\ub525 \ub7ec\ub2dd\uc744 \uc774\uc6a9\ud55c \uc790\uc5f0\uc5b4 \ucc98\ub9ac: \ubc14\uc774\ud2b8 \ud398\uc5b4 \uc778\ucf54\ub529 (Byte Pair Encoding, BPE) - \ub77c\uc774\ube0c\uc2a4\ub9c8\ud2b8<\/title>\n<meta name=\"robots\" content=\"index, follow, max-snippet:-1, max-image-preview:large, max-video-preview:-1\" \/>\n<link rel=\"canonical\" href=\"https:\/\/atmokpo.com\/w\/25371\/\" \/>\n<meta property=\"og:locale\" content=\"ko_KR\" \/>\n<meta property=\"og:type\" content=\"article\" \/>\n<meta property=\"og:title\" content=\"\ub525 \ub7ec\ub2dd\uc744 \uc774\uc6a9\ud55c \uc790\uc5f0\uc5b4 \ucc98\ub9ac: \ubc14\uc774\ud2b8 \ud398\uc5b4 \uc778\ucf54\ub529 (Byte Pair Encoding, BPE) - \ub77c\uc774\ube0c\uc2a4\ub9c8\ud2b8\" \/>\n<meta property=\"og:description\" content=\"\uc790\uc5f0\uc5b4 \ucc98\ub9ac\ub294 \ucef4\ud4e8\ud130\uac00 \uc778\uac04\uc758 \uc5b8\uc5b4\ub97c \uc774\ud574\ud558\uace0 \ud574\uc11d\ud558\ub294 \uae30\uc220\ub85c, \uc778\uacf5\uc9c0\ub2a5 \ubc0f \uae30\uacc4 \ud559\uc2b5\uc758 \uc911\uc694\ud55c \ubd84\uc57c \uc911 \ud558\ub098\uc785\ub2c8\ub2e4. \ucd5c\uadfc \uba87 \ub144\uac04 \ub525 \ub7ec\ub2dd \uae30\uc220\uc774 \ubc1c\uc804\ud558\uba74\uc11c \uc790\uc5f0\uc5b4 \ucc98\ub9ac(NLP)\uc758 \uc131\ub2a5\uc774 \ube44\uc57d\uc801\uc73c\ub85c \ud5a5\uc0c1\ub418\uc5c8\uc2b5\ub2c8\ub2e4. \uc774 \uae00\uc5d0\uc11c\ub294 \ub525 \ub7ec\ub2dd\uc744 \ud1b5\ud55c \uc790\uc5f0\uc5b4 \ucc98\ub9ac \uae30\ubc95 \uc911 \ud558\ub098\uc778 \ubc14\uc774\ud2b8 \ud398\uc5b4 \uc778\ucf54\ub529(Byte Pair Encoding, BPE)\uc5d0 \ub300\ud574 \uc790\uc138\ud788 \uc54c\uc544\ubcf4\uaca0\uc2b5\ub2c8\ub2e4. 1. \uc790\uc5f0\uc5b4 \ucc98\ub9ac(NLP)\uc758 \ubc1c\uc804 \uc790\uc5f0\uc5b4 \ucc98\ub9ac\ub294 \ub2e4\uc591\ud55c \ubd84\uc57c\uc5d0\uc11c … \ub354 \ubcf4\uae30 "\ub525 \ub7ec\ub2dd\uc744 \uc774\uc6a9\ud55c \uc790\uc5f0\uc5b4 \ucc98\ub9ac: \ubc14\uc774\ud2b8 \ud398\uc5b4 \uc778\ucf54\ub529 (Byte Pair Encoding, BPE)"\" \/>\n<meta property=\"og:url\" content=\"https:\/\/atmokpo.com\/w\/25371\/\" \/>\n<meta property=\"og:site_name\" content=\"\ub77c\uc774\ube0c\uc2a4\ub9c8\ud2b8\" \/>\n<meta property=\"article:published_time\" content=\"2024-10-26T09:54:31+00:00\" \/>\n<meta property=\"article:modified_time\" content=\"2024-11-26T08:02:00+00:00\" \/>\n<meta name=\"author\" content=\"root\" \/>\n<meta name=\"twitter:card\" content=\"summary_large_image\" \/>\n<meta name=\"twitter:creator\" content=\"@bebubo4\" \/>\n<meta name=\"twitter:site\" content=\"@bebubo4\" \/>\n<meta name=\"twitter:label1\" content=\"\uae00\uc4f4\uc774\" \/>\n\t<meta name=\"twitter:data1\" content=\"root\" \/>\n\t<meta name=\"twitter:label2\" content=\"\uc608\uc0c1 \ub418\ub294 \ud310\ub3c5 \uc2dc\uac04\" \/>\n\t<meta name=\"twitter:data2\" content=\"1\ubd84\" \/>\n<script type=\"application\/ld+json\" class=\"yoast-schema-graph\">{\"@context\":\"https:\/\/schema.org\",\"@graph\":[{\"@type\":\"Article\",\"@id\":\"https:\/\/atmokpo.com\/w\/25371\/#article\",\"isPartOf\":{\"@id\":\"https:\/\/atmokpo.com\/w\/25371\/\"},\"author\":{\"name\":\"root\",\"@id\":\"https:\/\/atmokpo.com\/w\/#\/schema\/person\/91b6b3b138fbba0efb4ae64b1abd81d7\"},\"headline\":\"\ub525 \ub7ec\ub2dd\uc744 \uc774\uc6a9\ud55c \uc790\uc5f0\uc5b4 \ucc98\ub9ac: \ubc14\uc774\ud2b8 \ud398\uc5b4 \uc778\ucf54\ub529 (Byte Pair Encoding, BPE)\",\"datePublished\":\"2024-10-26T09:54:31+00:00\",\"dateModified\":\"2024-11-26T08:02:00+00:00\",\"mainEntityOfPage\":{\"@id\":\"https:\/\/atmokpo.com\/w\/25371\/\"},\"wordCount\":122,\"publisher\":{\"@id\":\"https:\/\/atmokpo.com\/w\/#organization\"},\"articleSection\":[\"\ub525\ub7ec\ub2dd \uc790\uc5f0\uc5b4\ucc98\ub9ac\"],\"inLanguage\":\"ko-KR\"},{\"@type\":\"WebPage\",\"@id\":\"https:\/\/atmokpo.com\/w\/25371\/\",\"url\":\"https:\/\/atmokpo.com\/w\/25371\/\",\"name\":\"\ub525 \ub7ec\ub2dd\uc744 \uc774\uc6a9\ud55c \uc790\uc5f0\uc5b4 \ucc98\ub9ac: \ubc14\uc774\ud2b8 \ud398\uc5b4 \uc778\ucf54\ub529 (Byte Pair Encoding, BPE) - \ub77c\uc774\ube0c\uc2a4\ub9c8\ud2b8\",\"isPartOf\":{\"@id\":\"https:\/\/atmokpo.com\/w\/#website\"},\"datePublished\":\"2024-10-26T09:54:31+00:00\",\"dateModified\":\"2024-11-26T08:02:00+00:00\",\"breadcrumb\":{\"@id\":\"https:\/\/atmokpo.com\/w\/25371\/#breadcrumb\"},\"inLanguage\":\"ko-KR\",\"potentialAction\":[{\"@type\":\"ReadAction\",\"target\":[\"https:\/\/atmokpo.com\/w\/25371\/\"]}]},{\"@type\":\"BreadcrumbList\",\"@id\":\"https:\/\/atmokpo.com\/w\/25371\/#breadcrumb\",\"itemListElement\":[{\"@type\":\"ListItem\",\"position\":1,\"name\":\"\ud648\",\"item\":\"https:\/\/atmokpo.com\/w\/en\/\"},{\"@type\":\"ListItem\",\"position\":2,\"name\":\"\ub525 \ub7ec\ub2dd\uc744 \uc774\uc6a9\ud55c \uc790\uc5f0\uc5b4 \ucc98\ub9ac: \ubc14\uc774\ud2b8 \ud398\uc5b4 \uc778\ucf54\ub529 (Byte Pair Encoding, BPE)\"}]},{\"@type\":\"WebSite\",\"@id\":\"https:\/\/atmokpo.com\/w\/#website\",\"url\":\"https:\/\/atmokpo.com\/w\/\",\"name\":\"\ub77c\uc774\ube0c\uc2a4\ub9c8\ud2b8\",\"description\":\"\",\"publisher\":{\"@id\":\"https:\/\/atmokpo.com\/w\/#organization\"},\"potentialAction\":[{\"@type\":\"SearchAction\",\"target\":{\"@type\":\"EntryPoint\",\"urlTemplate\":\"https:\/\/atmokpo.com\/w\/?s={search_term_string}\"},\"query-input\":{\"@type\":\"PropertyValueSpecification\",\"valueRequired\":true,\"valueName\":\"search_term_string\"}}],\"inLanguage\":\"ko-KR\"},{\"@type\":\"Organization\",\"@id\":\"https:\/\/atmokpo.com\/w\/#organization\",\"name\":\"\ub77c\uc774\ube0c\uc2a4\ub9c8\ud2b8\",\"url\":\"https:\/\/atmokpo.com\/w\/\",\"logo\":{\"@type\":\"ImageObject\",\"inLanguage\":\"ko-KR\",\"@id\":\"https:\/\/atmokpo.com\/w\/#\/schema\/logo\/image\/\",\"url\":\"https:\/\/atmokpo.com\/w\/wp-content\/uploads\/2024\/11\/logo.png\",\"contentUrl\":\"https:\/\/atmokpo.com\/w\/wp-content\/uploads\/2024\/11\/logo.png\",\"width\":400,\"height\":400,\"caption\":\"\ub77c\uc774\ube0c\uc2a4\ub9c8\ud2b8\"},\"image\":{\"@id\":\"https:\/\/atmokpo.com\/w\/#\/schema\/logo\/image\/\"},\"sameAs\":[\"https:\/\/x.com\/bebubo4\"]},{\"@type\":\"Person\",\"@id\":\"https:\/\/atmokpo.com\/w\/#\/schema\/person\/91b6b3b138fbba0efb4ae64b1abd81d7\",\"name\":\"root\",\"image\":{\"@type\":\"ImageObject\",\"inLanguage\":\"ko-KR\",\"@id\":\"https:\/\/atmokpo.com\/w\/#\/schema\/person\/image\/\",\"url\":\"https:\/\/secure.gravatar.com\/avatar\/708197b41fc6435a7ce22d951b25d4a47e9e904270cb1f04682d4f025066f80c?s=96&d=mm&r=g\",\"contentUrl\":\"https:\/\/secure.gravatar.com\/avatar\/708197b41fc6435a7ce22d951b25d4a47e9e904270cb1f04682d4f025066f80c?s=96&d=mm&r=g\",\"caption\":\"root\"},\"sameAs\":[\"http:\/\/atmokpo.com\/w\"],\"url\":\"https:\/\/atmokpo.com\/w\/author\/root\/\"}]}<\/script>\n","yoast_head_json":{"title":"\ub525 \ub7ec\ub2dd\uc744 \uc774\uc6a9\ud55c \uc790\uc5f0\uc5b4 \ucc98\ub9ac: \ubc14\uc774\ud2b8 \ud398\uc5b4 \uc778\ucf54\ub529 (Byte Pair Encoding, BPE) - \ub77c\uc774\ube0c\uc2a4\ub9c8\ud2b8","robots":{"index":"index","follow":"follow","max-snippet":"max-snippet:-1","max-image-preview":"max-image-preview:large","max-video-preview":"max-video-preview:-1"},"canonical":"https:\/\/atmokpo.com\/w\/25371\/","og_locale":"ko_KR","og_type":"article","og_title":"\ub525 \ub7ec\ub2dd\uc744 \uc774\uc6a9\ud55c \uc790\uc5f0\uc5b4 \ucc98\ub9ac: \ubc14\uc774\ud2b8 \ud398\uc5b4 \uc778\ucf54\ub529 (Byte Pair Encoding, BPE) - \ub77c\uc774\ube0c\uc2a4\ub9c8\ud2b8","og_description":"\uc790\uc5f0\uc5b4 \ucc98\ub9ac\ub294 \ucef4\ud4e8\ud130\uac00 \uc778\uac04\uc758 \uc5b8\uc5b4\ub97c \uc774\ud574\ud558\uace0 \ud574\uc11d\ud558\ub294 \uae30\uc220\ub85c, \uc778\uacf5\uc9c0\ub2a5 \ubc0f \uae30\uacc4 \ud559\uc2b5\uc758 \uc911\uc694\ud55c \ubd84\uc57c \uc911 \ud558\ub098\uc785\ub2c8\ub2e4. \ucd5c\uadfc \uba87 \ub144\uac04 \ub525 \ub7ec\ub2dd \uae30\uc220\uc774 \ubc1c\uc804\ud558\uba74\uc11c \uc790\uc5f0\uc5b4 \ucc98\ub9ac(NLP)\uc758 \uc131\ub2a5\uc774 \ube44\uc57d\uc801\uc73c\ub85c \ud5a5\uc0c1\ub418\uc5c8\uc2b5\ub2c8\ub2e4. \uc774 \uae00\uc5d0\uc11c\ub294 \ub525 \ub7ec\ub2dd\uc744 \ud1b5\ud55c \uc790\uc5f0\uc5b4 \ucc98\ub9ac \uae30\ubc95 \uc911 \ud558\ub098\uc778 \ubc14\uc774\ud2b8 \ud398\uc5b4 \uc778\ucf54\ub529(Byte Pair Encoding, BPE)\uc5d0 \ub300\ud574 \uc790\uc138\ud788 \uc54c\uc544\ubcf4\uaca0\uc2b5\ub2c8\ub2e4. 1. \uc790\uc5f0\uc5b4 \ucc98\ub9ac(NLP)\uc758 \ubc1c\uc804 \uc790\uc5f0\uc5b4 \ucc98\ub9ac\ub294 \ub2e4\uc591\ud55c \ubd84\uc57c\uc5d0\uc11c … \ub354 \ubcf4\uae30 \"\ub525 \ub7ec\ub2dd\uc744 \uc774\uc6a9\ud55c \uc790\uc5f0\uc5b4 \ucc98\ub9ac: \ubc14\uc774\ud2b8 \ud398\uc5b4 \uc778\ucf54\ub529 (Byte Pair Encoding, BPE)\"","og_url":"https:\/\/atmokpo.com\/w\/25371\/","og_site_name":"\ub77c\uc774\ube0c\uc2a4\ub9c8\ud2b8","article_published_time":"2024-10-26T09:54:31+00:00","article_modified_time":"2024-11-26T08:02:00+00:00","author":"root","twitter_card":"summary_large_image","twitter_creator":"@bebubo4","twitter_site":"@bebubo4","twitter_misc":{"\uae00\uc4f4\uc774":"root","\uc608\uc0c1 \ub418\ub294 \ud310\ub3c5 \uc2dc\uac04":"1\ubd84"},"schema":{"@context":"https:\/\/schema.org","@graph":[{"@type":"Article","@id":"https:\/\/atmokpo.com\/w\/25371\/#article","isPartOf":{"@id":"https:\/\/atmokpo.com\/w\/25371\/"},"author":{"name":"root","@id":"https:\/\/atmokpo.com\/w\/#\/schema\/person\/91b6b3b138fbba0efb4ae64b1abd81d7"},"headline":"\ub525 \ub7ec\ub2dd\uc744 \uc774\uc6a9\ud55c \uc790\uc5f0\uc5b4 \ucc98\ub9ac: \ubc14\uc774\ud2b8 \ud398\uc5b4 \uc778\ucf54\ub529 (Byte Pair Encoding, BPE)","datePublished":"2024-10-26T09:54:31+00:00","dateModified":"2024-11-26T08:02:00+00:00","mainEntityOfPage":{"@id":"https:\/\/atmokpo.com\/w\/25371\/"},"wordCount":122,"publisher":{"@id":"https:\/\/atmokpo.com\/w\/#organization"},"articleSection":["\ub525\ub7ec\ub2dd \uc790\uc5f0\uc5b4\ucc98\ub9ac"],"inLanguage":"ko-KR"},{"@type":"WebPage","@id":"https:\/\/atmokpo.com\/w\/25371\/","url":"https:\/\/atmokpo.com\/w\/25371\/","name":"\ub525 \ub7ec\ub2dd\uc744 \uc774\uc6a9\ud55c \uc790\uc5f0\uc5b4 \ucc98\ub9ac: \ubc14\uc774\ud2b8 \ud398\uc5b4 \uc778\ucf54\ub529 (Byte Pair Encoding, BPE) - \ub77c\uc774\ube0c\uc2a4\ub9c8\ud2b8","isPartOf":{"@id":"https:\/\/atmokpo.com\/w\/#website"},"datePublished":"2024-10-26T09:54:31+00:00","dateModified":"2024-11-26T08:02:00+00:00","breadcrumb":{"@id":"https:\/\/atmokpo.com\/w\/25371\/#breadcrumb"},"inLanguage":"ko-KR","potentialAction":[{"@type":"ReadAction","target":["https:\/\/atmokpo.com\/w\/25371\/"]}]},{"@type":"BreadcrumbList","@id":"https:\/\/atmokpo.com\/w\/25371\/#breadcrumb","itemListElement":[{"@type":"ListItem","position":1,"name":"\ud648","item":"https:\/\/atmokpo.com\/w\/en\/"},{"@type":"ListItem","position":2,"name":"\ub525 \ub7ec\ub2dd\uc744 \uc774\uc6a9\ud55c \uc790\uc5f0\uc5b4 \ucc98\ub9ac: \ubc14\uc774\ud2b8 \ud398\uc5b4 \uc778\ucf54\ub529 (Byte Pair Encoding, BPE)"}]},{"@type":"WebSite","@id":"https:\/\/atmokpo.com\/w\/#website","url":"https:\/\/atmokpo.com\/w\/","name":"\ub77c\uc774\ube0c\uc2a4\ub9c8\ud2b8","description":"","publisher":{"@id":"https:\/\/atmokpo.com\/w\/#organization"},"potentialAction":[{"@type":"SearchAction","target":{"@type":"EntryPoint","urlTemplate":"https:\/\/atmokpo.com\/w\/?s={search_term_string}"},"query-input":{"@type":"PropertyValueSpecification","valueRequired":true,"valueName":"search_term_string"}}],"inLanguage":"ko-KR"},{"@type":"Organization","@id":"https:\/\/atmokpo.com\/w\/#organization","name":"\ub77c\uc774\ube0c\uc2a4\ub9c8\ud2b8","url":"https:\/\/atmokpo.com\/w\/","logo":{"@type":"ImageObject","inLanguage":"ko-KR","@id":"https:\/\/atmokpo.com\/w\/#\/schema\/logo\/image\/","url":"https:\/\/atmokpo.com\/w\/wp-content\/uploads\/2024\/11\/logo.png","contentUrl":"https:\/\/atmokpo.com\/w\/wp-content\/uploads\/2024\/11\/logo.png","width":400,"height":400,"caption":"\ub77c\uc774\ube0c\uc2a4\ub9c8\ud2b8"},"image":{"@id":"https:\/\/atmokpo.com\/w\/#\/schema\/logo\/image\/"},"sameAs":["https:\/\/x.com\/bebubo4"]},{"@type":"Person","@id":"https:\/\/atmokpo.com\/w\/#\/schema\/person\/91b6b3b138fbba0efb4ae64b1abd81d7","name":"root","image":{"@type":"ImageObject","inLanguage":"ko-KR","@id":"https:\/\/atmokpo.com\/w\/#\/schema\/person\/image\/","url":"https:\/\/secure.gravatar.com\/avatar\/708197b41fc6435a7ce22d951b25d4a47e9e904270cb1f04682d4f025066f80c?s=96&d=mm&r=g","contentUrl":"https:\/\/secure.gravatar.com\/avatar\/708197b41fc6435a7ce22d951b25d4a47e9e904270cb1f04682d4f025066f80c?s=96&d=mm&r=g","caption":"root"},"sameAs":["http:\/\/atmokpo.com\/w"],"url":"https:\/\/atmokpo.com\/w\/author\/root\/"}]}},"jetpack_featured_media_url":"","jetpack_sharing_enabled":true,"jetpack-related-posts":[{"id":25381,"url":"https:\/\/atmokpo.com\/w\/25381\/","url_meta":{"origin":25371,"position":0},"title":"\ub525 \ub7ec\ub2dd\uc744 \uc774\uc6a9\ud55c \uc790\uc5f0\uc5b4 \ucc98\ub9ac, \uc11c\ube0c\uc6cc\ub4dc \ud1a0\ud06c\ub098\uc774\uc800","author":"root","date":"2024\ub144 10\uc6d4 26\uc77c","format":false,"excerpt":"\uc791\uc131\uc77c: YYYY-MM-DD \uc791\uc131\uc790: \uc870\uad11\ud615 1. \uc11c\ub860 \uc790\uc5f0\uc5b4 \ucc98\ub9ac\ub294 \uc778\uac04\uc758 \uc5b8\uc5b4\ub97c \ucef4\ud4e8\ud130\uac00 \uc774\ud574\ud558\uace0 \ucc98\ub9ac\ud560 \uc218 \uc788\ub3c4\ub85d \ud558\ub294 \uae30\uc220\uc774\ub2e4. \ucd5c\uadfc \uba87 \ub144 \ub3d9\uc548 \ub525 \ub7ec\ub2dd \uae30\ubc18\uc758 \uc790\uc5f0\uc5b4 \ucc98\ub9ac \uae30\uc220\uc740 \ube44\uc57d\uc801\uc778 \ubc1c\uc804\uc744 \uc774\ub8e8\uc5c8\uc73c\uba70, \ud2b9\ud788 BERT, GPT\uc640 \uac19\uc740 \ub300\ud615 \uc5b8\uc5b4 \ubaa8\ub378\uc740 \ub180\ub77c\uc6b4 \uc131\uacfc\ub97c \uac70\ub450\uc5c8\ub2e4. \uadf8\ub7ec\ub098 \uc774\ub7ec\ud55c \ubaa8\ub378\uc740 \ud559\uc2b5 \ub370\uc774\ud130\uc5d0 \ub530\ub77c \uc131\ub2a5\uc774 \ud06c\uac8c \ub2ec\ub77c\uc9c0\uba70, \ub300\uc6a9\ub7c9\uc758\u2026","rel":"","context":""\ub525\ub7ec\ub2dd \uc790\uc5f0\uc5b4\ucc98\ub9ac"\uc5d0\uc11c","block_context":{"text":"\ub525\ub7ec\ub2dd \uc790\uc5f0\uc5b4\ucc98\ub9ac","link":"https:\/\/atmokpo.com\/w\/category\/%eb%94%a5%eb%9f%ac%eb%8b%9d-%ec%9e%90%ec%97%b0%ec%96%b4%ec%b2%98%eb%a6%ac\/"},"img":{"alt_text":"","src":"","width":0,"height":0},"classes":[]},{"id":25181,"url":"https:\/\/atmokpo.com\/w\/25181\/","url_meta":{"origin":25371,"position":1},"title":"\ub525 \ub7ec\ub2dd\uc744 \uc774\uc6a9\ud55c \uc790\uc5f0\uc5b4 \ucc98\ub9ac\uc640 \uc815\uaddc \ud45c\ud604\uc2dd","author":"root","date":"2024\ub144 10\uc6d4 26\uc77c","format":false,"excerpt":"\uc790\uc5f0\uc5b4 \ucc98\ub9ac\ub294 \uae30\uacc4\uac00 \uc778\uac04\uc758 \uc5b8\uc5b4\ub97c \uc774\ud574\ud558\uace0 \ubd84\uc11d\ud560 \uc218 \uc788\ub3c4\ub85d \ub3d5\ub294 \ucef4\ud4e8\ud130 \uacfc\ud559\uc758 \ud55c \ubd84\uc57c\uc785\ub2c8\ub2e4. \ub525 \ub7ec\ub2dd(deep learning)\uc740 \uc778\uacf5 \uc2e0\uacbd\ub9dd\uc744 \uae30\ubc18\uc73c\ub85c \ud55c \uba38\uc2e0 \ub7ec\ub2dd\uc758 \ud55c \ud615\ud0dc\ub85c, \ub300\ub7c9\uc758 \ub370\uc774\ud130\ub97c \ubd84\uc11d\ud558\uc5ec \ud328\ud134\uc744 \ud559\uc2b5\ud558\ub294 \ub370 \ub9e4\uc6b0 \ud6a8\uacfc\uc801\uc785\ub2c8\ub2e4. \ucd5c\uadfc \uba87 \ub144 \uac04 \uc790\uc5f0\uc5b4 \ucc98\ub9ac \ubd84\uc57c\uc5d0\uc11c\uc758 \ub525 \ub7ec\ub2dd\uc758 \ubc1c\uc804\uc740 \uc8fc\ubaa9\ud560 \ub9cc\ud55c \uc131\uacfc\ub97c \uc774\ub8e8\uc5c8\uace0, \uc774\ub7ec\ud55c \uae30\uc220\ub4e4\uc774 \uc2e4\uc81c\u2026","rel":"","context":""\ub525\ub7ec\ub2dd \uc790\uc5f0\uc5b4\ucc98\ub9ac"\uc5d0\uc11c","block_context":{"text":"\ub525\ub7ec\ub2dd \uc790\uc5f0\uc5b4\ucc98\ub9ac","link":"https:\/\/atmokpo.com\/w\/category\/%eb%94%a5%eb%9f%ac%eb%8b%9d-%ec%9e%90%ec%97%b0%ec%96%b4%ec%b2%98%eb%a6%ac\/"},"img":{"alt_text":"","src":"","width":0,"height":0},"classes":[]},{"id":25283,"url":"https:\/\/atmokpo.com\/w\/25283\/","url_meta":{"origin":25371,"position":2},"title":"\ub525 \ub7ec\ub2dd\uc744 \uc774\uc6a9\ud55c \uc790\uc5f0\uc5b4 \ucc98\ub9ac: RNN\uc744 \uc774\uc6a9\ud55c \ud14d\uc2a4\ud2b8 \uc0dd\uc131","author":"root","date":"2024\ub144 10\uc6d4 26\uc77c","format":false,"excerpt":"\uc791\uc131\uc77c: 2023\ub144 9\uc6d4 15\uc77c \uc791\uc131\uc790: \uc870\uad11\ud615 1. \uc11c\ub860 \uc778\uacf5\uc9c0\ub2a5\uc758 \ubc1c\uc804\uc740 \ub2e4\uc591\ud55c \ubd84\uc57c\uc5d0\uc11c \ud601\uc2e0\uc801\uc778 \ubcc0\ud654\ub97c \uac00\uc838\uc624\uace0 \uc788\uc2b5\ub2c8\ub2e4. \uadf8 \uc911\uc5d0\uc11c\ub3c4 \uc790\uc5f0\uc5b4 \ucc98\ub9ac(NLP)\ub294 \uae30\uacc4\uac00 \uc778\uac04\uc758 \uc5b8\uc5b4\ub97c \uc774\ud574\ud558\uace0 \uc0dd\uc131\ud560 \uc218 \uc788\ub3c4\ub85d \ud558\ub294 \uae30\uc220\ub85c, \ucd5c\uadfc \uba87 \ub144\uac04 \ub9ce\uc740 \uad00\uc2ec\uc744 \ubc1b\uace0 \uc788\uc2b5\ub2c8\ub2e4. \ud2b9\ud788, \ub525 \ub7ec\ub2dd \uae30\uc220\uc744 \ud65c\uc6a9\ud55c \uc790\uc5f0\uc5b4 \ucc98\ub9ac\uc758 \ubc1c\uc804\uc740 \ub9ce\uc740 \uc5f0\uad6c\uc790\uc640 \uac1c\ubc1c\uc790\ub4e4\uc5d0\uac8c \uc0c8\ub85c\uc6b4 \uac00\ub2a5\uc131\uc744 \uc5f4\uc5b4\uc8fc\uc5c8\uc2b5\ub2c8\ub2e4.\u2026","rel":"","context":""\ub525\ub7ec\ub2dd \uc790\uc5f0\uc5b4\ucc98\ub9ac"\uc5d0\uc11c","block_context":{"text":"\ub525\ub7ec\ub2dd \uc790\uc5f0\uc5b4\ucc98\ub9ac","link":"https:\/\/atmokpo.com\/w\/category\/%eb%94%a5%eb%9f%ac%eb%8b%9d-%ec%9e%90%ec%97%b0%ec%96%b4%ec%b2%98%eb%a6%ac\/"},"img":{"alt_text":"","src":"","width":0,"height":0},"classes":[]},{"id":25423,"url":"https:\/\/atmokpo.com\/w\/25423\/","url_meta":{"origin":25371,"position":3},"title":"\ub525 \ub7ec\ub2dd\uc744 \uc774\uc6a9\ud55c \uc790\uc5f0\uc5b4 \ucc98\ub9ac, \ucf54\ub7a9(Colab)\uc5d0\uc11c TPU \uc0ac\uc6a9\ud558\uae30","author":"root","date":"2024\ub144 10\uc6d4 26\uc77c","format":false,"excerpt":"\uc790\uc5f0\uc5b4 \ucc98\ub9ac\ub294 \uc778\uacf5\uc9c0\ub2a5\uc758 \ud55c \ubd84\uc57c\ub85c, \ucef4\ud4e8\ud130\uac00 \uc778\uac04\uc758 \uc5b8\uc5b4\ub97c \uc774\ud574\ud558\uace0 \ucc98\ub9ac\ud560 \uc218 \uc788\ub3c4\ub85d \ud558\ub294 \uae30\uc220\uc785\ub2c8\ub2e4. \ucd5c\uadfc \uba87 \ub144 \ub3d9\uc548 \u27e8\ub525 \ub7ec\ub2dd\u27e9 \uae30\ubc95\uc758 \ubc1c\uc804\uc73c\ub85c \uc790\uc5f0\uc5b4 \ucc98\ub9ac \ubd84\uc57c\ub294 \uad04\ubaa9\ud560 \ub9cc\ud55c \uc131\uacfc\ub97c \uc774\ub8e8\uc5b4 \uc654\uc2b5\ub2c8\ub2e4. \uc774\ubc88 \uae00\uc5d0\uc11c\ub294 \ub525 \ub7ec\ub2dd\uc744 \ud65c\uc6a9\ud55c \uc790\uc5f0\uc5b4 \ucc98\ub9ac \ubaa8\ub378\uc744 Google Colab\uc5d0\uc11c TPU\ub97c \uc774\uc6a9\ud558\uc5ec \ud559\uc2b5\uc2dc\ud0a4\ub294 \ubc29\ubc95\uc5d0 \ub300\ud574 \uc790\uc138\ud788 \uc0b4\ud3b4\ubcf4\uaca0\uc2b5\ub2c8\ub2e4. 1. \uc790\uc5f0\uc5b4 \ucc98\ub9ac(NLP)\u2026","rel":"","context":""\ub525\ub7ec\ub2dd \uc790\uc5f0\uc5b4\ucc98\ub9ac"\uc5d0\uc11c","block_context":{"text":"\ub525\ub7ec\ub2dd \uc790\uc5f0\uc5b4\ucc98\ub9ac","link":"https:\/\/atmokpo.com\/w\/category\/%eb%94%a5%eb%9f%ac%eb%8b%9d-%ec%9e%90%ec%97%b0%ec%96%b4%ec%b2%98%eb%a6%ac\/"},"img":{"alt_text":"","src":"","width":0,"height":0},"classes":[]},{"id":25493,"url":"https:\/\/atmokpo.com\/w\/25493\/","url_meta":{"origin":25371,"position":4},"title":"\ub525 \ub7ec\ub2dd\uc744 \uc774\uc6a9\ud55c \uc790\uc5f0\uc5b4 \ucc98\ub9ac, \uc9c8\uc758 \uc751\ub2f5(Question Answering, QA)","author":"root","date":"2024\ub144 10\uc6d4 26\uc77c","format":false,"excerpt":"\uc791\uc131\uc790: \uc870\uad11\ud615 | \ub0a0\uc9dc: 2024\ub144 11\uc6d4 26\uc77c 1. \uc11c\ub860 \uc790\uc5f0\uc5b4 \ucc98\ub9ac(Natural Language Processing, NLP)\ub294 \uc778\uacf5\uc9c0\ub2a5(AI)\uacfc \ucef4\ud4e8\ud130 \uacfc\ud559\uc758 \ud55c \ubd84\uc57c\ub85c, \ucef4\ud4e8\ud130\uac00 \uc778\uac04\uc758 \uc5b8\uc5b4\ub97c \uc774\ud574\ud558\uace0 \ucc98\ub9ac\ud560 \uc218 \uc788\ub3c4\ub85d \ud558\ub294 \uae30\uc220\uc744 \ud3ec\ud568\ud569\ub2c8\ub2e4. \ud2b9\ud788, \uc9c8\uc758 \uc751\ub2f5 \uc2dc\uc2a4\ud15c\uc740 \uc0ac\uc6a9\uc790\ub85c\ubd80\ud130 \uc790\uc5f0\uc5b4\ub85c \uc785\ub825\ub41c \uc9c8\ubb38\uc744 \uc774\ud574\ud558\uace0, \uadf8\uc5d0 \ub300\ud55c \uc801\uc808\ud55c \ub2f5\ubcc0\uc744 \uc81c\uacf5\ud558\ub294 \uc2dc\uc2a4\ud15c\uc785\ub2c8\ub2e4. \ucd5c\uadfc \uba87 \ub144\uac04 \ub525 \ub7ec\ub2dd\uc758 \ubc1c\uc804\uc740\u2026","rel":"","context":""\ub525\ub7ec\ub2dd \uc790\uc5f0\uc5b4\ucc98\ub9ac"\uc5d0\uc11c","block_context":{"text":"\ub525\ub7ec\ub2dd \uc790\uc5f0\uc5b4\ucc98\ub9ac","link":"https:\/\/atmokpo.com\/w\/category\/%eb%94%a5%eb%9f%ac%eb%8b%9d-%ec%9e%90%ec%97%b0%ec%96%b4%ec%b2%98%eb%a6%ac\/"},"img":{"alt_text":"","src":"","width":0,"height":0},"classes":[]},{"id":25287,"url":"https:\/\/atmokpo.com\/w\/25287\/","url_meta":{"origin":25371,"position":5},"title":"\ub525 \ub7ec\ub2dd\uc744 \uc774\uc6a9\ud55c \uc790\uc5f0\uc5b4 \ucc98\ub9ac: \uc21c\ud658 \uc2e0\uacbd\ub9dd(Recurrent Neural Network)","author":"root","date":"2024\ub144 10\uc6d4 26\uc77c","format":false,"excerpt":"\uc791\uc131\uc790: \uc870\uad11\ud615 | \ub0a0\uc9dc: [\ub0a0\uc9dc] 1. \uc11c\ub860 \uc790\uc5f0\uc5b4 \ucc98\ub9ac(Natural Language Processing, NLP)\ub294 \ucef4\ud4e8\ud130\uac00 \uc778\uac04\uc758 \uc5b8\uc5b4\ub97c \uc774\ud574\ud558\uace0 \ubd84\uc11d\ud558\ub294 \uae30\uc220\uc744 \uc758\ubbf8\ud569\ub2c8\ub2e4. \ub525 \ub7ec\ub2dd\uc758 \ubc1c\uc804\uc73c\ub85c \uc790\uc5f0\uc5b4 \ucc98\ub9ac \ubd84\uc57c\ub294 \ube44\uc57d\uc801\uc778 \ubc1c\uc804\uc744 \uc774\ub8e8\uc5c8\uc73c\uba70, \uadf8 \uc911\uc5d0\uc11c\ub3c4 \uc21c\ud658 \uc2e0\uacbd\ub9dd(Recurrent Neural Network, RNN)\uc740 \uc5b8\uc5b4 \ub370\uc774\ud130\ub97c \ucc98\ub9ac\ud558\ub294 \ub370 \ub9e4\uc6b0 \ud6a8\uacfc\uc801\uc778 \ubaa8\ub378\ub85c \uc8fc\ubaa9\ubc1b\uace0 \uc788\uc2b5\ub2c8\ub2e4. \uc774\ubc88 \uae00\uc5d0\uc11c\ub294 RNN\uc758 \uc6d0\ub9ac, \uad6c\uc870, \uadf8\ub9ac\uace0\u2026","rel":"","context":""\ub525\ub7ec\ub2dd \uc790\uc5f0\uc5b4\ucc98\ub9ac"\uc5d0\uc11c","block_context":{"text":"\ub525\ub7ec\ub2dd \uc790\uc5f0\uc5b4\ucc98\ub9ac","link":"https:\/\/atmokpo.com\/w\/category\/%eb%94%a5%eb%9f%ac%eb%8b%9d-%ec%9e%90%ec%97%b0%ec%96%b4%ec%b2%98%eb%a6%ac\/"},"img":{"alt_text":"","src":"","width":0,"height":0},"classes":[]}],"_links":{"self":[{"href":"https:\/\/atmokpo.com\/w\/wp-json\/wp\/v2\/posts\/25371","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/atmokpo.com\/w\/wp-json\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/atmokpo.com\/w\/wp-json\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/atmokpo.com\/w\/wp-json\/wp\/v2\/users\/1"}],"replies":[{"embeddable":true,"href":"https:\/\/atmokpo.com\/w\/wp-json\/wp\/v2\/comments?post=25371"}],"version-history":[{"count":1,"href":"https:\/\/atmokpo.com\/w\/wp-json\/wp\/v2\/posts\/25371\/revisions"}],"predecessor-version":[{"id":25372,"href":"https:\/\/atmokpo.com\/w\/wp-json\/wp\/v2\/posts\/25371\/revisions\/25372"}],"wp:attachment":[{"href":"https:\/\/atmokpo.com\/w\/wp-json\/wp\/v2\/media?parent=25371"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/atmokpo.com\/w\/wp-json\/wp\/v2\/categories?post=25371"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/atmokpo.com\/w\/wp-json\/wp\/v2\/tags?post=25371"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}

{"id":25371,"date":"2024-10-26T09:54:31","date_gmt":"2024-10-26T09:54:31","guid":{"rendered":"http:\/\/atmokpo.com\/w\/?p=25371"},"modified":"2024-11-26T08:02:00","modified_gmt":"2024-11-26T08:02:00","slug":"%eb%94%a5-%eb%9f%ac%eb%8b%9d%ec%9d%84-%ec%9d%b4%ec%9a%a9%ed%95%9c-%ec%9e%90%ec%97%b0%ec%96%b4-%ec%b2%98%eb%a6%ac-%eb%b0%94%ec%9d%b4%ed%8a%b8-%ed%8e%98%ec%96%b4-%ec%9d%b8%ec%bd%94%eb%94%a9-byte-pair","status":"publish","type":"post","link":"https:\/\/atmokpo.com\/w\/25371\/","title":{"rendered":"\ub525 \ub7ec\ub2dd\uc744 \uc774\uc6a9\ud55c \uc790\uc5f0\uc5b4 \ucc98\ub9ac: \ubc14\uc774\ud2b8 \ud398\uc5b4 \uc778\ucf54\ub529 (Byte Pair Encoding, BPE)"},"content":{"rendered":"

<\/p>\n

\uc790\uc5f0\uc5b4 \ucc98\ub9ac\ub294 \ucef4\ud4e8\ud130\uac00 \uc778\uac04\uc758 \uc5b8\uc5b4\ub97c \uc774\ud574\ud558\uace0 \ud574\uc11d\ud558\ub294 \uae30\uc220\ub85c, \uc778\uacf5\uc9c0\ub2a5 \ubc0f \uae30\uacc4 \ud559\uc2b5\uc758 \uc911\uc694\ud55c \ubd84\uc57c \uc911 \ud558\ub098\uc785\ub2c8\ub2e4. \ucd5c\uadfc \uba87 \ub144\uac04 \ub525 \ub7ec\ub2dd \uae30\uc220\uc774 \ubc1c\uc804\ud558\uba74\uc11c \uc790\uc5f0\uc5b4 \ucc98\ub9ac(NLP)\uc758 \uc131\ub2a5\uc774 \ube44\uc57d\uc801\uc73c\ub85c \ud5a5\uc0c1\ub418\uc5c8\uc2b5\ub2c8\ub2e4. \uc774 \uae00\uc5d0\uc11c\ub294 \ub525 \ub7ec\ub2dd\uc744 \ud1b5\ud55c \uc790\uc5f0\uc5b4 \ucc98\ub9ac \uae30\ubc95 \uc911 \ud558\ub098\uc778 \ubc14\uc774\ud2b8 \ud398\uc5b4 \uc778\ucf54\ub529(Byte Pair Encoding, BPE)\uc5d0 \ub300\ud574 \uc790\uc138\ud788 \uc54c\uc544\ubcf4\uaca0\uc2b5\ub2c8\ub2e4.<\/p>\n

1. \uc790\uc5f0\uc5b4 \ucc98\ub9ac(NLP)\uc758 \ubc1c\uc804<\/h2>\n
\uc790\uc5f0\uc5b4 \ucc98\ub9ac\ub294 \ub2e4\uc591\ud55c \ubd84\uc57c\uc5d0\uc11c \ud65c\uc6a9\ub418\uace0 \uc788\uc2b5\ub2c8\ub2e4. \uc608\ub97c \ub4e4\uc5b4, \uae30\uacc4 \ubc88\uc5ed, \uac10\uc815 \ubd84\uc11d, \uc694\uc57d \uc0dd\uc131, \uc9c8\ubb38 \uc751\ub2f5 \uc2dc\uc2a4\ud15c \ub4f1\uc774 \uc788\uc2b5\ub2c8\ub2e4. NLP\uc758 \ubc1c\uc804\uc740 \ud2b9\ud788 \ub525 \ub7ec\ub2dd \uae30\uc220\uc758 \ubc1c\uc804\uacfc \ubc00\uc811\ud55c \uad00\uacc4\uac00 \uc788\uc2b5\ub2c8\ub2e4. \uc804\ud1b5\uc801\uc778 \uae30\uacc4 \ud559\uc2b5 \ubc29\ubc95\uacfc\ub294 \ub2ec\ub9ac, \ub525 \ub7ec\ub2dd\uc740 \ub300\uaddc\ubaa8 \ub370\uc774\ud130\uc5d0\uc11c \ubcf5\uc7a1\ud55c \ud328\ud134\uc744 \uc778\uc2dd\ud558\uace0 \ucd94\ucd9c\ud560 \uc218 \uc788\ub294 \ub2a5\ub825\uc744 \uac00\uc9c0\uace0 \uc788\uc2b5\ub2c8\ub2e4.<\/p>\n

1.1 \ub525 \ub7ec\ub2dd\uc758 \uc5ed\ud560<\/h3>\n
\ub525 \ub7ec\ub2dd \ubaa8\ub378\uc740 \uc2e0\uacbd\ub9dd\uc744 \uae30\ubc18\uc73c\ub85c \ud558\uba70, \uacc4\uce35 \uad6c\uc870\ub97c \ud1b5\ud574 \uc785\ub825 \ub370\uc774\ud130\uc758 \uc218\ub9ce\uc740 \ud2b9\uc131\uc744 \uc790\ub3d9\uc73c\ub85c \ud559\uc2b5\ud569\ub2c8\ub2e4. \uc774 \uacfc\uc815\uc5d0\uc11c \ub525 \ub7ec\ub2dd\uc740 \ud14d\uc2a4\ud2b8\uc758 \uc758\ubbf8\uc801 \ud2b9\uc131\uc744 \uc774\ud574\ud558\uace0, \ubb38\uc7a5 \uad6c\uc870 \ubc0f \ub9e5\ub77d\uc744 \uace0\ub824\ud558\uc5ec \ub6f0\uc5b4\ub09c \uc131\ub2a5\uc744 \ubc1c\ud718\ud569\ub2c8\ub2e4. \uc774\ub7ec\ud55c \ubc1c\uc804\uc740 NLP \uc5c5\ubb34\uc758 \uc131\ub2a5\uacfc \ud6a8\uc728\uc131\uc744 \ud5a5\uc0c1\uc2dc\ud0a4\uace0 \uc788\uc2b5\ub2c8\ub2e4.<\/p>\n

2. \ubc14\uc774\ud2b8 \ud398\uc5b4 \uc778\ucf54\ub529(Byte Pair Encoding, BPE)<\/h2>\n
BPE\ub294 \ud14d\uc2a4\ud2b8 \ub370\uc774\ud130\ub97c \uc778\ucf54\ub529\ud558\ub294 \uae30\uc220\ub85c, \uc8fc\ub85c \uc790\uc5f0\uc5b4 \ucc98\ub9ac\uc5d0\uc11c \uc5b4\ud718 \uc9d1\ud569\uc744 \uc904\uc774\uace0, \ud76c\uadc0 \ub2e8\uc5b4 \ubb38\uc81c\ub97c \ud574\uacb0\ud558\ub294 \ub370 \uc0ac\uc6a9\ub429\ub2c8\ub2e4. \uc774 \ubc29\ubc95\uc740 \ub370\uc774\ud130\uc758 \uc555\ucd95 \uae30\uc220\uc5d0 \uae30\ucd08\ud558\uace0 \uc788\uc73c\uba70, \ubd84\ub9ac\ub41c \ubb38\uc790 \uc9d1\ud569\uc758 \ube48\ub3c4\uc218\ub97c \uae30\ubc18\uc73c\ub85c \uac00\uc7a5 \ube48\ubc88\ud788 \ub098\ud0c0\ub098\ub294 \ubb38\uc790 \uc30d\uc744 \uacb0\ud569\ud558\uc5ec \uc0c8\ub85c\uc6b4 \uae30\ud638\ub97c \ub9cc\ub4e4\uc5b4\ub0c5\ub2c8\ub2e4.<\/p>\n

2.1 BPE\uc758 \uae30\ubcf8 \uc6d0\ub9ac<\/h3>\n

\ucd08\uae30 \ud14d\uc2a4\ud2b8\ub97c \ubb38\uc790 \ub2e8\uc704\ub85c \ubd84\ub9ac\ud569\ub2c8\ub2e4.<\/li>\n
\ubaa8\ub4e0 \ubb38\uc790 \uc30d\uc758 \ube48\ub3c4\ub97c \uacc4\uc0b0\ud55c \ud6c4 \ube48\ub3c4\uac00 \uac00\uc7a5 \ub192\uc740 \uc30d\uc744 \ucc3e\uc2b5\ub2c8\ub2e4.<\/li>\n
\ucc3e\uc740 \ubb38\uc790 \uc30d\uc744 \uc0c8\ub85c\uc6b4 \uae30\ud638\ub85c \uacb0\ud569\ud558\uace0 \uae30\uc874 \ubb38\uc790\ub97c \ub300\uccb4\ud569\ub2c8\ub2e4.<\/li>\n

\uc774 \uacfc\uc815\uc744 \ubc18\ubcf5\ud558\uc5ec \uc0ac\uc804\uc758 \ud06c\uae30\ub97c \uc904\uc774\uace0 \ud6a8\uc728\uc801\uc778 \uc778\ucf54\ub529\uc744 \uc0dd\uc131\ud569\ub2c8\ub2e4.<\/li>\n<\/ul>\n

3. BPE\uc758 \uc7a5\uc810<\/h2>\n

\uc5b4\ud718 \uc9d1\ud569\uc758 \ud06c\uae30\ub97c \uc904\uc784\uc73c\ub85c\uc368 \ubaa8\ub378\uc758 \ud06c\uae30\ub97c \uc791\uac8c \uc720\uc9c0\ud560 \uc218 \uc788\uc2b5\ub2c8\ub2e4.<\/li>\n
\ud76c\uadc0 \ub2e8\uc5b4\ub97c \ucc98\ub9ac\ud558\ub294 \ub370 \ud6a8\uacfc\uc801\uc774\uba70, \ub370\uc774\ud130\uc758 \ub2e4\uc591\uc131\uc744 \uc99d\uac00\uc2dc\ud0ac \uc218 \uc788\uc2b5\ub2c8\ub2e4.<\/li>\n

\uc790\uc5f0\uc5b4\uc758 \ubcf5\uc7a1\uc131\uc744 \ub354 \uc798 \ubc18\uc601\ud560 \uc218 \uc788\ub294 \uc720\uc5f0\uc131\uc744 \uc81c\uacf5\ud569\ub2c8\ub2e4.<\/li>\n<\/ul>\n

3.1 Zeros, ONES, and Unknowns: BPE\uc758 \uc791\ud488<\/h3>\n
BPE\ub294 \ud2b9\ud788 \uc790\uc5f0\uc5b4 \ucc98\ub9ac\uc5d0\uc11c \ubc1c\uc0dd\ud558\ub294 “UNKnown” \ubb38\uc81c\ub97c \ud6a8\uacfc\uc801\uc73c\ub85c \ub2e4\ub8f0 \uc218 \uc788\uc2b5\ub2c8\ub2e4. \uc2e0\uacbd\ub9dd\uc744 \ud1b5\ud574 \ucc98\uc74c \ubcf4\ub294 \ub2e8\uc5b4\ub97c \ucc98\ub9ac\ud560 \uc218 \uc788\ub294 \ub2a5\ub825\uc744 \uac16\ucd94\uac8c \ub429\ub2c8\ub2e4. \uc608\ub97c \ub4e4\uc5b4, “happy”\ub77c\ub294 \ub2e8\uc5b4\uac00 \uc54c\ub824\uc838 \uc788\uc9c0\ub9cc “happiest”\ub294 \uccab \ubc88\uc9f8\ub85c \ubc1c\uc0dd\ud558\uc9c0 \uc54a\uc744 \uc218 \uc788\uc2b5\ub2c8\ub2e4. BPE\ub97c \uc0ac\uc6a9\ud558\uba74 \uc774\ub97c “happi”\uc640 “est”\ub85c \ubd84\ud560\ud558\uc5ec \ucc98\ub9ac\ud558\uac8c \ub429\ub2c8\ub2e4.<\/p>\n

4. BPE\uc758 \uc801\uc6a9 \uc0ac\ub840<\/h2>\n
BPE\ub294 \ub9ce\uc740 \ud604\ub300 NLP \ubaa8\ub378\uc5d0\uc11c \uc0ac\uc6a9\ub418\uace0 \uc788\uc2b5\ub2c8\ub2e4. Google’s Transformer \ubaa8\ub378\uacfc OpenAI\uc758 GPT \uc2dc\ub9ac\uc988\uc640 \uac19\uc740 \ucd5c\uc2e0 \ubaa8\ub378\ub4e4\uc774 \uc774 \uae30\ubc95\uc744 \ub3c4\uc785\ud558\uc5ec \uc131\ub2a5\uc744 \ud06c\uac8c \ud5a5\uc0c1\uc2dc\ucf30\uc2b5\ub2c8\ub2e4.<\/p>\n

4.1 \uad6c\uae00\uc758 Transformer \ubaa8\ub378<\/h3>\n
Transformer \ubaa8\ub378\uc740 \uc5b4\ud150\uc158 \uba54\ucee4\ub2c8\uc998\uc744 \uae30\ubc18\uc73c\ub85c \ud558\uc5ec \ubb38\ub9e5 \uc815\ubcf4\ub97c \ud6a8\uc728\uc801\uc73c\ub85c \ucc98\ub9ac\ud558\uba70, BPE\ub97c \ud1b5\ud574 \uc785\ub825 \ud14d\uc2a4\ud2b8\ub97c \ud6a8\uacfc\uc801\uc73c\ub85c \uc778\ucf54\ub529\ud558\uace0 \uc788\uc2b5\ub2c8\ub2e4. \uc774\ub7ec\ud55c \uc870\ud569\uc740 \ubc88\uc5ed \ud488\uc9c8\uc744 \ub192\uc774\uace0, \ud14d\uc2a4\ud2b8 \uc0dd\uc131 \uc791\uc5c5\uc5d0\uc11c \ub192\uc740 \uc131\uacfc\ub97c \ubcf4\uc785\ub2c8\ub2e4.<\/p>\n

4.2 OpenAI\uc758 GPT \uc2dc\ub9ac\uc988<\/h3>\n
OpenAI\uc758 GPT(Generative Pre-trained Transformer) \ubaa8\ub378\uc740 \ub300\uaddc\ubaa8 \ucf54\ud37c\uc2a4\ub97c \uc0ac\uc804 \ud559\uc2b5\ud558\uc5ec \ud14d\uc2a4\ud2b8\ub97c \uc0dd\uc131\ud558\ub294\ub370 \ud2b9\ud654\ub418\uc5b4 \uc788\uc2b5\ub2c8\ub2e4. BPE\ub97c \ud1b5\ud574 \ub2e4\ub8e8\uae30 \uc5b4\ub824\uc6b4 \ub2e8\uc5b4\uc5d0 \ub300\ud55c \uc720\uc5f0\uc131\uc744 \uc81c\uacf5\ud558\uc5ec, \ubaa8\ub378\uc758 \uc0dd\uc131 \ub2a5\ub825\uc744 \uadf9\ub300\ud654\ud569\ub2c8\ub2e4.<\/p>\n

5. BPE \uad6c\ud604\ud558\uae30<\/h2>\n

\uc544\ub798\ub294 BPE\ub97c \uad6c\ud604\ud558\ub294 \uac04\ub2e8\ud55c \ud30c\uc774\uc36c \ucf54\ub4dc\uc758 \uc608\uc785\ub2c8\ub2e4:<\/p>\n

\nimport re\nfrom collections import defaultdict\n\ndef get_stats(corpora):\n    \"\"\"\ubb38\uc11c\uc5d0\uc11c \ubb38\uc790 \uc30d\uc758 \ube48\ub3c4\ub97c \uacc4\uc0b0\ud569\ub2c8\ub2e4.\"\"\"\n    pairs = defaultdict(int)\n    for word in corpora:\n        symbols = word.split()\n        for i in range(len(symbols) - 1):\n            pairs[(symbols[i], symbols[i + 1])] += 1\n    return pairs\n\ndef merge_pair(pair, corpora):\n    \"\"\"\uc785\ub825\ub41c \ubb38\uc790 \uc30d\uc744 \ubb38\uc11c\uc5d0\uc11c \ubcd1\ud569\ud569\ub2c8\ub2e4.\"\"\"\n    out = []\n    bigram = ' '.join(pair)\n    replacement = ''.join(pair)\n    for word in corpora:\n        word = re.sub(bigram, replacement, word)\n        out.append(word)\n    return out\n\ndef byte_pair_encoding(corpora, num_merges):\n    \"\"\"BPE \uc54c\uace0\ub9ac\uc998\uc744 \uc2e4\ud589\ud569\ub2c8\ub2e4.\"\"\"\n    corpora = [' '.join(list(word)) for word in corpora]\n    for i in range(num_merges):\n        pairs = get_stats(corpora)\n        if not pairs:\n            break\n        best_pair = max(pairs, key=pairs.get)\n        corpora = merge_pair(best_pair, corpora)\n    return corpora\n\n# \uc608\uc2dc \ub370\uc774\ud130\ncorpora = ['low', 'low', 'lower', 'newer', 'new', 'wide', 'wider', 'widest']\nnum_merges = 10\nresult = byte_pair_encoding(corpora, num_merges)\nprint(result)\n    <\/code><\/pre>\n6. \uacb0\ub860<\/h2>\nBPE\ub294 \uc790\uc5f0\uc5b4 \ucc98\ub9ac\uc5d0\uc11c \ud14d\uc2a4\ud2b8 \ub370\uc774\ud130\ub97c \ud6a8\uacfc\uc801\uc73c\ub85c \uc778\ucf54\ub529\ud558\uace0 \uc5b4\ud718 \uc9d1\ud569\uc744 \uc904\uc774\ub294 \ub370 \uc911\uc694\ud55c \uc5ed\ud560\uc744 \ud569\ub2c8\ub2e4. \ub525 \ub7ec\ub2dd\uc744 \ud65c\uc6a9\ud55c NLP\uc758 \ubc1c\uc804\uacfc \ud568\uaed8, BPE\ub294 \uc131\ub2a5 \ud5a5\uc0c1\uc5d0 \uae30\uc5ec\ud558\uace0 \uc788\uc73c\uba70, \ud604\ub300\uc801\uc778 NLP \ubaa8\ub378\uc5d0\uc11c \ub110\ub9ac \uc0ac\uc6a9\ub418\uace0 \uc788\uc2b5\ub2c8\ub2e4. \uc55e\uc73c\ub85c\ub3c4 \uc774\ub7ec\ud55c \uae30\uc220\ub4e4\uc774 \ubcf4\ub2e4 \ubc1c\uc804\ud558\uc5ec \ub354 \ub098\uc740 \uc790\uc5f0\uc5b4 \uc774\ud574\uc640 \ucc98\ub9ac \uae30\uc220\uc774 \ubc1c\uc804\ud558\uae30\ub97c \uae30\ub300\ud569\ub2c8\ub2e4.<\/p>\n
7. \ucc38\uace0 \ubb38\ud5cc<\/h2>\n\nSennrich, R., Haddow, B., & Birch, A. (2016). Neural Machine Translation of Rare Words with Subword Units. Proceedings of the 54th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)<\/i>.<\/li>\n
Vaswani, A., Shard, N., Parmar, N., & Uszkoreit, J. (2017). Attention is All You Need. Advances in Neural Information Processing Systems<\/i>.<\/li>\n
Radford, A., Karthik, N., & Wu, D. (2018). Improving Language Understanding by Generative Pre-Training. OpenAI Preprint<\/i>.<\/li>\n<\/ul>\n<\/body><\/p>\n","protected":false},"excerpt":{"rendered":"
\uc790\uc5f0\uc5b4 \ucc98\ub9ac\ub294 \ucef4\ud4e8\ud130\uac00 \uc778\uac04\uc758 \uc5b8\uc5b4\ub97c \uc774\ud574\ud558\uace0 \ud574\uc11d\ud558\ub294 \uae30\uc220\ub85c, \uc778\uacf5\uc9c0\ub2a5 \ubc0f \uae30\uacc4 \ud559\uc2b5\uc758 \uc911\uc694\ud55c \ubd84\uc57c \uc911 \ud558\ub098\uc785\ub2c8\ub2e4. \ucd5c\uadfc \uba87 \ub144\uac04 \ub525 \ub7ec\ub2dd \uae30\uc220\uc774 \ubc1c\uc804\ud558\uba74\uc11c \uc790\uc5f0\uc5b4 \ucc98\ub9ac(NLP)\uc758 \uc131\ub2a5\uc774 \ube44\uc57d\uc801\uc73c\ub85c \ud5a5\uc0c1\ub418\uc5c8\uc2b5\ub2c8\ub2e4. \uc774 \uae00\uc5d0\uc11c\ub294 \ub525 \ub7ec\ub2dd\uc744 \ud1b5\ud55c \uc790\uc5f0\uc5b4 \ucc98\ub9ac \uae30\ubc95 \uc911 \ud558\ub098\uc778 \ubc14\uc774\ud2b8 \ud398\uc5b4 \uc778\ucf54\ub529(Byte Pair Encoding, BPE)\uc5d0 \ub300\ud574 \uc790\uc138\ud788 \uc54c\uc544\ubcf4\uaca0\uc2b5\ub2c8\ub2e4. 1. \uc790\uc5f0\uc5b4 \ucc98\ub9ac(NLP)\uc758 \ubc1c\uc804 \uc790\uc5f0\uc5b4 \ucc98\ub9ac\ub294 \ub2e4\uc591\ud55c \ubd84\uc57c\uc5d0\uc11c … \ub354 \ubcf4\uae30 “\ub525 \ub7ec\ub2dd\uc744 \uc774\uc6a9\ud55c \uc790\uc5f0\uc5b4 \ucc98\ub9ac: \ubc14\uc774\ud2b8 \ud398\uc5b4 \uc778\ucf54\ub529 (Byte Pair Encoding, BPE)”<\/span><\/a><\/p>\n","protected":false},"author":1,"featured_media":0,"comment_status":"closed","ping_status":"open","sticky":false,"template":"","format":"standard","meta":{"_jetpack_memberships_contains_paid_content":false,"footnotes":""},"categories":[16],"tags":[],"class_list":["post-25371","post","type-post","status-publish","format-standard","hentry","category-16"],"yoast_head":"\n\ub525 \ub7ec\ub2dd\uc744 \uc774\uc6a9\ud55c \uc790\uc5f0\uc5b4 \ucc98\ub9ac: \ubc14\uc774\ud2b8 \ud398\uc5b4 \uc778\ucf54\ub529 (Byte Pair Encoding, BPE) - \ub77c\uc774\ube0c\uc2a4\ub9c8\ud2b8<\/title>\n<meta name=\"robots\" content=\"index, follow, max-snippet:-1, max-image-preview:large, max-video-preview:-1\" \/>\n<link rel=\"canonical\" href=\"https:\/\/atmokpo.com\/w\/25371\/\" \/>\n<meta property=\"og:locale\" content=\"ko_KR\" \/>\n<meta property=\"og:type\" content=\"article\" \/>\n<meta property=\"og:title\" content=\"\ub525 \ub7ec\ub2dd\uc744 \uc774\uc6a9\ud55c \uc790\uc5f0\uc5b4 \ucc98\ub9ac: \ubc14\uc774\ud2b8 \ud398\uc5b4 \uc778\ucf54\ub529 (Byte Pair Encoding, BPE) - \ub77c\uc774\ube0c\uc2a4\ub9c8\ud2b8\" \/>\n<meta property=\"og:description\" content=\"\uc790\uc5f0\uc5b4 \ucc98\ub9ac\ub294 \ucef4\ud4e8\ud130\uac00 \uc778\uac04\uc758 \uc5b8\uc5b4\ub97c \uc774\ud574\ud558\uace0 \ud574\uc11d\ud558\ub294 \uae30\uc220\ub85c, \uc778\uacf5\uc9c0\ub2a5 \ubc0f \uae30\uacc4 \ud559\uc2b5\uc758 \uc911\uc694\ud55c \ubd84\uc57c \uc911 \ud558\ub098\uc785\ub2c8\ub2e4. \ucd5c\uadfc \uba87 \ub144\uac04 \ub525 \ub7ec\ub2dd \uae30\uc220\uc774 \ubc1c\uc804\ud558\uba74\uc11c \uc790\uc5f0\uc5b4 \ucc98\ub9ac(NLP)\uc758 \uc131\ub2a5\uc774 \ube44\uc57d\uc801\uc73c\ub85c \ud5a5\uc0c1\ub418\uc5c8\uc2b5\ub2c8\ub2e4. \uc774 \uae00\uc5d0\uc11c\ub294 \ub525 \ub7ec\ub2dd\uc744 \ud1b5\ud55c \uc790\uc5f0\uc5b4 \ucc98\ub9ac \uae30\ubc95 \uc911 \ud558\ub098\uc778 \ubc14\uc774\ud2b8 \ud398\uc5b4 \uc778\ucf54\ub529(Byte Pair Encoding, BPE)\uc5d0 \ub300\ud574 \uc790\uc138\ud788 \uc54c\uc544\ubcf4\uaca0\uc2b5\ub2c8\ub2e4. 1. \uc790\uc5f0\uc5b4 \ucc98\ub9ac(NLP)\uc758 \ubc1c\uc804 \uc790\uc5f0\uc5b4 \ucc98\ub9ac\ub294 \ub2e4\uc591\ud55c \ubd84\uc57c\uc5d0\uc11c … \ub354 \ubcf4\uae30 "\ub525 \ub7ec\ub2dd\uc744 \uc774\uc6a9\ud55c \uc790\uc5f0\uc5b4 \ucc98\ub9ac: \ubc14\uc774\ud2b8 \ud398\uc5b4 \uc778\ucf54\ub529 (Byte Pair Encoding, BPE)"\" \/>\n<meta property=\"og:url\" content=\"https:\/\/atmokpo.com\/w\/25371\/\" \/>\n<meta property=\"og:site_name\" content=\"\ub77c\uc774\ube0c\uc2a4\ub9c8\ud2b8\" \/>\n<meta property=\"article:published_time\" content=\"2024-10-26T09:54:31+00:00\" \/>\n<meta property=\"article:modified_time\" content=\"2024-11-26T08:02:00+00:00\" \/>\n<meta name=\"author\" content=\"root\" \/>\n<meta name=\"twitter:card\" content=\"summary_large_image\" \/>\n<meta name=\"twitter:creator\" content=\"@bebubo4\" \/>\n<meta name=\"twitter:site\" content=\"@bebubo4\" \/>\n<meta name=\"twitter:label1\" content=\"\uae00\uc4f4\uc774\" \/>\n\t<meta name=\"twitter:data1\" content=\"root\" \/>\n\t<meta name=\"twitter:label2\" content=\"\uc608\uc0c1 \ub418\ub294 \ud310\ub3c5 \uc2dc\uac04\" \/>\n\t<meta name=\"twitter:data2\" content=\"1\ubd84\" \/>\n<script type=\"application\/ld+json\" class=\"yoast-schema-graph\">{\"@context\":\"https:\/\/schema.org\",\"@graph\":[{\"@type\":\"Article\",\"@id\":\"https:\/\/atmokpo.com\/w\/25371\/#article\",\"isPartOf\":{\"@id\":\"https:\/\/atmokpo.com\/w\/25371\/\"},\"author\":{\"name\":\"root\",\"@id\":\"https:\/\/atmokpo.com\/w\/#\/schema\/person\/91b6b3b138fbba0efb4ae64b1abd81d7\"},\"headline\":\"\ub525 \ub7ec\ub2dd\uc744 \uc774\uc6a9\ud55c \uc790\uc5f0\uc5b4 \ucc98\ub9ac: \ubc14\uc774\ud2b8 \ud398\uc5b4 \uc778\ucf54\ub529 (Byte Pair Encoding, BPE)\",\"datePublished\":\"2024-10-26T09:54:31+00:00\",\"dateModified\":\"2024-11-26T08:02:00+00:00\",\"mainEntityOfPage\":{\"@id\":\"https:\/\/atmokpo.com\/w\/25371\/\"},\"wordCount\":122,\"publisher\":{\"@id\":\"https:\/\/atmokpo.com\/w\/#organization\"},\"articleSection\":[\"\ub525\ub7ec\ub2dd \uc790\uc5f0\uc5b4\ucc98\ub9ac\"],\"inLanguage\":\"ko-KR\"},{\"@type\":\"WebPage\",\"@id\":\"https:\/\/atmokpo.com\/w\/25371\/\",\"url\":\"https:\/\/atmokpo.com\/w\/25371\/\",\"name\":\"\ub525 \ub7ec\ub2dd\uc744 \uc774\uc6a9\ud55c \uc790\uc5f0\uc5b4 \ucc98\ub9ac: \ubc14\uc774\ud2b8 \ud398\uc5b4 \uc778\ucf54\ub529 (Byte Pair Encoding, BPE) - \ub77c\uc774\ube0c\uc2a4\ub9c8\ud2b8\",\"isPartOf\":{\"@id\":\"https:\/\/atmokpo.com\/w\/#website\"},\"datePublished\":\"2024-10-26T09:54:31+00:00\",\"dateModified\":\"2024-11-26T08:02:00+00:00\",\"breadcrumb\":{\"@id\":\"https:\/\/atmokpo.com\/w\/25371\/#breadcrumb\"},\"inLanguage\":\"ko-KR\",\"potentialAction\":[{\"@type\":\"ReadAction\",\"target\":[\"https:\/\/atmokpo.com\/w\/25371\/\"]}]},{\"@type\":\"BreadcrumbList\",\"@id\":\"https:\/\/atmokpo.com\/w\/25371\/#breadcrumb\",\"itemListElement\":[{\"@type\":\"ListItem\",\"position\":1,\"name\":\"\ud648\",\"item\":\"https:\/\/atmokpo.com\/w\/en\/\"},{\"@type\":\"ListItem\",\"position\":2,\"name\":\"\ub525 \ub7ec\ub2dd\uc744 \uc774\uc6a9\ud55c \uc790\uc5f0\uc5b4 \ucc98\ub9ac: \ubc14\uc774\ud2b8 \ud398\uc5b4 \uc778\ucf54\ub529 (Byte Pair Encoding, BPE)\"}]},{\"@type\":\"WebSite\",\"@id\":\"https:\/\/atmokpo.com\/w\/#website\",\"url\":\"https:\/\/atmokpo.com\/w\/\",\"name\":\"\ub77c\uc774\ube0c\uc2a4\ub9c8\ud2b8\",\"description\":\"\",\"publisher\":{\"@id\":\"https:\/\/atmokpo.com\/w\/#organization\"},\"potentialAction\":[{\"@type\":\"SearchAction\",\"target\":{\"@type\":\"EntryPoint\",\"urlTemplate\":\"https:\/\/atmokpo.com\/w\/?s={search_term_string}\"},\"query-input\":{\"@type\":\"PropertyValueSpecification\",\"valueRequired\":true,\"valueName\":\"search_term_string\"}}],\"inLanguage\":\"ko-KR\"},{\"@type\":\"Organization\",\"@id\":\"https:\/\/atmokpo.com\/w\/#organization\",\"name\":\"\ub77c\uc774\ube0c\uc2a4\ub9c8\ud2b8\",\"url\":\"https:\/\/atmokpo.com\/w\/\",\"logo\":{\"@type\":\"ImageObject\",\"inLanguage\":\"ko-KR\",\"@id\":\"https:\/\/atmokpo.com\/w\/#\/schema\/logo\/image\/\",\"url\":\"https:\/\/atmokpo.com\/w\/wp-content\/uploads\/2024\/11\/logo.png\",\"contentUrl\":\"https:\/\/atmokpo.com\/w\/wp-content\/uploads\/2024\/11\/logo.png\",\"width\":400,\"height\":400,\"caption\":\"\ub77c\uc774\ube0c\uc2a4\ub9c8\ud2b8\"},\"image\":{\"@id\":\"https:\/\/atmokpo.com\/w\/#\/schema\/logo\/image\/\"},\"sameAs\":[\"https:\/\/x.com\/bebubo4\"]},{\"@type\":\"Person\",\"@id\":\"https:\/\/atmokpo.com\/w\/#\/schema\/person\/91b6b3b138fbba0efb4ae64b1abd81d7\",\"name\":\"root\",\"image\":{\"@type\":\"ImageObject\",\"inLanguage\":\"ko-KR\",\"@id\":\"https:\/\/atmokpo.com\/w\/#\/schema\/person\/image\/\",\"url\":\"https:\/\/secure.gravatar.com\/avatar\/708197b41fc6435a7ce22d951b25d4a47e9e904270cb1f04682d4f025066f80c?s=96&d=mm&r=g\",\"contentUrl\":\"https:\/\/secure.gravatar.com\/avatar\/708197b41fc6435a7ce22d951b25d4a47e9e904270cb1f04682d4f025066f80c?s=96&d=mm&r=g\",\"caption\":\"root\"},\"sameAs\":[\"http:\/\/atmokpo.com\/w\"],\"url\":\"https:\/\/atmokpo.com\/w\/author\/root\/\"}]}<\/script>\n<!-- \/ Yoast SEO plugin. -->","yoast_head_json":{"title":"\ub525 \ub7ec\ub2dd\uc744 \uc774\uc6a9\ud55c \uc790\uc5f0\uc5b4 \ucc98\ub9ac: \ubc14\uc774\ud2b8 \ud398\uc5b4 \uc778\ucf54\ub529 (Byte Pair Encoding, BPE) - \ub77c\uc774\ube0c\uc2a4\ub9c8\ud2b8","robots":{"index":"index","follow":"follow","max-snippet":"max-snippet:-1","max-image-preview":"max-image-preview:large","max-video-preview":"max-video-preview:-1"},"canonical":"https:\/\/atmokpo.com\/w\/25371\/","og_locale":"ko_KR","og_type":"article","og_title":"\ub525 \ub7ec\ub2dd\uc744 \uc774\uc6a9\ud55c \uc790\uc5f0\uc5b4 \ucc98\ub9ac: \ubc14\uc774\ud2b8 \ud398\uc5b4 \uc778\ucf54\ub529 (Byte Pair Encoding, BPE) - \ub77c\uc774\ube0c\uc2a4\ub9c8\ud2b8","og_description":"\uc790\uc5f0\uc5b4 \ucc98\ub9ac\ub294 \ucef4\ud4e8\ud130\uac00 \uc778\uac04\uc758 \uc5b8\uc5b4\ub97c \uc774\ud574\ud558\uace0 \ud574\uc11d\ud558\ub294 \uae30\uc220\ub85c, \uc778\uacf5\uc9c0\ub2a5 \ubc0f \uae30\uacc4 \ud559\uc2b5\uc758 \uc911\uc694\ud55c \ubd84\uc57c \uc911 \ud558\ub098\uc785\ub2c8\ub2e4. \ucd5c\uadfc \uba87 \ub144\uac04 \ub525 \ub7ec\ub2dd \uae30\uc220\uc774 \ubc1c\uc804\ud558\uba74\uc11c \uc790\uc5f0\uc5b4 \ucc98\ub9ac(NLP)\uc758 \uc131\ub2a5\uc774 \ube44\uc57d\uc801\uc73c\ub85c \ud5a5\uc0c1\ub418\uc5c8\uc2b5\ub2c8\ub2e4. \uc774 \uae00\uc5d0\uc11c\ub294 \ub525 \ub7ec\ub2dd\uc744 \ud1b5\ud55c \uc790\uc5f0\uc5b4 \ucc98\ub9ac \uae30\ubc95 \uc911 \ud558\ub098\uc778 \ubc14\uc774\ud2b8 \ud398\uc5b4 \uc778\ucf54\ub529(Byte Pair Encoding, BPE)\uc5d0 \ub300\ud574 \uc790\uc138\ud788 \uc54c\uc544\ubcf4\uaca0\uc2b5\ub2c8\ub2e4. 1. \uc790\uc5f0\uc5b4 \ucc98\ub9ac(NLP)\uc758 \ubc1c\uc804 \uc790\uc5f0\uc5b4 \ucc98\ub9ac\ub294 \ub2e4\uc591\ud55c \ubd84\uc57c\uc5d0\uc11c … \ub354 \ubcf4\uae30 \"\ub525 \ub7ec\ub2dd\uc744 \uc774\uc6a9\ud55c \uc790\uc5f0\uc5b4 \ucc98\ub9ac: \ubc14\uc774\ud2b8 \ud398\uc5b4 \uc778\ucf54\ub529 (Byte Pair Encoding, BPE)\"","og_url":"https:\/\/atmokpo.com\/w\/25371\/","og_site_name":"\ub77c\uc774\ube0c\uc2a4\ub9c8\ud2b8","article_published_time":"2024-10-26T09:54:31+00:00","article_modified_time":"2024-11-26T08:02:00+00:00","author":"root","twitter_card":"summary_large_image","twitter_creator":"@bebubo4","twitter_site":"@bebubo4","twitter_misc":{"\uae00\uc4f4\uc774":"root","\uc608\uc0c1 \ub418\ub294 \ud310\ub3c5 \uc2dc\uac04":"1\ubd84"},"schema":{"@context":"https:\/\/schema.org","@graph":[{"@type":"Article","@id":"https:\/\/atmokpo.com\/w\/25371\/#article","isPartOf":{"@id":"https:\/\/atmokpo.com\/w\/25371\/"},"author":{"name":"root","@id":"https:\/\/atmokpo.com\/w\/#\/schema\/person\/91b6b3b138fbba0efb4ae64b1abd81d7"},"headline":"\ub525 \ub7ec\ub2dd\uc744 \uc774\uc6a9\ud55c \uc790\uc5f0\uc5b4 \ucc98\ub9ac: \ubc14\uc774\ud2b8 \ud398\uc5b4 \uc778\ucf54\ub529 (Byte Pair Encoding, BPE)","datePublished":"2024-10-26T09:54:31+00:00","dateModified":"2024-11-26T08:02:00+00:00","mainEntityOfPage":{"@id":"https:\/\/atmokpo.com\/w\/25371\/"},"wordCount":122,"publisher":{"@id":"https:\/\/atmokpo.com\/w\/#organization"},"articleSection":["\ub525\ub7ec\ub2dd \uc790\uc5f0\uc5b4\ucc98\ub9ac"],"inLanguage":"ko-KR"},{"@type":"WebPage","@id":"https:\/\/atmokpo.com\/w\/25371\/","url":"https:\/\/atmokpo.com\/w\/25371\/","name":"\ub525 \ub7ec\ub2dd\uc744 \uc774\uc6a9\ud55c \uc790\uc5f0\uc5b4 \ucc98\ub9ac: \ubc14\uc774\ud2b8 \ud398\uc5b4 \uc778\ucf54\ub529 (Byte Pair Encoding, BPE) - \ub77c\uc774\ube0c\uc2a4\ub9c8\ud2b8","isPartOf":{"@id":"https:\/\/atmokpo.com\/w\/#website"},"datePublished":"2024-10-26T09:54:31+00:00","dateModified":"2024-11-26T08:02:00+00:00","breadcrumb":{"@id":"https:\/\/atmokpo.com\/w\/25371\/#breadcrumb"},"inLanguage":"ko-KR","potentialAction":[{"@type":"ReadAction","target":["https:\/\/atmokpo.com\/w\/25371\/"]}]},{"@type":"BreadcrumbList","@id":"https:\/\/atmokpo.com\/w\/25371\/#breadcrumb","itemListElement":[{"@type":"ListItem","position":1,"name":"\ud648","item":"https:\/\/atmokpo.com\/w\/en\/"},{"@type":"ListItem","position":2,"name":"\ub525 \ub7ec\ub2dd\uc744 \uc774\uc6a9\ud55c \uc790\uc5f0\uc5b4 \ucc98\ub9ac: \ubc14\uc774\ud2b8 \ud398\uc5b4 \uc778\ucf54\ub529 (Byte Pair Encoding, BPE)"}]},{"@type":"WebSite","@id":"https:\/\/atmokpo.com\/w\/#website","url":"https:\/\/atmokpo.com\/w\/","name":"\ub77c\uc774\ube0c\uc2a4\ub9c8\ud2b8","description":"","publisher":{"@id":"https:\/\/atmokpo.com\/w\/#organization"},"potentialAction":[{"@type":"SearchAction","target":{"@type":"EntryPoint","urlTemplate":"https:\/\/atmokpo.com\/w\/?s={search_term_string}"},"query-input":{"@type":"PropertyValueSpecification","valueRequired":true,"valueName":"search_term_string"}}],"inLanguage":"ko-KR"},{"@type":"Organization","@id":"https:\/\/atmokpo.com\/w\/#organization","name":"\ub77c\uc774\ube0c\uc2a4\ub9c8\ud2b8","url":"https:\/\/atmokpo.com\/w\/","logo":{"@type":"ImageObject","inLanguage":"ko-KR","@id":"https:\/\/atmokpo.com\/w\/#\/schema\/logo\/image\/","url":"https:\/\/atmokpo.com\/w\/wp-content\/uploads\/2024\/11\/logo.png","contentUrl":"https:\/\/atmokpo.com\/w\/wp-content\/uploads\/2024\/11\/logo.png","width":400,"height":400,"caption":"\ub77c\uc774\ube0c\uc2a4\ub9c8\ud2b8"},"image":{"@id":"https:\/\/atmokpo.com\/w\/#\/schema\/logo\/image\/"},"sameAs":["https:\/\/x.com\/bebubo4"]},{"@type":"Person","@id":"https:\/\/atmokpo.com\/w\/#\/schema\/person\/91b6b3b138fbba0efb4ae64b1abd81d7","name":"root","image":{"@type":"ImageObject","inLanguage":"ko-KR","@id":"https:\/\/atmokpo.com\/w\/#\/schema\/person\/image\/","url":"https:\/\/secure.gravatar.com\/avatar\/708197b41fc6435a7ce22d951b25d4a47e9e904270cb1f04682d4f025066f80c?s=96&d=mm&r=g","contentUrl":"https:\/\/secure.gravatar.com\/avatar\/708197b41fc6435a7ce22d951b25d4a47e9e904270cb1f04682d4f025066f80c?s=96&d=mm&r=g","caption":"root"},"sameAs":["http:\/\/atmokpo.com\/w"],"url":"https:\/\/atmokpo.com\/w\/author\/root\/"}]}},"jetpack_featured_media_url":"","jetpack_sharing_enabled":true,"jetpack-related-posts":[{"id":25381,"url":"https:\/\/atmokpo.com\/w\/25381\/","url_meta":{"origin":25371,"position":0},"title":"\ub525 \ub7ec\ub2dd\uc744 \uc774\uc6a9\ud55c \uc790\uc5f0\uc5b4 \ucc98\ub9ac, \uc11c\ube0c\uc6cc\ub4dc \ud1a0\ud06c\ub098\uc774\uc800","author":"root","date":"2024\ub144 10\uc6d4 26\uc77c","format":false,"excerpt":"\uc791\uc131\uc77c: YYYY-MM-DD \uc791\uc131\uc790: \uc870\uad11\ud615 1. \uc11c\ub860 \uc790\uc5f0\uc5b4 \ucc98\ub9ac\ub294 \uc778\uac04\uc758 \uc5b8\uc5b4\ub97c \ucef4\ud4e8\ud130\uac00 \uc774\ud574\ud558\uace0 \ucc98\ub9ac\ud560 \uc218 \uc788\ub3c4\ub85d \ud558\ub294 \uae30\uc220\uc774\ub2e4. \ucd5c\uadfc \uba87 \ub144 \ub3d9\uc548 \ub525 \ub7ec\ub2dd \uae30\ubc18\uc758 \uc790\uc5f0\uc5b4 \ucc98\ub9ac \uae30\uc220\uc740 \ube44\uc57d\uc801\uc778 \ubc1c\uc804\uc744 \uc774\ub8e8\uc5c8\uc73c\uba70, \ud2b9\ud788 BERT, GPT\uc640 \uac19\uc740 \ub300\ud615 \uc5b8\uc5b4 \ubaa8\ub378\uc740 \ub180\ub77c\uc6b4 \uc131\uacfc\ub97c \uac70\ub450\uc5c8\ub2e4. \uadf8\ub7ec\ub098 \uc774\ub7ec\ud55c \ubaa8\ub378\uc740 \ud559\uc2b5 \ub370\uc774\ud130\uc5d0 \ub530\ub77c \uc131\ub2a5\uc774 \ud06c\uac8c \ub2ec\ub77c\uc9c0\uba70, \ub300\uc6a9\ub7c9\uc758\u2026","rel":"","context":""\ub525\ub7ec\ub2dd \uc790\uc5f0\uc5b4\ucc98\ub9ac"\uc5d0\uc11c","block_context":{"text":"\ub525\ub7ec\ub2dd \uc790\uc5f0\uc5b4\ucc98\ub9ac","link":"https:\/\/atmokpo.com\/w\/category\/%eb%94%a5%eb%9f%ac%eb%8b%9d-%ec%9e%90%ec%97%b0%ec%96%b4%ec%b2%98%eb%a6%ac\/"},"img":{"alt_text":"","src":"","width":0,"height":0},"classes":[]},{"id":25181,"url":"https:\/\/atmokpo.com\/w\/25181\/","url_meta":{"origin":25371,"position":1},"title":"\ub525 \ub7ec\ub2dd\uc744 \uc774\uc6a9\ud55c \uc790\uc5f0\uc5b4 \ucc98\ub9ac\uc640 \uc815\uaddc \ud45c\ud604\uc2dd","author":"root","date":"2024\ub144 10\uc6d4 26\uc77c","format":false,"excerpt":"\uc790\uc5f0\uc5b4 \ucc98\ub9ac\ub294 \uae30\uacc4\uac00 \uc778\uac04\uc758 \uc5b8\uc5b4\ub97c \uc774\ud574\ud558\uace0 \ubd84\uc11d\ud560 \uc218 \uc788\ub3c4\ub85d \ub3d5\ub294 \ucef4\ud4e8\ud130 \uacfc\ud559\uc758 \ud55c \ubd84\uc57c\uc785\ub2c8\ub2e4. \ub525 \ub7ec\ub2dd(deep learning)\uc740 \uc778\uacf5 \uc2e0\uacbd\ub9dd\uc744 \uae30\ubc18\uc73c\ub85c \ud55c \uba38\uc2e0 \ub7ec\ub2dd\uc758 \ud55c \ud615\ud0dc\ub85c, \ub300\ub7c9\uc758 \ub370\uc774\ud130\ub97c \ubd84\uc11d\ud558\uc5ec \ud328\ud134\uc744 \ud559\uc2b5\ud558\ub294 \ub370 \ub9e4\uc6b0 \ud6a8\uacfc\uc801\uc785\ub2c8\ub2e4. \ucd5c\uadfc \uba87 \ub144 \uac04 \uc790\uc5f0\uc5b4 \ucc98\ub9ac \ubd84\uc57c\uc5d0\uc11c\uc758 \ub525 \ub7ec\ub2dd\uc758 \ubc1c\uc804\uc740 \uc8fc\ubaa9\ud560 \ub9cc\ud55c \uc131\uacfc\ub97c \uc774\ub8e8\uc5c8\uace0, \uc774\ub7ec\ud55c \uae30\uc220\ub4e4\uc774 \uc2e4\uc81c\u2026","rel":"","context":""\ub525\ub7ec\ub2dd \uc790\uc5f0\uc5b4\ucc98\ub9ac"\uc5d0\uc11c","block_context":{"text":"\ub525\ub7ec\ub2dd \uc790\uc5f0\uc5b4\ucc98\ub9ac","link":"https:\/\/atmokpo.com\/w\/category\/%eb%94%a5%eb%9f%ac%eb%8b%9d-%ec%9e%90%ec%97%b0%ec%96%b4%ec%b2%98%eb%a6%ac\/"},"img":{"alt_text":"","src":"","width":0,"height":0},"classes":[]},{"id":25283,"url":"https:\/\/atmokpo.com\/w\/25283\/","url_meta":{"origin":25371,"position":2},"title":"\ub525 \ub7ec\ub2dd\uc744 \uc774\uc6a9\ud55c \uc790\uc5f0\uc5b4 \ucc98\ub9ac: RNN\uc744 \uc774\uc6a9\ud55c \ud14d\uc2a4\ud2b8 \uc0dd\uc131","author":"root","date":"2024\ub144 10\uc6d4 26\uc77c","format":false,"excerpt":"\uc791\uc131\uc77c: 2023\ub144 9\uc6d4 15\uc77c \uc791\uc131\uc790: \uc870\uad11\ud615 1. \uc11c\ub860 \uc778\uacf5\uc9c0\ub2a5\uc758 \ubc1c\uc804\uc740 \ub2e4\uc591\ud55c \ubd84\uc57c\uc5d0\uc11c \ud601\uc2e0\uc801\uc778 \ubcc0\ud654\ub97c \uac00\uc838\uc624\uace0 \uc788\uc2b5\ub2c8\ub2e4. \uadf8 \uc911\uc5d0\uc11c\ub3c4 \uc790\uc5f0\uc5b4 \ucc98\ub9ac(NLP)\ub294 \uae30\uacc4\uac00 \uc778\uac04\uc758 \uc5b8\uc5b4\ub97c \uc774\ud574\ud558\uace0 \uc0dd\uc131\ud560 \uc218 \uc788\ub3c4\ub85d \ud558\ub294 \uae30\uc220\ub85c, \ucd5c\uadfc \uba87 \ub144\uac04 \ub9ce\uc740 \uad00\uc2ec\uc744 \ubc1b\uace0 \uc788\uc2b5\ub2c8\ub2e4. \ud2b9\ud788, \ub525 \ub7ec\ub2dd \uae30\uc220\uc744 \ud65c\uc6a9\ud55c \uc790\uc5f0\uc5b4 \ucc98\ub9ac\uc758 \ubc1c\uc804\uc740 \ub9ce\uc740 \uc5f0\uad6c\uc790\uc640 \uac1c\ubc1c\uc790\ub4e4\uc5d0\uac8c \uc0c8\ub85c\uc6b4 \uac00\ub2a5\uc131\uc744 \uc5f4\uc5b4\uc8fc\uc5c8\uc2b5\ub2c8\ub2e4.\u2026","rel":"","context":""\ub525\ub7ec\ub2dd \uc790\uc5f0\uc5b4\ucc98\ub9ac"\uc5d0\uc11c","block_context":{"text":"\ub525\ub7ec\ub2dd \uc790\uc5f0\uc5b4\ucc98\ub9ac","link":"https:\/\/atmokpo.com\/w\/category\/%eb%94%a5%eb%9f%ac%eb%8b%9d-%ec%9e%90%ec%97%b0%ec%96%b4%ec%b2%98%eb%a6%ac\/"},"img":{"alt_text":"","src":"","width":0,"height":0},"classes":[]},{"id":25423,"url":"https:\/\/atmokpo.com\/w\/25423\/","url_meta":{"origin":25371,"position":3},"title":"\ub525 \ub7ec\ub2dd\uc744 \uc774\uc6a9\ud55c \uc790\uc5f0\uc5b4 \ucc98\ub9ac, \ucf54\ub7a9(Colab)\uc5d0\uc11c TPU \uc0ac\uc6a9\ud558\uae30","author":"root","date":"2024\ub144 10\uc6d4 26\uc77c","format":false,"excerpt":"\uc790\uc5f0\uc5b4 \ucc98\ub9ac\ub294 \uc778\uacf5\uc9c0\ub2a5\uc758 \ud55c \ubd84\uc57c\ub85c, \ucef4\ud4e8\ud130\uac00 \uc778\uac04\uc758 \uc5b8\uc5b4\ub97c \uc774\ud574\ud558\uace0 \ucc98\ub9ac\ud560 \uc218 \uc788\ub3c4\ub85d \ud558\ub294 \uae30\uc220\uc785\ub2c8\ub2e4. \ucd5c\uadfc \uba87 \ub144 \ub3d9\uc548 \u27e8\ub525 \ub7ec\ub2dd\u27e9 \uae30\ubc95\uc758 \ubc1c\uc804\uc73c\ub85c \uc790\uc5f0\uc5b4 \ucc98\ub9ac \ubd84\uc57c\ub294 \uad04\ubaa9\ud560 \ub9cc\ud55c \uc131\uacfc\ub97c \uc774\ub8e8\uc5b4 \uc654\uc2b5\ub2c8\ub2e4. \uc774\ubc88 \uae00\uc5d0\uc11c\ub294 \ub525 \ub7ec\ub2dd\uc744 \ud65c\uc6a9\ud55c \uc790\uc5f0\uc5b4 \ucc98\ub9ac \ubaa8\ub378\uc744 Google Colab\uc5d0\uc11c TPU\ub97c \uc774\uc6a9\ud558\uc5ec \ud559\uc2b5\uc2dc\ud0a4\ub294 \ubc29\ubc95\uc5d0 \ub300\ud574 \uc790\uc138\ud788 \uc0b4\ud3b4\ubcf4\uaca0\uc2b5\ub2c8\ub2e4. 1. \uc790\uc5f0\uc5b4 \ucc98\ub9ac(NLP)\u2026","rel":"","context":""\ub525\ub7ec\ub2dd \uc790\uc5f0\uc5b4\ucc98\ub9ac"\uc5d0\uc11c","block_context":{"text":"\ub525\ub7ec\ub2dd \uc790\uc5f0\uc5b4\ucc98\ub9ac","link":"https:\/\/atmokpo.com\/w\/category\/%eb%94%a5%eb%9f%ac%eb%8b%9d-%ec%9e%90%ec%97%b0%ec%96%b4%ec%b2%98%eb%a6%ac\/"},"img":{"alt_text":"","src":"","width":0,"height":0},"classes":[]},{"id":25493,"url":"https:\/\/atmokpo.com\/w\/25493\/","url_meta":{"origin":25371,"position":4},"title":"\ub525 \ub7ec\ub2dd\uc744 \uc774\uc6a9\ud55c \uc790\uc5f0\uc5b4 \ucc98\ub9ac, \uc9c8\uc758 \uc751\ub2f5(Question Answering, QA)","author":"root","date":"2024\ub144 10\uc6d4 26\uc77c","format":false,"excerpt":"\uc791\uc131\uc790: \uc870\uad11\ud615 | \ub0a0\uc9dc: 2024\ub144 11\uc6d4 26\uc77c 1. \uc11c\ub860 \uc790\uc5f0\uc5b4 \ucc98\ub9ac(Natural Language Processing, NLP)\ub294 \uc778\uacf5\uc9c0\ub2a5(AI)\uacfc \ucef4\ud4e8\ud130 \uacfc\ud559\uc758 \ud55c \ubd84\uc57c\ub85c, \ucef4\ud4e8\ud130\uac00 \uc778\uac04\uc758 \uc5b8\uc5b4\ub97c \uc774\ud574\ud558\uace0 \ucc98\ub9ac\ud560 \uc218 \uc788\ub3c4\ub85d \ud558\ub294 \uae30\uc220\uc744 \ud3ec\ud568\ud569\ub2c8\ub2e4. \ud2b9\ud788, \uc9c8\uc758 \uc751\ub2f5 \uc2dc\uc2a4\ud15c\uc740 \uc0ac\uc6a9\uc790\ub85c\ubd80\ud130 \uc790\uc5f0\uc5b4\ub85c \uc785\ub825\ub41c \uc9c8\ubb38\uc744 \uc774\ud574\ud558\uace0, \uadf8\uc5d0 \ub300\ud55c \uc801\uc808\ud55c \ub2f5\ubcc0\uc744 \uc81c\uacf5\ud558\ub294 \uc2dc\uc2a4\ud15c\uc785\ub2c8\ub2e4. \ucd5c\uadfc \uba87 \ub144\uac04 \ub525 \ub7ec\ub2dd\uc758 \ubc1c\uc804\uc740\u2026","rel":"","context":""\ub525\ub7ec\ub2dd \uc790\uc5f0\uc5b4\ucc98\ub9ac"\uc5d0\uc11c","block_context":{"text":"\ub525\ub7ec\ub2dd \uc790\uc5f0\uc5b4\ucc98\ub9ac","link":"https:\/\/atmokpo.com\/w\/category\/%eb%94%a5%eb%9f%ac%eb%8b%9d-%ec%9e%90%ec%97%b0%ec%96%b4%ec%b2%98%eb%a6%ac\/"},"img":{"alt_text":"","src":"","width":0,"height":0},"classes":[]},{"id":25287,"url":"https:\/\/atmokpo.com\/w\/25287\/","url_meta":{"origin":25371,"position":5},"title":"\ub525 \ub7ec\ub2dd\uc744 \uc774\uc6a9\ud55c \uc790\uc5f0\uc5b4 \ucc98\ub9ac: \uc21c\ud658 \uc2e0\uacbd\ub9dd(Recurrent Neural Network)","author":"root","date":"2024\ub144 10\uc6d4 26\uc77c","format":false,"excerpt":"\uc791\uc131\uc790: \uc870\uad11\ud615 | \ub0a0\uc9dc: [\ub0a0\uc9dc] 1. \uc11c\ub860 \uc790\uc5f0\uc5b4 \ucc98\ub9ac(Natural Language Processing, NLP)\ub294 \ucef4\ud4e8\ud130\uac00 \uc778\uac04\uc758 \uc5b8\uc5b4\ub97c \uc774\ud574\ud558\uace0 \ubd84\uc11d\ud558\ub294 \uae30\uc220\uc744 \uc758\ubbf8\ud569\ub2c8\ub2e4. \ub525 \ub7ec\ub2dd\uc758 \ubc1c\uc804\uc73c\ub85c \uc790\uc5f0\uc5b4 \ucc98\ub9ac \ubd84\uc57c\ub294 \ube44\uc57d\uc801\uc778 \ubc1c\uc804\uc744 \uc774\ub8e8\uc5c8\uc73c\uba70, \uadf8 \uc911\uc5d0\uc11c\ub3c4 \uc21c\ud658 \uc2e0\uacbd\ub9dd(Recurrent Neural Network, RNN)\uc740 \uc5b8\uc5b4 \ub370\uc774\ud130\ub97c \ucc98\ub9ac\ud558\ub294 \ub370 \ub9e4\uc6b0 \ud6a8\uacfc\uc801\uc778 \ubaa8\ub378\ub85c \uc8fc\ubaa9\ubc1b\uace0 \uc788\uc2b5\ub2c8\ub2e4. \uc774\ubc88 \uae00\uc5d0\uc11c\ub294 RNN\uc758 \uc6d0\ub9ac, \uad6c\uc870, \uadf8\ub9ac\uace0\u2026","rel":"","context":""\ub525\ub7ec\ub2dd \uc790\uc5f0\uc5b4\ucc98\ub9ac"\uc5d0\uc11c","block_context":{"text":"\ub525\ub7ec\ub2dd \uc790\uc5f0\uc5b4\ucc98\ub9ac","link":"https:\/\/atmokpo.com\/w\/category\/%eb%94%a5%eb%9f%ac%eb%8b%9d-%ec%9e%90%ec%97%b0%ec%96%b4%ec%b2%98%eb%a6%ac\/"},"img":{"alt_text":"","src":"","width":0,"height":0},"classes":[]}],"_links":{"self":[{"href":"https:\/\/atmokpo.com\/w\/wp-json\/wp\/v2\/posts\/25371","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/atmokpo.com\/w\/wp-json\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/atmokpo.com\/w\/wp-json\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/atmokpo.com\/w\/wp-json\/wp\/v2\/users\/1"}],"replies":[{"embeddable":true,"href":"https:\/\/atmokpo.com\/w\/wp-json\/wp\/v2\/comments?post=25371"}],"version-history":[{"count":1,"href":"https:\/\/atmokpo.com\/w\/wp-json\/wp\/v2\/posts\/25371\/revisions"}],"predecessor-version":[{"id":25372,"href":"https:\/\/atmokpo.com\/w\/wp-json\/wp\/v2\/posts\/25371\/revisions\/25372"}],"wp:attachment":[{"href":"https:\/\/atmokpo.com\/w\/wp-json\/wp\/v2\/media?parent=25371"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/atmokpo.com\/w\/wp-json\/wp\/v2\/categories?post=25371"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/atmokpo.com\/w\/wp-json\/wp\/v2\/tags?post=25371"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}