê

Loading..

Please wait....

±¹³» ³í¹®Áö

Ȩ Ȩ > ¿¬±¸¹®Çå > ±¹³» ³í¹®Áö > Çѱ¹ÀÎÅͳÝÁ¤º¸ÇÐȸ ³í¹®Áö

Çѱ¹ÀÎÅͳÝÁ¤º¸ÇÐȸ ³í¹®Áö

Current Result Document :

ÇѱÛÁ¦¸ñ(Korean Title) ÀÚ±â Áöµµ ÇнÀ ±â¹ÝÀÇ ¾ð¾î ¸ðµ¨À» È°¿ëÇÑ ´ÙÃâó Á¤º¸ ÅëÇÕ ÇÁ·¹ÀÓ¿öÅ©
¿µ¹®Á¦¸ñ(English Title) Multi-source information integration framework using self-supervised learning-based language model
ÀúÀÚ(Author) ±èÇѹΠ  ÀÌÁ¤ºó   ¹Ú±Ôµ¿   ¼Õ¹Ì¾Ö   Hanmin Kim   Jeongbin Lee   Gyudong Park   Mye Sohn  
¿ø¹®¼ö·Ïó(Citation) VOL 22 NO. 06 PP. 0141 ~ 0150 (2021. 12)
Çѱ۳»¿ë
(Korean Abstract)
ÀΰøÁö´É(Artificial Intelligence) ±â¼úÀ» È°¿ëÇÏ¿© ÀΰøÁö´É ±â¹ÝÀÇ ÀüÀï (AI-enabled warfare)°¡ ¹Ì·¡ÀüÀÇ ÇÙ½ÉÀÌ µÉ °ÍÀ¸·Î ¿¹»óÇÑ´Ù. ÀÚ¿¬¾î ó¸® ±â¼úÀº ÀÌ·¯ÇÑ AI ±â¼úÀÇ ÇÙ½É ±â¼ú·Î ÁöÈÖ°ü ¹× Âü¸ðµéÀÌ ÀÚ¿¬¾î·Î ÀÛ¼ºµÈ º¸°í¼­, Á¤º¸ ¹× øº¸¸¦ ÀÏÀÏÀÌ ¿­¾î È®ÀÎÇÏ´Â ºÎ´ãÀ» ÁÙÀ̴µ¥ ȹ±âÀûÀ¸·Î ±â¿©ÇÒ ¼ö ÀÖ´Ù. º» ³í¹®¿¡¼­´Â ÁöÈÖ°ü ¹× Âü¸ðÀÇ Á¤º¸ ó¸® ºÎ´ãÀ» ÁÙÀÌ°í ½Å¼ÓÇÑ ÁöÈÖ°á½ÉÀ» Áö¿øÇϱâ À§ÇØ ¾ð¾î ¸ðµ¨ ±â¹ÝÀÇ ´ÙÃâó Á¤º¸ ÅëÇÕ (Language model-based Multi-source Information Integration, LAMII) ÇÁ·¹ÀÓ¿öÅ©¸¦ Á¦¾ÈÇÑ´Ù. Á¦¾ÈµÈ LAMII ÇÁ·¹ÀÓ¿öÅ©´Â ÀÚ±âÁöµµ ÇнÀ¹ýÀ» È°¿ëÇÑ ¾ð¾î ¸ðµ¨¿¡ ±â¹ÝÇÑ Ç¥ÇöÇнÀ°ú ¿ÀÅäÀÎÄÚ´õ¸¦ È°¿ëÇÑ ¹®¼­ ÅëÇÕÀÇ ÇÙ½É ´Ü°è·Î ±¸¼ºµÇ¾î ÀÖ´Ù. ù ¹ø° ´Ü°è¿¡¼­´Â, ÀÚ±âÁöµµ ÇнÀ ±â¹ýÀ» È°¿ëÇÏ¿© ±¸Á¶ÀûÀ¸·Î ÀÌÁúÀûÀÎ µÎ ¹®Àå°£ÀÇ À¯»ç °ü°è¸¦ ½Äº°ÇÒ ¼ö Àִ ǥÇöÇнÀÀ» ¼öÇàÇÑ´Ù. µÎ ¹ø° ´Ü°è¿¡¼­´Â, ¾Õ¼­ ÇнÀµÈ ¸ðµ¨À» È°¿ëÇÏ¿© ´ÙÃâó·ÎºÎÅÍ ºñ½ÁÇÑ ³»¿ë ȤÀº ÅäÇÈÀ» ÇÔ¾çÇÏ´Â ¹®¼­µéÀ» ¹ß°ßÇÏ°í À̵éÀ» ÅëÇÕÇÑ´Ù. ÀÌ ¶§, Áߺ¹µÇ´Â ¹®ÀåÀ» Á¦°ÅÇϱâ À§ÇØ ¿ÀÅäÀÎÄÚ´õ¸¦ È°¿ëÇÏ¿© ¹®ÀåÀÇ Áߺ¹¼ºÀ» ÃøÁ¤ÇÑ´Ù. º» ³í¹®ÀÇ ¿ì¼ö¼ºÀ» ÀÔÁõÇϱâ À§ÇØ, ¿ì¸®´Â ¾ð¾î¸ðµ¨µé°ú ÀÌÀÇ ¼º´ÉÀ» Æò°¡ÇÒ ¶§ È°¿ëµÇ´Â ´ëÇ¥ÀûÀÎ º¥Ä¡¸¶Å© ¼ÂµéÀ» ÇÔ²² È°¿ëÇÏ¿© ÀÌÁúÀûÀÎ ¹®Àå°£ÀÇ À¯»ç °ü°è¸¦ ¿¹ÃøÀÇ ºñ±³ ½ÇÇèÇÏ¿´´Ù. ½ÇÇè °á°ú, Á¦¾ÈµÈ LAMII ÇÁ·¹ÀÓ¿öÅ©°¡ ´Ù¸¥ ¾ð¾î ¸ðµ¨¿¡ ºñÇÏ¿© ÀÌÁúÀûÀÎ ¹®Àå ±¸Á¶°£ÀÇ À¯»ç °ü°è¸¦ È¿°úÀûÀ¸·Î ¿¹ÃøÇÒ ¼ö ÀÖÀ½À» ÀÔÁõÇÏ¿´´Ù.
¿µ¹®³»¿ë
(English Abstract)
Based on Artificial Intelligence technology, AI-enabled warfare is expected to become the main issue in the future warfare. Natural language processing technology is a core technology of AI technology, and it can significantly contribute to reducing the information burden of underrstanidng reports, information objects and intelligences written in natural language by commanders and staff. In this paper, we propose a Language model-based Multi-source Information Integration (LAMII) framework to reduce the information overload of commanders and support rapid decision-making. The proposed LAMII framework consists of the key steps of representation learning based on language models in self-supervsied way and document integration using autoencoders. In the first step, representation learning that can identify the similar relationship between two heterogeneous sentences is performed using the self-supervised learning technique. In the second step, using the learned model, documents that implies similar contents or topics from multiple sources are found and integrated. At this time, the autoencoder is used to measure the information redundancy of the sentences in order to remove the duplicate sentences. In order to prove the superiority of this paper, we conducted comparison experiments using the language models and the benchmark sets used to evaluate their performance. As a result of the experiment, it was demonstrated that the proposed LAMII framework can effectively predict the similar relationship between heterogeneous sentence compared to other language models.
Å°¿öµå(Keyword) ÀÚ±âÁöµµ ÇнÀ   ¾ð¾î ¸ðµ¨   ¹®Àå°£ÀÇ À¯»ç °ü°è   ´ÙÃâó Á¤º¸ ÅëÇÕ   Self-supervised learning   similar relationship between sentences   Language model   Multi-source information integration  
ÆÄÀÏ÷ºÎ PDF ´Ù¿î·Îµå