{"id":90,"date":"2025-03-10T12:55:37","date_gmt":"2025-03-10T16:55:37","guid":{"rendered":"https:\/\/businessphysics.ai\/?p=90"},"modified":"2025-03-17T13:53:01","modified_gmt":"2025-03-17T17:53:01","slug":"how-do-llms-understand-words-with-multiple-meanings","status":"publish","type":"post","link":"https:\/\/businessphysics.ai\/es\/how-do-llms-understand-words-with-multiple-meanings\/","title":{"rendered":"\u00bfC\u00f3mo entienden los LLM las palabras con significados m\u00faltiples?"},"content":{"rendered":"
\"\"<\/figure>\n\n\n\n

\u00a1Incorporaciones!<\/strong> Son formas de convertir palabras, frases o incluso documentos completos en representaciones num\u00e9ricas (vectores) que los ordenadores pueden entender. Las incrustaciones traducen el lenguaje humano a una forma que las m\u00e1quinas pueden procesar y analizar f\u00e1cilmente.<\/p>\n\n\n\n

Para entender mejor las incrustaciones, empecemos con una analog\u00eda sencilla. Supongamos que est\u00e1 ordenando libros en una biblioteca. Puede colocar libros de temas similares uno al lado del otro. Por ejemplo, los libros de ciencia en una estanter\u00eda y los de cocina en otra. Las incrustaciones funcionan de forma parecida: colocan palabras o conceptos con un significado similar cerca unos de otros en un espacio multidimensional.<\/p>\n\n\n\n

\n\n\n\n

C\u00f3mo funcionan las incrustaciones (explicado de forma sencilla):<\/h2>\n\n\n\n
    \n
  1. Convierte palabras en n\u00fameros:\n
      \n
    • A cada palabra se le asigna un conjunto \u00fanico de n\u00fameros (un vector). Las palabras con significados similares tienen vectores similares.<\/li>\n<\/ul>\n<\/li>\n\n\n\n
    • Medici\u00f3n de la similitud:\n
        \n
      • Al calcular la distancia entre vectores, los modelos de IA pueden entender si los conceptos o las palabras est\u00e1n relacionados. Vectores m\u00e1s cercanos significan m\u00e1s similitud.<\/li>\n<\/ul>\n<\/li>\n<\/ol>\n\n\n\n

        Ejemplos pr\u00e1cticos de incrustaciones:<\/h2>\n\n\n\n
          \n
        1. B\u00fasqueda sem\u00e1ntica:\n
            \n
          • Cuando se busca un t\u00e9rmino que tiene muchos significados, por ejemplo \"manzana\", va a distinguir entre la empresa y la fruta en funci\u00f3n del contexto.<\/li>\n<\/ul>\n<\/li>\n\n\n\n
          • Sistemas de recomendaci\u00f3n:\n
              \n
            • Plataformas como Amazon o Netflix utilizan incrustaciones para sugerirte art\u00edculos similares a pel\u00edculas o productos que ya has disfrutado.<\/li>\n<\/ul>\n<\/li>\n\n\n\n
            • Segmentaci\u00f3n de clientes:\n
                \n
              • Agrupar a los clientes en funci\u00f3n de su comportamiento o intereses para mejorar su experiencia y permitir un marketing personalizado.<\/li>\n<\/ul>\n<\/li>\n<\/ol>\n\n\n\n

                Valor empresarial de las incrustaciones:<\/h2>\n\n\n\n
                  \n
                • Mejorar la eficacia<\/strong> para recuperar r\u00e1pidamente la informaci\u00f3n pertinente.<\/li>\n\n\n\n
                • Personalizar las recomendaciones<\/strong>Mejorar la satisfacci\u00f3n y el compromiso de los clientes.<\/li>\n\n\n\n
                • Profundizar en la informaci\u00f3n<\/strong> en el comportamiento de los clientes mediante una agrupaci\u00f3n eficaz de los datos.<\/li>\n<\/ul>\n\n\n\n
                  \n\n\n\n

                  Entender las incrustaciones ayuda a aprovechar la IA Generativa de forma m\u00e1s eficaz. Como hemos visto, las incrustaciones son muy potentes y ayudan a las empresas a tomar decisiones m\u00e1s informadas basadas en datos. Espero que este art\u00edculo te haya sido \u00fatil para comprender mejor las incrustaciones en la IA Generativa.<\/p>","protected":false},"excerpt":{"rendered":"

                  Embeddings! They are ways to convert words, sentences or even full fledged documents into numerical representations (vectors) that computers can understand. You can think of embeddings as translating human language into a form that machines can easily process and analyze. To better understand embeddings, let\u2019s start with a simple analogy. Let\u2019s say you are arranging […]<\/p>\n","protected":false},"author":2,"featured_media":0,"comment_status":"open","ping_status":"open","sticky":false,"template":"","format":"standard","meta":{"footnotes":""},"categories":[9],"tags":[21,22,18,20,23,19,11,24],"class_list":["post-90","post","type-post","status-publish","format-standard","hentry","category-ai-article","tag-bert","tag-contextual-word-representations","tag-embeddings","tag-gpt","tag-semantic-understanding","tag-transformers","tag-understanding-ai","tag-word-embeddings"],"yoast_head":"\nHow Do LLMs Understand Words with Multiple Meanings? - Business Physics AI Lab<\/title>\n<meta name=\"description\" content=\"What trick do LLMs use to differentiate between two words that have a similar meaning ? Embeddings. How do they work ? Find out in this short article !\" \/>\n<meta name=\"robots\" content=\"index, follow, max-snippet:-1, max-image-preview:large, max-video-preview:-1\" \/>\n<link rel=\"canonical\" href=\"https:\/\/businessphysics.ai\/es\/how-do-llms-understand-words-with-multiple-meanings\/\" \/>\n<meta property=\"og:locale\" content=\"es_MX\" \/>\n<meta property=\"og:type\" content=\"article\" \/>\n<meta property=\"og:title\" content=\"How Do LLMs Understand Words with Multiple Meanings? - Business Physics AI Lab\" \/>\n<meta property=\"og:description\" content=\"What trick do LLMs use to differentiate between two words that have a similar meaning ? Embeddings. How do they work ? Find out in this short article !\" \/>\n<meta property=\"og:url\" content=\"https:\/\/businessphysics.ai\/es\/how-do-llms-understand-words-with-multiple-meanings\/\" \/>\n<meta property=\"og:site_name\" content=\"Business Physics AI Lab\" \/>\n<meta property=\"article:published_time\" content=\"2025-03-10T16:55:37+00:00\" \/>\n<meta property=\"article:modified_time\" content=\"2025-03-17T17:53:01+00:00\" \/>\n<meta property=\"og:image\" content=\"https:\/\/businessphysics.ai\/wp-content\/uploads\/2025\/03\/embeddings-1.png\" \/>\n\t<meta property=\"og:image:width\" content=\"512\" \/>\n\t<meta property=\"og:image:height\" content=\"512\" \/>\n\t<meta property=\"og:image:type\" content=\"image\/png\" \/>\n<meta name=\"author\" content=\"Thomas Bedard\" \/>\n<meta name=\"twitter:card\" content=\"summary_large_image\" \/>\n<meta name=\"twitter:label1\" content=\"Escrito por\" \/>\n\t<meta name=\"twitter:data1\" content=\"Thomas Bedard\" \/>\n\t<meta name=\"twitter:label2\" content=\"Tiempo de lectura\" \/>\n\t<meta name=\"twitter:data2\" content=\"2 minutos\" \/>\n<script type=\"application\/ld+json\" class=\"yoast-schema-graph\">{\"@context\":\"https:\\\/\\\/schema.org\",\"@graph\":[{\"@type\":\"Article\",\"@id\":\"https:\\\/\\\/businessphysics.ai\\\/how-do-llms-understand-words-with-multiple-meanings\\\/#article\",\"isPartOf\":{\"@id\":\"https:\\\/\\\/businessphysics.ai\\\/how-do-llms-understand-words-with-multiple-meanings\\\/\"},\"author\":{\"name\":\"Thomas Bedard\",\"@id\":\"https:\\\/\\\/businessphysics.ai\\\/#\\\/schema\\\/person\\\/337b2d796da9445d118014b3f47fd0f9\"},\"headline\":\"How Do LLMs Understand Words with Multiple Meanings?\",\"datePublished\":\"2025-03-10T16:55:37+00:00\",\"dateModified\":\"2025-03-17T17:53:01+00:00\",\"mainEntityOfPage\":{\"@id\":\"https:\\\/\\\/businessphysics.ai\\\/how-do-llms-understand-words-with-multiple-meanings\\\/\"},\"wordCount\":310,\"commentCount\":0,\"publisher\":{\"@id\":\"https:\\\/\\\/businessphysics.ai\\\/#organization\"},\"image\":{\"@id\":\"https:\\\/\\\/businessphysics.ai\\\/how-do-llms-understand-words-with-multiple-meanings\\\/#primaryimage\"},\"thumbnailUrl\":\"https:\\\/\\\/businessphysics.ai\\\/wp-content\\\/uploads\\\/2025\\\/03\\\/embeddings-1.png\",\"keywords\":[\"Bert\",\"Contextual Word Representations\",\"Embeddings\",\"GPT\",\"Semantic Understanding\",\"Transformers\",\"Understanding AI\",\"Word Embeddings\"],\"articleSection\":[\"AI Article\"],\"inLanguage\":\"es\",\"potentialAction\":[{\"@type\":\"CommentAction\",\"name\":\"Comment\",\"target\":[\"https:\\\/\\\/businessphysics.ai\\\/how-do-llms-understand-words-with-multiple-meanings\\\/#respond\"]}]},{\"@type\":\"WebPage\",\"@id\":\"https:\\\/\\\/businessphysics.ai\\\/how-do-llms-understand-words-with-multiple-meanings\\\/\",\"url\":\"https:\\\/\\\/businessphysics.ai\\\/how-do-llms-understand-words-with-multiple-meanings\\\/\",\"name\":\"How Do LLMs Understand Words with Multiple Meanings? - Business Physics AI Lab\",\"isPartOf\":{\"@id\":\"https:\\\/\\\/businessphysics.ai\\\/#website\"},\"primaryImageOfPage\":{\"@id\":\"https:\\\/\\\/businessphysics.ai\\\/how-do-llms-understand-words-with-multiple-meanings\\\/#primaryimage\"},\"image\":{\"@id\":\"https:\\\/\\\/businessphysics.ai\\\/how-do-llms-understand-words-with-multiple-meanings\\\/#primaryimage\"},\"thumbnailUrl\":\"https:\\\/\\\/businessphysics.ai\\\/wp-content\\\/uploads\\\/2025\\\/03\\\/embeddings-1.png\",\"datePublished\":\"2025-03-10T16:55:37+00:00\",\"dateModified\":\"2025-03-17T17:53:01+00:00\",\"description\":\"What trick do LLMs use to differentiate between two words that have a similar meaning ? Embeddings. How do they work ? Find out in this short article !\",\"breadcrumb\":{\"@id\":\"https:\\\/\\\/businessphysics.ai\\\/how-do-llms-understand-words-with-multiple-meanings\\\/#breadcrumb\"},\"inLanguage\":\"es\",\"potentialAction\":[{\"@type\":\"ReadAction\",\"target\":[\"https:\\\/\\\/businessphysics.ai\\\/how-do-llms-understand-words-with-multiple-meanings\\\/\"]}]},{\"@type\":\"ImageObject\",\"inLanguage\":\"es\",\"@id\":\"https:\\\/\\\/businessphysics.ai\\\/how-do-llms-understand-words-with-multiple-meanings\\\/#primaryimage\",\"url\":\"https:\\\/\\\/businessphysics.ai\\\/wp-content\\\/uploads\\\/2025\\\/03\\\/embeddings-1.png\",\"contentUrl\":\"https:\\\/\\\/businessphysics.ai\\\/wp-content\\\/uploads\\\/2025\\\/03\\\/embeddings-1.png\"},{\"@type\":\"BreadcrumbList\",\"@id\":\"https:\\\/\\\/businessphysics.ai\\\/how-do-llms-understand-words-with-multiple-meanings\\\/#breadcrumb\",\"itemListElement\":[{\"@type\":\"ListItem\",\"position\":1,\"name\":\"Home\",\"item\":\"https:\\\/\\\/businessphysics.ai\\\/\"},{\"@type\":\"ListItem\",\"position\":2,\"name\":\"How Do LLMs Understand Words with Multiple Meanings?\"}]},{\"@type\":\"WebSite\",\"@id\":\"https:\\\/\\\/businessphysics.ai\\\/#website\",\"url\":\"https:\\\/\\\/businessphysics.ai\\\/\",\"name\":\"Business Physics AI Lab\",\"description\":\"About the Founder: Professor Thomas Hormaza Dow fosters an environment where research meets application, and where interns, researchers, and industry leaders collaborate to unlock new frontiers.\",\"publisher\":{\"@id\":\"https:\\\/\\\/businessphysics.ai\\\/#organization\"},\"potentialAction\":[{\"@type\":\"SearchAction\",\"target\":{\"@type\":\"EntryPoint\",\"urlTemplate\":\"https:\\\/\\\/businessphysics.ai\\\/?s={search_term_string}\"},\"query-input\":{\"@type\":\"PropertyValueSpecification\",\"valueRequired\":true,\"valueName\":\"search_term_string\"}}],\"inLanguage\":\"es\"},{\"@type\":\"Organization\",\"@id\":\"https:\\\/\\\/businessphysics.ai\\\/#organization\",\"name\":\"Business Physics AI Lab\",\"url\":\"https:\\\/\\\/businessphysics.ai\\\/\",\"logo\":{\"@type\":\"ImageObject\",\"inLanguage\":\"es\",\"@id\":\"https:\\\/\\\/businessphysics.ai\\\/#\\\/schema\\\/logo\\\/image\\\/\",\"url\":\"https:\\\/\\\/businessphysics.ai\\\/wp-content\\\/uploads\\\/2025\\\/01\\\/business-physics-logo-large-720.jpg\",\"contentUrl\":\"https:\\\/\\\/businessphysics.ai\\\/wp-content\\\/uploads\\\/2025\\\/01\\\/business-physics-logo-large-720.jpg\",\"width\":720,\"height\":720,\"caption\":\"Business Physics AI Lab\"},\"image\":{\"@id\":\"https:\\\/\\\/businessphysics.ai\\\/#\\\/schema\\\/logo\\\/image\\\/\"}},{\"@type\":\"Person\",\"@id\":\"https:\\\/\\\/businessphysics.ai\\\/#\\\/schema\\\/person\\\/337b2d796da9445d118014b3f47fd0f9\",\"name\":\"Thomas Bedard\",\"image\":{\"@type\":\"ImageObject\",\"inLanguage\":\"es\",\"@id\":\"https:\\\/\\\/secure.gravatar.com\\\/avatar\\\/6b5f80a3d129991d23276ed930ddd1bd960279e44a5e67a61e379b2b130493a9?s=96&d=mm&r=g\",\"url\":\"https:\\\/\\\/secure.gravatar.com\\\/avatar\\\/6b5f80a3d129991d23276ed930ddd1bd960279e44a5e67a61e379b2b130493a9?s=96&d=mm&r=g\",\"contentUrl\":\"https:\\\/\\\/secure.gravatar.com\\\/avatar\\\/6b5f80a3d129991d23276ed930ddd1bd960279e44a5e67a61e379b2b130493a9?s=96&d=mm&r=g\",\"caption\":\"Thomas Bedard\"},\"url\":\"https:\\\/\\\/businessphysics.ai\\\/es\\\/author\\\/thomas-bedard\\\/\"}]}<\/script>\n<!-- \/ Yoast SEO plugin. -->","yoast_head_json":{"title":"How Do LLMs Understand Words with Multiple Meanings? - Business Physics AI Lab","description":"What trick do LLMs use to differentiate between two words that have a similar meaning ? Embeddings. How do they work ? Find out in this short article !","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:\/\/businessphysics.ai\/es\/how-do-llms-understand-words-with-multiple-meanings\/","og_locale":"es_MX","og_type":"article","og_title":"How Do LLMs Understand Words with Multiple Meanings? - Business Physics AI Lab","og_description":"What trick do LLMs use to differentiate between two words that have a similar meaning ? Embeddings. How do they work ? Find out in this short article !","og_url":"https:\/\/businessphysics.ai\/es\/how-do-llms-understand-words-with-multiple-meanings\/","og_site_name":"Business Physics AI Lab","article_published_time":"2025-03-10T16:55:37+00:00","article_modified_time":"2025-03-17T17:53:01+00:00","og_image":[{"width":512,"height":512,"url":"https:\/\/businessphysics.ai\/wp-content\/uploads\/2025\/03\/embeddings-1.png","type":"image\/png"}],"author":"Thomas Bedard","twitter_card":"summary_large_image","twitter_misc":{"Escrito por":"Thomas Bedard","Tiempo de lectura":"2 minutos"},"schema":{"@context":"https:\/\/schema.org","@graph":[{"@type":"Article","@id":"https:\/\/businessphysics.ai\/how-do-llms-understand-words-with-multiple-meanings\/#article","isPartOf":{"@id":"https:\/\/businessphysics.ai\/how-do-llms-understand-words-with-multiple-meanings\/"},"author":{"name":"Thomas Bedard","@id":"https:\/\/businessphysics.ai\/#\/schema\/person\/337b2d796da9445d118014b3f47fd0f9"},"headline":"How Do LLMs Understand Words with Multiple Meanings?","datePublished":"2025-03-10T16:55:37+00:00","dateModified":"2025-03-17T17:53:01+00:00","mainEntityOfPage":{"@id":"https:\/\/businessphysics.ai\/how-do-llms-understand-words-with-multiple-meanings\/"},"wordCount":310,"commentCount":0,"publisher":{"@id":"https:\/\/businessphysics.ai\/#organization"},"image":{"@id":"https:\/\/businessphysics.ai\/how-do-llms-understand-words-with-multiple-meanings\/#primaryimage"},"thumbnailUrl":"https:\/\/businessphysics.ai\/wp-content\/uploads\/2025\/03\/embeddings-1.png","keywords":["Bert","Contextual Word Representations","Embeddings","GPT","Semantic Understanding","Transformers","Understanding AI","Word Embeddings"],"articleSection":["AI Article"],"inLanguage":"es","potentialAction":[{"@type":"CommentAction","name":"Comment","target":["https:\/\/businessphysics.ai\/how-do-llms-understand-words-with-multiple-meanings\/#respond"]}]},{"@type":"WebPage","@id":"https:\/\/businessphysics.ai\/how-do-llms-understand-words-with-multiple-meanings\/","url":"https:\/\/businessphysics.ai\/how-do-llms-understand-words-with-multiple-meanings\/","name":"How Do LLMs Understand Words with Multiple Meanings? - Business Physics AI Lab","isPartOf":{"@id":"https:\/\/businessphysics.ai\/#website"},"primaryImageOfPage":{"@id":"https:\/\/businessphysics.ai\/how-do-llms-understand-words-with-multiple-meanings\/#primaryimage"},"image":{"@id":"https:\/\/businessphysics.ai\/how-do-llms-understand-words-with-multiple-meanings\/#primaryimage"},"thumbnailUrl":"https:\/\/businessphysics.ai\/wp-content\/uploads\/2025\/03\/embeddings-1.png","datePublished":"2025-03-10T16:55:37+00:00","dateModified":"2025-03-17T17:53:01+00:00","description":"What trick do LLMs use to differentiate between two words that have a similar meaning ? Embeddings. How do they work ? Find out in this short article !","breadcrumb":{"@id":"https:\/\/businessphysics.ai\/how-do-llms-understand-words-with-multiple-meanings\/#breadcrumb"},"inLanguage":"es","potentialAction":[{"@type":"ReadAction","target":["https:\/\/businessphysics.ai\/how-do-llms-understand-words-with-multiple-meanings\/"]}]},{"@type":"ImageObject","inLanguage":"es","@id":"https:\/\/businessphysics.ai\/how-do-llms-understand-words-with-multiple-meanings\/#primaryimage","url":"https:\/\/businessphysics.ai\/wp-content\/uploads\/2025\/03\/embeddings-1.png","contentUrl":"https:\/\/businessphysics.ai\/wp-content\/uploads\/2025\/03\/embeddings-1.png"},{"@type":"BreadcrumbList","@id":"https:\/\/businessphysics.ai\/how-do-llms-understand-words-with-multiple-meanings\/#breadcrumb","itemListElement":[{"@type":"ListItem","position":1,"name":"Home","item":"https:\/\/businessphysics.ai\/"},{"@type":"ListItem","position":2,"name":"How Do LLMs Understand Words with Multiple Meanings?"}]},{"@type":"WebSite","@id":"https:\/\/businessphysics.ai\/#website","url":"https:\/\/businessphysics.ai\/","name":"Laboratorio de Inteligencia Artificial","description":"Sobre el fundador: El profesor Thomas Hormaza Dow fomenta un entorno en el que la investigaci\u00f3n se encuentra con la aplicaci\u00f3n, y en el que becarios, investigadores y l\u00edderes de la industria colaboran para desvelar nuevas fronteras.","publisher":{"@id":"https:\/\/businessphysics.ai\/#organization"},"potentialAction":[{"@type":"SearchAction","target":{"@type":"EntryPoint","urlTemplate":"https:\/\/businessphysics.ai\/?s={search_term_string}"},"query-input":{"@type":"PropertyValueSpecification","valueRequired":true,"valueName":"search_term_string"}}],"inLanguage":"es"},{"@type":"Organization","@id":"https:\/\/businessphysics.ai\/#organization","name":"Laboratorio de Inteligencia Artificial","url":"https:\/\/businessphysics.ai\/","logo":{"@type":"ImageObject","inLanguage":"es","@id":"https:\/\/businessphysics.ai\/#\/schema\/logo\/image\/","url":"https:\/\/businessphysics.ai\/wp-content\/uploads\/2025\/01\/business-physics-logo-large-720.jpg","contentUrl":"https:\/\/businessphysics.ai\/wp-content\/uploads\/2025\/01\/business-physics-logo-large-720.jpg","width":720,"height":720,"caption":"Business Physics AI Lab"},"image":{"@id":"https:\/\/businessphysics.ai\/#\/schema\/logo\/image\/"}},{"@type":"Person","@id":"https:\/\/businessphysics.ai\/#\/schema\/person\/337b2d796da9445d118014b3f47fd0f9","name":"Thomas Bedard","image":{"@type":"ImageObject","inLanguage":"es","@id":"https:\/\/secure.gravatar.com\/avatar\/6b5f80a3d129991d23276ed930ddd1bd960279e44a5e67a61e379b2b130493a9?s=96&d=mm&r=g","url":"https:\/\/secure.gravatar.com\/avatar\/6b5f80a3d129991d23276ed930ddd1bd960279e44a5e67a61e379b2b130493a9?s=96&d=mm&r=g","contentUrl":"https:\/\/secure.gravatar.com\/avatar\/6b5f80a3d129991d23276ed930ddd1bd960279e44a5e67a61e379b2b130493a9?s=96&d=mm&r=g","caption":"Thomas Bedard"},"url":"https:\/\/businessphysics.ai\/es\/author\/thomas-bedard\/"}]}},"_links":{"self":[{"href":"https:\/\/businessphysics.ai\/es\/wp-json\/wp\/v2\/posts\/90","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/businessphysics.ai\/es\/wp-json\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/businessphysics.ai\/es\/wp-json\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/businessphysics.ai\/es\/wp-json\/wp\/v2\/users\/2"}],"replies":[{"embeddable":true,"href":"https:\/\/businessphysics.ai\/es\/wp-json\/wp\/v2\/comments?post=90"}],"version-history":[{"count":3,"href":"https:\/\/businessphysics.ai\/es\/wp-json\/wp\/v2\/posts\/90\/revisions"}],"predecessor-version":[{"id":115,"href":"https:\/\/businessphysics.ai\/es\/wp-json\/wp\/v2\/posts\/90\/revisions\/115"}],"wp:attachment":[{"href":"https:\/\/businessphysics.ai\/es\/wp-json\/wp\/v2\/media?parent=90"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/businessphysics.ai\/es\/wp-json\/wp\/v2\/categories?post=90"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/businessphysics.ai\/es\/wp-json\/wp\/v2\/tags?post=90"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}