course/pr_1069/ko/chapter1/5.html

<meta charset="utf-8" /><meta name="hf:doc:metadata" content="{&quot;title&quot;:&quot;인코더 모델&quot;,&quot;local&quot;:&quot;인코더-모델&quot;,&quot;sections&quot;:[],&quot;depth&quot;:1}">
		<link href="/docs/course/pr_1069/ko/_app/immutable/assets/0.e3b0c442.css" rel="modulepreload">
		<link rel="modulepreload" href="/docs/course/pr_1069/ko/_app/immutable/entry/start.667ba29b.js">
		<link rel="modulepreload" href="/docs/course/pr_1069/ko/_app/immutable/chunks/scheduler.37c15a92.js">
		<link rel="modulepreload" href="/docs/course/pr_1069/ko/_app/immutable/chunks/singletons.8de3d8e2.js">
		<link rel="modulepreload" href="/docs/course/pr_1069/ko/_app/immutable/chunks/index.18351ede.js">
		<link rel="modulepreload" href="/docs/course/pr_1069/ko/_app/immutable/chunks/paths.6047fff5.js">
		<link rel="modulepreload" href="/docs/course/pr_1069/ko/_app/immutable/entry/app.65e35200.js">
		<link rel="modulepreload" href="/docs/course/pr_1069/ko/_app/immutable/chunks/index.2bf4358c.js">
		<link rel="modulepreload" href="/docs/course/pr_1069/ko/_app/immutable/nodes/0.9169bc8c.js">
		<link rel="modulepreload" href="/docs/course/pr_1069/ko/_app/immutable/chunks/each.e59479a4.js">
		<link rel="modulepreload" href="/docs/course/pr_1069/ko/_app/immutable/nodes/8.5d89f380.js">
		<link rel="modulepreload" href="/docs/course/pr_1069/ko/_app/immutable/chunks/Youtube.1e50a667.js">
		<link rel="modulepreload" href="/docs/course/pr_1069/ko/_app/immutable/chunks/CourseFloatingBanner.9ff4c771.js">
		<link rel="modulepreload" href="/docs/course/pr_1069/ko/_app/immutable/chunks/DocNotebookDropdown.efc1fb7c.js">
		<link rel="modulepreload" href="/docs/course/pr_1069/ko/_app/immutable/chunks/getInferenceSnippets.24b50994.js"><!-- HEAD_svelte-u9bgzb_START --><meta name="hf:doc:metadata" content="{&quot;title&quot;:&quot;인코더 모델&quot;,&quot;local&quot;:&quot;인코더-모델&quot;,&quot;sections&quot;:[],&quot;depth&quot;:1}"><!-- HEAD_svelte-u9bgzb_END -->      <p></p>  <h1 class="relative group"><a id="인코더-모델" class="header-link block pr-1.5 text-lg no-hover:hidden with-hover:absolute with-hover:p-1.5 with-hover:opacity-0 with-hover:group-hover:opacity-100 with-hover:right-full" href="#인코더-모델"><span><svg class="" xmlns="http://www.w3.org/2000/svg" xmlns:xlink="http://www.w3.org/1999/xlink" aria-hidden="true" role="img" width="1em" height="1em" preserveAspectRatio="xMidYMid meet" viewBox="0 0 256 256"><path d="M167.594 88.393a8.001 8.001 0 0 1 0 11.314l-67.882 67.882a8 8 0 1 1-11.314-11.315l67.882-67.881a8.003 8.003 0 0 1 11.314 0zm-28.287 84.86l-28.284 28.284a40 40 0 0 1-56.567-56.567l28.284-28.284a8 8 0 0 0-11.315-11.315l-28.284 28.284a56 56 0 0 0 79.196 79.197l28.285-28.285a8 8 0 1 0-11.315-11.314zM212.852 43.14a56.002 56.002 0 0 0-79.196 0l-28.284 28.284a8 8 0 1 0 11.314 11.314l28.284-28.284a40 40 0 0 1 56.568 56.567l-28.285 28.285a8 8 0 0 0 11.315 11.314l28.284-28.284a56.065 56.065 0 0 0 0-79.196z" fill="currentColor"></path></svg></span></a> <span>인코더 모델</span></h1>  <div class="flex space-x-1 absolute z-10 right-0 top-0"><a href="https://discuss.huggingface.co/t/chapter-1-questions" target="_blank"><img alt="Ask a Question" class="!m-0" src="https://img.shields.io/badge/Ask%20a%20question-ffcb4c.svg?logo=data:image/svg+xml;base64,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"></a>  </div> <iframe class="w-full xl:w-4/6 h-80" src="https://www.youtube-nocookie.com/embed/MUqNwgPjJvQ" title="YouTube video player" frameborder="0" allow="accelerometer; autoplay; clipboard-write; encrypted-media; gyroscope; picture-in-picture" allowfullscreen></iframe> <p data-svelte-h="svelte-fcsfy5">인코더 모델(Encoder models)은 트랜스포머 모델의 인코더만 사용합니다. 각각의 단계에서 어텐션 레이어는 초기 문장의 모든 단어에 액세스 할 수 있습니다. 이러한 모델은 “양방향성(bi-directional)” 어텐션을 지닌 특성이 있다고도 하며 <em>자동 인코딩(auto-enoding) 모델</em>이라고 부릅니다.</p> <p data-svelte-h="svelte-5s30te">이러한 모델은 주어진 문장을 훼손시킨 후(랜덤으로 단어에 마스킹을 하는 방식 등으로) 모델이 원본 문장을 찾아 재구성하게끔 하는 과정을 반복시키는 방식으로 사전 학습을 진행 합니다.</p> <p data-svelte-h="svelte-1xwlvty">인코더 모델은 문장 분류, 개체명 인식(더 넓은 범위에서 단어 분류), 추출 질의 응답 등과 같이 전체 문장에 대한 이해를 요구하는 작업에 특화되어 있습니다.</p> <p data-svelte-h="svelte-hk1lgc">이 계열을 대표하는 모델들은 아래와 같습니다:</p> <ul data-svelte-h="svelte-18kzzol"><li><a href="https://huggingface.co/transformers/model_doc/albert.html" rel="nofollow">ALBERT</a></li> <li><a href="https://huggingface.co/transformers/model_doc/bert.html" rel="nofollow">BERT</a></li> <li><a href="https://huggingface.co/transformers/model_doc/distilbert.html" rel="nofollow">DistilBERT</a></li> <li><a href="https://huggingface.co/transformers/model_doc/electra.html" rel="nofollow">ELECTRA</a></li> <li><a href="https://huggingface.co/transformers/model_doc/roberta.html" rel="nofollow">RoBERTa</a></li></ul> <a class="!text-gray-400 !no-underline text-sm flex items-center not-prose mt-4" href="https://github.com/huggingface/course/blob/main/chapters/ko/chapter1/5.mdx" target="_blank"><span data-svelte-h="svelte-1kd6by1">&lt;</span> <span data-svelte-h="svelte-x0xyl0">&gt;</span> <span data-svelte-h="svelte-1dajgef"><span class="underline ml-1.5">Update</span> on GitHub</span></a>  <p></p> 
			
			<script>
				{
					__sveltekit_5pcgyl = {
						assets: "/docs/course/pr_1069/ko",
						base: "/docs/course/pr_1069/ko",
						env: {}
					};

					const element = document.currentScript.parentElement;

					const data = [null,null];

					Promise.all([
						import("/docs/course/pr_1069/ko/_app/immutable/entry/start.667ba29b.js"),
						import("/docs/course/pr_1069/ko/_app/immutable/entry/app.65e35200.js")
					]).then(([kit, app]) => {
						kit.start(app, element, {
							node_ids: [0, 8],
							data,
							form: null,
							error: null
						});
					});
				}
			</script>