{"id":159494,"date":"2022-05-17T14:50:13","date_gmt":"2022-05-17T13:50:13","guid":{"rendered":"https:\/\/multi.datascientest.com\/?p=159494"},"modified":"2023-10-30T17:15:37","modified_gmt":"2023-10-30T16:15:37","slug":"nlp-word-embedding-word2vec-es","status":"publish","type":"post","link":"https:\/\/datascientest.com\/es\/nlp-word-embedding-word2vec-es","title":{"rendered":"Word2vec : NLP y Word Embedding"},"content":{"rendered":"\t\t<div data-elementor-type=\"wp-post\" data-elementor-id=\"159494\" class=\"elementor elementor-159494\" data-elementor-post-type=\"post\">\n\t\t\t\t\t\t\t\t\t<section class=\"elementor-section elementor-top-section elementor-element elementor-element-8f2c54a elementor-section-boxed elementor-section-height-default elementor-section-height-default\" data-id=\"8f2c54a\" data-element_type=\"section\">\n\t\t\t\t\t\t<div class=\"elementor-container elementor-column-gap-default\">\n\t\t\t\t\t<div class=\"elementor-column elementor-col-100 elementor-top-column elementor-element elementor-element-cbba665\" data-id=\"cbba665\" data-element_type=\"column\">\n\t\t\t<div class=\"elementor-widget-wrap elementor-element-populated\">\n\t\t\t\t\t\t\t\t<div class=\"elementor-element elementor-element-1acb6cb elementor-widget elementor-widget-text-editor\" data-id=\"1acb6cb\" data-element_type=\"widget\" data-widget_type=\"text-editor.default\">\n\t\t\t\t<div class=\"elementor-widget-container\">\n\t\t\t<style>\/*! elementor - v3.15.0 - 02-08-2023 *\/\n.elementor-widget-text-editor.elementor-drop-cap-view-stacked .elementor-drop-cap{background-color:#69727d;color:#fff}.elementor-widget-text-editor.elementor-drop-cap-view-framed .elementor-drop-cap{color:#69727d;border:3px solid;background-color:transparent}.elementor-widget-text-editor:not(.elementor-drop-cap-view-default) .elementor-drop-cap{margin-top:8px}.elementor-widget-text-editor:not(.elementor-drop-cap-view-default) .elementor-drop-cap-letter{width:1em;height:1em}.elementor-widget-text-editor .elementor-drop-cap{float:left;text-align:center;line-height:1;font-size:50px}.elementor-widget-text-editor .elementor-drop-cap-letter{display:inline-block}<\/style>\t\t\t\t<p><strong>El Word Embedding designa un conjunto de m\u00e9todos de aprendizaje que pretende representar las palabras de un texto mediante vectores de n\u00fameros reales. Hoy vamos a presentarte la 3.\u00aa parte de nuestro dosier NLP.<\/strong><\/p>\t\t\t\t\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t\t\t\t<\/div>\n\t\t<\/div>\n\t\t\t\t\t\t\t<\/div>\n\t\t<\/section>\n\t\t\t\t<section class=\"elementor-section elementor-top-section elementor-element elementor-element-c4de547 elementor-section-boxed elementor-section-height-default elementor-section-height-default\" data-id=\"c4de547\" data-element_type=\"section\">\n\t\t\t\t\t\t<div class=\"elementor-container elementor-column-gap-default\">\n\t\t\t\t\t<div class=\"elementor-column elementor-col-100 elementor-top-column elementor-element elementor-element-923fe37\" data-id=\"923fe37\" data-element_type=\"column\">\n\t\t\t<div class=\"elementor-widget-wrap elementor-element-populated\">\n\t\t\t\t\t\t\t\t<div class=\"elementor-element elementor-element-1a82bf0 elementor-widget elementor-widget-text-editor\" data-id=\"1a82bf0\" data-element_type=\"widget\" data-widget_type=\"text-editor.default\">\n\t\t\t\t<div class=\"elementor-widget-container\">\n\t\t\t\t\t\t\t<p><span style=\"font-weight: 400;\">Esta secci\u00f3n pretende explicar c\u00f3mo funciona el famoso <\/span><b>algoritmo Word2vec<\/b> <b>en Python<\/b><span style=\"font-weight: 400;\"> y su implementaci\u00f3n.<\/span><\/p>\t\t\t\t\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t\t\t\t<\/div>\n\t\t<\/div>\n\t\t\t\t\t\t\t<\/div>\n\t\t<\/section>\n\t\t\t\t<section class=\"elementor-section elementor-top-section elementor-element elementor-element-5f78904 elementor-section-boxed elementor-section-height-default elementor-section-height-default\" data-id=\"5f78904\" data-element_type=\"section\">\n\t\t\t\t\t\t<div class=\"elementor-container elementor-column-gap-default\">\n\t\t\t\t\t<div class=\"elementor-column elementor-col-100 elementor-top-column elementor-element elementor-element-43a2956\" data-id=\"43a2956\" data-element_type=\"column\">\n\t\t\t<div class=\"elementor-widget-wrap elementor-element-populated\">\n\t\t\t\t\t\t\t\t<div class=\"elementor-element elementor-element-697dbf8 elementor-widget elementor-widget-menu-anchor\" data-id=\"697dbf8\" data-element_type=\"widget\" data-widget_type=\"menu-anchor.default\">\n\t\t\t\t<div class=\"elementor-widget-container\">\n\t\t\t<style>\/*! elementor - v3.15.0 - 02-08-2023 *\/\nbody.elementor-page .elementor-widget-menu-anchor{margin-bottom:0}<\/style>\t\t<div id=\"wordembedding\" class=\"elementor-menu-anchor\"><\/div>\n\t\t\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t\t\t<div class=\"elementor-element elementor-element-955f284 elementor-widget elementor-widget-heading\" data-id=\"955f284\" data-element_type=\"widget\" data-widget_type=\"heading.default\">\n\t\t\t\t<div class=\"elementor-widget-container\">\n\t\t\t<style>\/*! elementor - v3.15.0 - 02-08-2023 *\/\n.elementor-heading-title{padding:0;margin:0;line-height:1}.elementor-widget-heading .elementor-heading-title[class*=elementor-size-]>a{color:inherit;font-size:inherit;line-height:inherit}.elementor-widget-heading .elementor-heading-title.elementor-size-small{font-size:15px}.elementor-widget-heading .elementor-heading-title.elementor-size-medium{font-size:19px}.elementor-widget-heading .elementor-heading-title.elementor-size-large{font-size:29px}.elementor-widget-heading .elementor-heading-title.elementor-size-xl{font-size:39px}.elementor-widget-heading .elementor-heading-title.elementor-size-xxl{font-size:59px}<\/style><h2 class=\"elementor-heading-title elementor-size-default\">Word Embedding<\/h2>\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t\t\t<div class=\"elementor-element elementor-element-8577d1d elementor-widget elementor-widget-text-editor\" data-id=\"8577d1d\" data-element_type=\"widget\" data-widget_type=\"text-editor.default\">\n\t\t\t\t<div class=\"elementor-widget-container\">\n\t\t\t\t\t\t\t<blockquote><p><i><span style=\"font-weight: 400;\">Como recordatorio, el <a href=\"https:\/\/datascientest.com\/es\/word-embedding-es\">Word Embedding<\/a> es capaz <\/span><\/i><b><i>de capturar el contexto, la similitud sem\u00e1ntica y sint\u00e1ctica (g\u00e9nero, sin\u00f3nimos, etc.) de una palabra reduciendo su dimensi\u00f3n.<\/i><\/b><\/p><\/blockquote><p><span style=\"font-weight: 400;\">Por ejemplo, cabr\u00eda esperar que las palabras \u00abnotable\u00bb y \u00abadmirable\u00bb estuvieran representadas por vectores relativamente cercanos en el espacio vectorial donde se definen estos vectores.<\/span><\/p><p><span style=\"font-weight: 400;\">El m\u00e9todo de embedding que se usa habitualmente para reducir la dimensi\u00f3n de un vector consiste en utilizar el resultado que devuelve una capa densa, es decir, multiplicar una matriz de embedding W por la representaci\u00f3n \u00abone hot\u00bb de la palabra :<\/span><\/p>\t\t\t\t\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t\t\t<div class=\"elementor-element elementor-element-627376e elementor-widget elementor-widget-image\" data-id=\"627376e\" data-element_type=\"widget\" data-widget_type=\"image.default\">\n\t\t\t\t<div class=\"elementor-widget-container\">\n\t\t\t<style>\/*! elementor - v3.15.0 - 02-08-2023 *\/\n.elementor-widget-image{text-align:center}.elementor-widget-image a{display:inline-block}.elementor-widget-image a img[src$=\".svg\"]{width:48px}.elementor-widget-image img{vertical-align:middle;display:inline-block}<\/style>\t\t\t\t\t\t\t\t\t\t\t\t<img decoding=\"async\" width=\"260\" height=\"144\" src=\"https:\/\/datascientest.com\/es\/files\/2020\/09\/Capture-de\u0301cran-2020-09-18-a\u0300-09.23.47.png\" class=\"attachment-medium_large size-medium_large wp-image-9721\" alt=\"Word2vec\" \/>\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t\t\t<div class=\"elementor-element elementor-element-70817f2 elementor-widget elementor-widget-text-editor\" data-id=\"70817f2\" data-element_type=\"widget\" data-widget_type=\"text-editor.default\">\n\t\t\t\t<div class=\"elementor-widget-container\">\n\t\t\t\t\t\t\t<p><span style=\"font-weight: 400;\">En forma vectorial :<\/span><\/p>\t\t\t\t\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t\t\t<div class=\"elementor-element elementor-element-01aaa82 elementor-widget elementor-widget-image\" data-id=\"01aaa82\" data-element_type=\"widget\" data-widget_type=\"image.default\">\n\t\t\t\t<div class=\"elementor-widget-container\">\n\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t<img decoding=\"async\" width=\"278\" height=\"78\" src=\"https:\/\/datascientest.com\/es\/files\/2020\/09\/Capture-de\u0301cran-2020-09-18-a\u0300-09.23.58.png\" class=\"attachment-medium_large size-medium_large wp-image-9719\" alt=\"Word2vec\" \/>\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t\t\t<div class=\"elementor-element elementor-element-3ff51e9 elementor-widget elementor-widget-image\" data-id=\"3ff51e9\" data-element_type=\"widget\" data-widget_type=\"image.default\">\n\t\t\t\t<div class=\"elementor-widget-container\">\n\t\t\t\t\t\t\t\t\t\t\t\t<figure class=\"wp-caption\">\n\t\t\t\t\t\t\t\t\t\t\t<a href=\"https:\/\/medium.com\/datadriveninvestor\/deep-learning-autoencoders-db265359943e\">\n\t\t\t\t\t\t\t<img decoding=\"async\" width=\"287\" height=\"300\" src=\"https:\/\/datascientest.com\/es\/files\/2020\/09\/Sche\u0301ma-1-287x300.png\" class=\"attachment-medium size-medium wp-image-9809\" alt=\"auto encodeur\" srcset=\"https:\/\/datascientest.com\/es\/files\/2020\/09\/Sche\u0301ma-1-287x300.png 287w, https:\/\/datascientest.com\/es\/files\/2020\/09\/Sche\u0301ma-1-980x1024.png 980w, https:\/\/datascientest.com\/es\/files\/2020\/09\/Sche\u0301ma-1-768x802.png 768w, https:\/\/datascientest.com\/es\/files\/2020\/09\/Sche\u0301ma-1-1470x1536.png 1470w, https:\/\/datascientest.com\/es\/files\/2020\/09\/Sche\u0301ma-1-1960x2048.png 1960w\" sizes=\"(max-width: 287px) 100vw, 287px\" \/>\t\t\t\t\t\t\t\t<\/a>\n\t\t\t\t\t\t\t\t\t\t\t<figcaption class=\"widget-image-caption wp-caption-text\">Autocodificador<\/figcaption>\n\t\t\t\t\t\t\t\t\t\t<\/figure>\n\t\t\t\t\t\t\t\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t\t\t\t<\/div>\n\t\t<\/div>\n\t\t\t\t\t\t\t<\/div>\n\t\t<\/section>\n\t\t\t\t<section class=\"elementor-section elementor-top-section elementor-element elementor-element-536a37b elementor-section-boxed elementor-section-height-default elementor-section-height-default\" data-id=\"536a37b\" data-element_type=\"section\">\n\t\t\t\t\t\t<div class=\"elementor-container elementor-column-gap-default\">\n\t\t\t\t\t<div class=\"elementor-column elementor-col-100 elementor-top-column elementor-element elementor-element-6bc97e7\" data-id=\"6bc97e7\" data-element_type=\"column\">\n\t\t\t<div class=\"elementor-widget-wrap elementor-element-populated\">\n\t\t\t\t\t\t\t\t<div class=\"elementor-element elementor-element-8eb1236 elementor-widget elementor-widget-heading\" data-id=\"8eb1236\" data-element_type=\"widget\" data-widget_type=\"heading.default\">\n\t\t\t\t<div class=\"elementor-widget-container\">\n\t\t\t<h2 class=\"elementor-heading-title elementor-size-default\">Embedding con la ayuda de Word2vec<\/h2>\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t\t\t<div class=\"elementor-element elementor-element-5ff89cd elementor-widget elementor-widget-menu-anchor\" data-id=\"5ff89cd\" data-element_type=\"widget\" data-widget_type=\"menu-anchor.default\">\n\t\t\t\t<div class=\"elementor-widget-container\">\n\t\t\t\t\t<div id=\"word2vec\" class=\"elementor-menu-anchor\"><\/div>\n\t\t\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t\t\t<div class=\"elementor-element elementor-element-c6a76a4 elementor-widget elementor-widget-text-editor\" data-id=\"c6a76a4\" data-element_type=\"widget\" data-widget_type=\"text-editor.default\">\n\t\t\t\t<div class=\"elementor-widget-container\">\n\t\t\t\t\t\t\t<p><span style=\"font-weight: 400;\">Sin embargo, para evitar las limitaciones del primer m\u00e9todo, es posible entrenar la matriz W <\/span><b>de forma no supervisada<\/b> <b>solo con texto<\/b><span style=\"font-weight: 400;\"> utilizando el famoso <\/span><b>algoritmo Word2Vec<\/b><span style=\"font-weight: 400;\">.<\/span><\/p><p><b>\u00bfC\u00f3mo funciona word2vec?<\/b><\/p><blockquote><p><i><span style=\"font-weight: 400;\">Existen dos variantes de Word2vec, ambas utilizan una red neuronal de 3 capas (1 capa de entrada, 1 capa oculta, 1 capa de salida): Common Bag Of Words (CBOW) y Skip-gram.<\/span><\/i><\/p><\/blockquote><p><span style=\"font-weight: 400;\">En la siguiente imagen, la <\/span><b>palabra del recuadro azul se llama palabra objetivo y las palabras de los recuadros blancos se llaman palabras de contexto<\/b><span style=\"font-weight: 400;\"> en una <\/span><b>ventana de tama\u00f1o 5.<\/b><\/p>\t\t\t\t\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t\t\t<div class=\"elementor-element elementor-element-6f6f17d elementor-widget elementor-widget-image\" data-id=\"6f6f17d\" data-element_type=\"widget\" data-widget_type=\"image.default\">\n\t\t\t\t<div class=\"elementor-widget-container\">\n\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t<img decoding=\"async\" width=\"800\" height=\"317\" src=\"https:\/\/datascientest.com\/es\/files\/2020\/09\/Capture-de\u0301cran-2020-09-18-a\u0300-09.27.50.png\" class=\"attachment-large size-large wp-image-9722\" alt=\"Embedding \u00e0 l\u2019aide du Word2vec\" srcset=\"https:\/\/datascientest.com\/es\/files\/2020\/09\/Capture-de\u0301cran-2020-09-18-a\u0300-09.27.50.png 842w, https:\/\/datascientest.com\/es\/files\/2020\/09\/Capture-de\u0301cran-2020-09-18-a\u0300-09.27.50-300x119.png 300w, https:\/\/datascientest.com\/es\/files\/2020\/09\/Capture-de\u0301cran-2020-09-18-a\u0300-09.27.50-768x305.png 768w\" sizes=\"(max-width: 800px) 100vw, 800px\" \/>\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t\t\t<div class=\"elementor-element elementor-element-38e1a78 elementor-widget elementor-widget-text-editor\" data-id=\"38e1a78\" data-element_type=\"widget\" data-widget_type=\"text-editor.default\">\n\t\t\t\t<div class=\"elementor-widget-container\">\n\t\t\t\t\t\t\t<p><b>CBOW : El modelo se alimenta del contexto<\/b><span style=\"font-weight: 400;\"> y predice la palabra objetivo. El resultado de la capa oculta es la nueva representaci\u00f3n de la palabra (<\/span><span style=\"font-weight: 400;\">\u210e<\/span><span style=\"font-weight: 400;\">1, &#8230;, <\/span><span style=\"font-weight: 400;\">\u210e\ud835\udc41<\/span><span style=\"font-weight: 400;\">).<\/span><\/p><p><b>Skip Gram: El modelo se alimenta de la palabra objetivo<\/b><span style=\"font-weight: 400;\"> y predice las palabras del contexto. El resultado de la capa oculta es la nueva representaci\u00f3n de la palabra (<\/span><span style=\"font-weight: 400;\">\u210e<\/span><span style=\"font-weight: 400;\">1, &#8230;, <\/span><span style=\"font-weight: 400;\">\u210e\ud835\udc41<\/span><span style=\"font-weight: 400;\">).<\/span><\/p>\t\t\t\t\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t\t\t<div class=\"elementor-element elementor-element-9bd8dee elementor-widget elementor-widget-image\" data-id=\"9bd8dee\" data-element_type=\"widget\" data-widget_type=\"image.default\">\n\t\t\t\t<div class=\"elementor-widget-container\">\n\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t<img decoding=\"async\" width=\"720\" height=\"433\" src=\"https:\/\/datascientest.com\/es\/files\/2020\/09\/word-2-vec-illu.png\" class=\"attachment-large size-large wp-image-9810\" alt=\"word2vec\" srcset=\"https:\/\/datascientest.com\/es\/files\/2020\/09\/word-2-vec-illu.png 720w, https:\/\/datascientest.com\/es\/files\/2020\/09\/word-2-vec-illu-300x180.png 300w\" sizes=\"(max-width: 720px) 100vw, 720px\" \/>\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t\t\t<div class=\"elementor-element elementor-element-b51096f elementor-widget elementor-widget-text-editor\" data-id=\"b51096f\" data-element_type=\"widget\" data-widget_type=\"text-editor.default\">\n\t\t\t\t<div class=\"elementor-widget-container\">\n\t\t\t\t\t\t\t<p><b>Formateo de los datos :<\/b><\/p><p><span style=\"font-weight: 400;\">Aqu\u00ed <\/span><b>presentaremos el modelo CBOW<\/b><span style=\"font-weight: 400;\">, es decir, el <\/span><b>contexto es la entrada<\/b><span style=\"font-weight: 400;\"> de nuestro modelo y <\/span><b>la palabra objetivo (palabra azul) es la salida<\/b><span style=\"font-weight: 400;\">. Definimos una ventana de longitud 5 para el contexto (entrada).<\/span><\/p>\t\t\t\t\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t\t\t<div class=\"elementor-element elementor-element-ffea1ac elementor-widget elementor-widget-image\" data-id=\"ffea1ac\" data-element_type=\"widget\" data-widget_type=\"image.default\">\n\t\t\t\t<div class=\"elementor-widget-container\">\n\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t<img decoding=\"async\" width=\"800\" height=\"317\" src=\"https:\/\/datascientest.com\/es\/files\/2020\/09\/Capture-de\u0301cran-2020-09-18-a\u0300-09.27.50.png\" class=\"attachment-large size-large wp-image-9722\" alt=\"Embedding \u00e0 l\u2019aide du Word2vec\" srcset=\"https:\/\/datascientest.com\/es\/files\/2020\/09\/Capture-de\u0301cran-2020-09-18-a\u0300-09.27.50.png 842w, https:\/\/datascientest.com\/es\/files\/2020\/09\/Capture-de\u0301cran-2020-09-18-a\u0300-09.27.50-300x119.png 300w, https:\/\/datascientest.com\/es\/files\/2020\/09\/Capture-de\u0301cran-2020-09-18-a\u0300-09.27.50-768x305.png 768w\" sizes=\"(max-width: 800px) 100vw, 800px\" \/>\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t\t\t<div class=\"elementor-element elementor-element-4ad6fb5 elementor-widget elementor-widget-image\" data-id=\"4ad6fb5\" data-element_type=\"widget\" data-widget_type=\"image.default\">\n\t\t\t\t<div class=\"elementor-widget-container\">\n\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t<img decoding=\"async\" width=\"800\" height=\"211\" src=\"https:\/\/datascientest.com\/es\/files\/2020\/09\/Sche\u0301ma-2-1024x270.png\" class=\"attachment-large size-large wp-image-9811\" alt=\"\" srcset=\"https:\/\/datascientest.com\/es\/files\/2020\/09\/Sche\u0301ma-2-1024x270.png 1024w, https:\/\/datascientest.com\/es\/files\/2020\/09\/Sche\u0301ma-2-300x79.png 300w, https:\/\/datascientest.com\/es\/files\/2020\/09\/Sche\u0301ma-2-768x202.png 768w, https:\/\/datascientest.com\/es\/files\/2020\/09\/Sche\u0301ma-2-1536x405.png 1536w, https:\/\/datascientest.com\/es\/files\/2020\/09\/Sche\u0301ma-2-2048x540.png 2048w\" sizes=\"(max-width: 800px) 100vw, 800px\" \/>\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t\t\t<div class=\"elementor-element elementor-element-3012954 elementor-widget elementor-widget-text-editor\" data-id=\"3012954\" data-element_type=\"widget\" data-widget_type=\"text-editor.default\">\n\t\t\t\t<div class=\"elementor-widget-container\">\n\t\t\t\t\t\t\t<p><b>Modelo :<\/b><\/p><p><span style=\"font-weight: 400;\">El modelo CBOW tiene similitudes con el modelo de clasificaci\u00f3n que acabamos de implementar en la secci\u00f3n anterior. Nuestro modelo estar\u00e1 compuesto por las siguientes capas :<\/span><\/p>\t\t\t\t\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t\t\t<div class=\"elementor-element elementor-element-b5f21d5 elementor-widget elementor-widget-image\" data-id=\"b5f21d5\" data-element_type=\"widget\" data-widget_type=\"image.default\">\n\t\t\t\t<div class=\"elementor-widget-container\">\n\t\t\t\t\t\t\t\t\t\t\t\t<figure class=\"wp-caption\">\n\t\t\t\t\t\t\t\t\t\t<img decoding=\"async\" width=\"800\" height=\"745\" src=\"https:\/\/datascientest.com\/es\/files\/2020\/09\/Sche\u0301ma-3-1024x954.png\" class=\"attachment-large size-large wp-image-9821\" alt=\"cbow\" srcset=\"https:\/\/datascientest.com\/es\/files\/2020\/09\/Sche\u0301ma-3-1024x954.png 1024w, https:\/\/datascientest.com\/es\/files\/2020\/09\/Sche\u0301ma-3-300x279.png 300w, https:\/\/datascientest.com\/es\/files\/2020\/09\/Sche\u0301ma-3-768x715.png 768w, https:\/\/datascientest.com\/es\/files\/2020\/09\/Sche\u0301ma-3-1536x1431.png 1536w, https:\/\/datascientest.com\/es\/files\/2020\/09\/Sche\u0301ma-3-2048x1908.png 2048w\" sizes=\"(max-width: 800px) 100vw, 800px\" \/>\t\t\t\t\t\t\t\t\t\t\t<figcaption class=\"widget-image-caption wp-caption-text\">Arquitectura CBOW<\/figcaption>\n\t\t\t\t\t\t\t\t\t\t<\/figure>\n\t\t\t\t\t\t\t\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t\t\t<div class=\"elementor-element elementor-element-afbee86 elementor-widget elementor-widget-text-editor\" data-id=\"afbee86\" data-element_type=\"widget\" data-widget_type=\"text-editor.default\">\n\t\t\t\t<div class=\"elementor-widget-container\">\n\t\t\t\t\t\t\t<ol><li><span style=\"font-weight: 400;\"> La capa Embedding <\/span><b>transformar\u00e1 cada palabra del contexto en un vector de embedding<\/b><span style=\"font-weight: 400;\">. La matriz W de embedding se aprender\u00e1 a medida que se entrena el modelo. Las dimensiones resultantes son: (lot, context_size, embedding).<\/span><\/li><li><span style=\"font-weight: 400;\"> A continuaci\u00f3n, la capa GlobalAveragePooling1D permite <\/span><b>sumar los diferentes embbeding<\/b><span style=\"font-weight: 400;\"> y obtener una dimensi\u00f3n de salida (batch_size, embedding).<\/span><\/li><li><span style=\"font-weight: 400;\">Por \u00faltimo, la capa densa de tama\u00f1o \u00abvoc_size\u00bb <\/span><b>permite predecir la palabra objetivo<\/b><span style=\"font-weight: 400;\">.<\/span><\/li><\/ol>\t\t\t\t\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t\t\t<div class=\"elementor-element elementor-element-26fc567 elementor-widget elementor-widget-shortcode\" data-id=\"26fc567\" data-element_type=\"widget\" data-widget_type=\"shortcode.default\">\n\t\t\t\t<div class=\"elementor-widget-container\">\n\t\t\t\t\t<div class=\"elementor-shortcode\"><script src=\"https:\/\/gist.github.com\/15boehler\/806f56f30a993bb7c933acb1f23d9014.js\"><\/script><\/div>\n\t\t\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t\t\t<div class=\"elementor-element elementor-element-2661ba4 elementor-widget elementor-widget-text-editor\" data-id=\"2661ba4\" data-element_type=\"widget\" data-widget_type=\"text-editor.default\">\n\t\t\t\t<div class=\"elementor-widget-container\">\n\t\t\t\t\t\t\t<p><span style=\"font-weight: 400;\">La funci\u00f3n de p\u00e9rdida cross-entropy se suele utilizar para entrenar al modelo :<\/span><\/p>\t\t\t\t\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t\t\t<div class=\"elementor-element elementor-element-254311e elementor-widget elementor-widget-shortcode\" data-id=\"254311e\" data-element_type=\"widget\" data-widget_type=\"shortcode.default\">\n\t\t\t\t<div class=\"elementor-widget-container\">\n\t\t\t\t\t<div class=\"elementor-shortcode\"><script src=\"https:\/\/gist.github.com\/15boehler\/2e3c21701abdfe7dfec520cfc52c3465.js\"><\/script><\/div>\n\t\t\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t\t\t\t<\/div>\n\t\t<\/div>\n\t\t\t\t\t\t\t<\/div>\n\t\t<\/section>\n\t\t\t\t<section class=\"elementor-section elementor-top-section elementor-element elementor-element-e2cc006 elementor-section-boxed elementor-section-height-default elementor-section-height-default\" data-id=\"e2cc006\" data-element_type=\"section\">\n\t\t\t\t\t\t<div class=\"elementor-container elementor-column-gap-default\">\n\t\t\t\t\t<div class=\"elementor-column elementor-col-100 elementor-top-column elementor-element elementor-element-9f539ab\" data-id=\"9f539ab\" data-element_type=\"column\">\n\t\t\t<div class=\"elementor-widget-wrap elementor-element-populated\">\n\t\t\t\t\t\t\t\t<div class=\"elementor-element elementor-element-da40f97 elementor-widget elementor-widget-heading\" data-id=\"da40f97\" data-element_type=\"widget\" data-widget_type=\"heading.default\">\n\t\t\t\t<div class=\"elementor-widget-container\">\n\t\t\t<h2 class=\"elementor-heading-title elementor-size-default\">M\u00e9trica en este espacio :<\/h2>\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t\t\t<div class=\"elementor-element elementor-element-e34e76e elementor-widget elementor-widget-menu-anchor\" data-id=\"e34e76e\" data-element_type=\"widget\" data-widget_type=\"menu-anchor.default\">\n\t\t\t\t<div class=\"elementor-widget-container\">\n\t\t\t\t\t<div id=\"metrique\" class=\"elementor-menu-anchor\"><\/div>\n\t\t\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t\t\t<div class=\"elementor-element elementor-element-3059987 elementor-widget elementor-widget-text-editor\" data-id=\"3059987\" data-element_type=\"widget\" data-widget_type=\"text-editor.default\">\n\t\t\t\t<div class=\"elementor-widget-container\">\n\t\t\t\t\t\t\t<p><span style=\"font-weight: 400;\">Ahora que el modelo est\u00e1 entrenado, puede ser interesante comparar la distancia entre las palabras.<\/span><\/p><p><b>La \u201cCosine similarity\u201d <\/b><span style=\"font-weight: 400;\">se utiliza por lo general como m\u00e9trica para <\/span><b>medir la distancia cuando la norma de los vectores no tiene importancia.<\/b><span style=\"font-weight: 400;\"> Esta m\u00e9trica capta la similitud entre dos palabras.<\/span><\/p><blockquote><p><i><span style=\"font-weight: 400;\">Cuanto m\u00e1s se acerque la cosine similarity a 1, <\/span><\/i><b><i>m\u00e1s relacionadas estar\u00e1n las dos palabras<\/i><\/b><i><span style=\"font-weight: 400;\">.<\/span><\/i><\/p><\/blockquote>\t\t\t\t\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t\t\t<div class=\"elementor-element elementor-element-30d21df elementor-widget elementor-widget-image\" data-id=\"30d21df\" data-element_type=\"widget\" data-widget_type=\"image.default\">\n\t\t\t\t<div class=\"elementor-widget-container\">\n\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t<img decoding=\"async\" width=\"512\" height=\"197\" src=\"https:\/\/datascientest.com\/es\/files\/2020\/09\/word2vec.png\" class=\"attachment-medium_large size-medium_large wp-image-9910\" alt=\"word2vec\" srcset=\"https:\/\/datascientest.com\/es\/files\/2020\/09\/word2vec.png 512w, https:\/\/datascientest.com\/es\/files\/2020\/09\/word2vec-300x115.png 300w\" sizes=\"(max-width: 512px) 100vw, 512px\" \/>\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t\t\t<div class=\"elementor-element elementor-element-7b6a416 elementor-widget elementor-widget-text-editor\" data-id=\"7b6a416\" data-element_type=\"widget\" data-widget_type=\"text-editor.default\">\n\t\t\t\t<div class=\"elementor-widget-container\">\n\t\t\t\t\t\t\t<p><span style=\"font-weight: 400;\">Con esta m\u00e9trica y en este subespacio vectorial, las 5 palabras <\/span><b>m\u00e1s cercanas a \u00abbody\u00bb<\/b><span style=\"font-weight: 400;\"> son :<\/span><\/p>\t\t\t\t\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t\t\t<div class=\"elementor-element elementor-element-7d0d45a elementor-widget elementor-widget-text-editor\" data-id=\"7d0d45a\" data-element_type=\"widget\" data-widget_type=\"text-editor.default\">\n\t\t\t\t<div class=\"elementor-widget-container\">\n\t\t\t\t\t\t\t<p><span style=\"font-weight: 400;\">intestines\u00a0 &#8212;\u00a0 0.30548161268234253<\/span><\/p><p><span style=\"font-weight: 400;\">bodies\u00a0 &#8212;\u00a0 0.2691531181335449<\/span><\/p><p><span style=\"font-weight: 400;\">arm\u00a0 &#8212;\u00a0 0.24878980219364166<\/span><\/p><p><span style=\"font-weight: 400;\">chest\u00a0 &#8212;\u00a0 0.2261650413274765<\/span><\/p><p><span style=\"font-weight: 400;\">leg\u00a0 &#8212;\u00a0 0.2193179428577423<\/span><\/p>\t\t\t\t\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t\t\t<div class=\"elementor-element elementor-element-b81fb3d elementor-widget elementor-widget-text-editor\" data-id=\"b81fb3d\" data-element_type=\"widget\" data-widget_type=\"text-editor.default\">\n\t\t\t\t<div class=\"elementor-widget-container\">\n\t\t\t\t\t\t\t<p><span style=\"font-weight: 400;\">Los n\u00fameros anteriores representan las distancias de similitud coseno entre la palabra \u00abbody\u00bb y las palabras m\u00e1s cercanas.<\/span><\/p>\t\t\t\t\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t\t\t<div class=\"elementor-element elementor-element-1f2c18a elementor-widget elementor-widget-heading\" data-id=\"1f2c18a\" data-element_type=\"widget\" data-widget_type=\"heading.default\">\n\t\t\t\t<div class=\"elementor-widget-container\">\n\t\t\t<p class=\"elementor-heading-title elementor-size-default\">Para la palabra \u00ab <b>zombie<\/b> \u00bb :\n<\/p>\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t\t\t<div class=\"elementor-element elementor-element-78cd317 elementor-widget elementor-widget-text-editor\" data-id=\"78cd317\" data-element_type=\"widget\" data-widget_type=\"text-editor.default\">\n\t\t\t\t<div class=\"elementor-widget-container\">\n\t\t\t\t\t\t\t<p><span style=\"font-weight: 400;\">slasher\u00a0 &#8212;\u00a0 0.3172745406627655<\/span><\/p><p><span style=\"font-weight: 400;\">cannibal\u00a0 &#8212;\u00a0 0.28496912121772766<\/span><\/p><p><span style=\"font-weight: 400;\">zombies\u00a0 &#8212;\u00a0 0.2767203450202942<\/span><\/p><p><span style=\"font-weight: 400;\">horror\u00a0 &#8212;\u00a0 0.2607246935367584<\/span><\/p><p><span style=\"font-weight: 400;\">zombi\u00a0 &#8212;\u00a0 0.25878411531448364<\/span><\/p>\t\t\t\t\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t\t\t<div class=\"elementor-element elementor-element-f0b3f0d elementor-widget elementor-widget-heading\" data-id=\"f0b3f0d\" data-element_type=\"widget\" data-widget_type=\"heading.default\">\n\t\t\t\t<div class=\"elementor-widget-container\">\n\t\t\t<p class=\"elementor-heading-title elementor-size-default\">Para la palabra \u00ab <b>amazing <\/b>\u00bb :\n<\/p>\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t\t\t<div class=\"elementor-element elementor-element-b9e1245 elementor-widget elementor-widget-text-editor\" data-id=\"b9e1245\" data-element_type=\"widget\" data-widget_type=\"text-editor.default\">\n\t\t\t\t<div class=\"elementor-widget-container\">\n\t\t\t\t\t\t\t<p><span style=\"font-weight: 400;\">brilliant\u00a0 &#8212;\u00a0 0.3372475802898407<\/span><\/p><p><span style=\"font-weight: 400;\">extraordinary\u00a0 &#8212;\u00a0 0.319326251745224<\/span><\/p><p><span style=\"font-weight: 400;\">great\u00a0 &#8212;\u00a0 0.29579296708106995<\/span><\/p><p><span style=\"font-weight: 400;\">breathtaking\u00a0 &#8212;\u00a0 0.2907085716724396<\/span><\/p><p><span style=\"font-weight: 400;\">fantastic\u00a0 &#8212;\u00a0 0.2871546149253845<\/span><\/p>\t\t\t\t\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t\t\t<div class=\"elementor-element elementor-element-a2a375f elementor-widget elementor-widget-heading\" data-id=\"a2a375f\" data-element_type=\"widget\" data-widget_type=\"heading.default\">\n\t\t\t\t<div class=\"elementor-widget-container\">\n\t\t\t<p class=\"elementor-heading-title elementor-size-default\">Para la palabra \u00ab<b> god<\/b> \u00bb :\n<\/p>\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t\t\t<div class=\"elementor-element elementor-element-70cd42e elementor-widget elementor-widget-text-editor\" data-id=\"70cd42e\" data-element_type=\"widget\" data-widget_type=\"text-editor.default\">\n\t\t\t\t<div class=\"elementor-widget-container\">\n\t\t\t\t\t\t\t<p><span style=\"font-weight: 400;\">heavens\u00a0 &#8212;\u00a0 0.268303781747818<\/span><\/p><p><span style=\"font-weight: 400;\">jesus\u00a0 &#8212;\u00a0 0.26807624101638794<\/span><\/p><p><span style=\"font-weight: 400;\">goodness\u00a0 &#8212;\u00a0 0.2618488669395447<\/span><\/p><p><span style=\"font-weight: 400;\">gods\u00a0 &#8212;\u00a0 0.24795521795749664<\/span><\/p><p><span style=\"font-weight: 400;\">doom\u00a0 &#8212;\u00a0 0.22242328524589539<\/span><\/p>\t\t\t\t\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t\t\t\t<\/div>\n\t\t<\/div>\n\t\t\t\t\t\t\t<\/div>\n\t\t<\/section>\n\t\t\t\t<section class=\"elementor-section elementor-top-section elementor-element elementor-element-e06edb3 elementor-section-boxed elementor-section-height-default elementor-section-height-default\" data-id=\"e06edb3\" data-element_type=\"section\">\n\t\t\t\t\t\t<div class=\"elementor-container elementor-column-gap-default\">\n\t\t\t\t\t<div class=\"elementor-column elementor-col-100 elementor-top-column elementor-element elementor-element-3461ef8\" data-id=\"3461ef8\" data-element_type=\"column\">\n\t\t\t<div class=\"elementor-widget-wrap elementor-element-populated\">\n\t\t\t\t\t\t\t\t<div class=\"elementor-element elementor-element-cba65e7 elementor-widget elementor-widget-text-editor\" data-id=\"cba65e7\" data-element_type=\"widget\" data-widget_type=\"text-editor.default\">\n\t\t\t\t<div class=\"elementor-widget-container\">\n\t\t\t\t\t\t\t<p><b>Propiedades aritm\u00e9ticas :<\/b><\/p><p><span style=\"font-weight: 400;\">Ahora podemos preguntarnos si nuestro subespacio vectorial de palabras tiene propiedades aritm\u00e9ticas. Veamos el siguiente ejemplo famoso :<\/span><\/p>\t\t\t\t\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t\t\t<div class=\"elementor-element elementor-element-2e0f805 elementor-widget elementor-widget-text-editor\" data-id=\"2e0f805\" data-element_type=\"widget\" data-widget_type=\"text-editor.default\">\n\t\t\t\t<div class=\"elementor-widget-container\">\n\t\t\t\t\t\t\t<p style=\"text-align: center;\"><span style=\"font-weight: 400;\">\ud835\udc3e\ud835\udc56\ud835\udc5b\ud835\udc54<\/span><span style=\"font-weight: 400;\">\u00a0\u2212\u00a0<\/span><span style=\"font-weight: 400;\">\ud835\udc40\ud835\udc4e\ud835\udc5b<\/span><span style=\"font-weight: 400;\">\u00a0+\u00a0<\/span><span style=\"font-weight: 400;\">\ud835\udc4a\ud835\udc5c\ud835\udc5a\ud835\udc4e\ud835\udc5b<\/span><span style=\"font-weight: 400;\">\u00a0=\u00a0<\/span><span style=\"font-size: 16px; font-weight: 400;\">\ud835\udc44\ud835\udc62\ud835\udc52\ud835\udc52\ud835\udc5b<\/span><\/p>\t\t\t\t\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t\t\t<div class=\"elementor-element elementor-element-45d4f2f elementor-widget elementor-widget-text-editor\" data-id=\"45d4f2f\" data-element_type=\"widget\" data-widget_type=\"text-editor.default\">\n\t\t\t\t<div class=\"elementor-widget-container\">\n\t\t\t\t\t\t\t<p><span style=\"font-weight: 400;\">En este ejemplo la <\/span><b>propiedad aritm\u00e9tica es la realeza<\/b><span style=\"font-weight: 400;\">. Queremos comprobar si esta propiedad se propagar\u00e1 a \u00abwoman\u00bb. Es decir, buscaremos las palabras m\u00e1s cercanas al siguiente vector :<\/span><\/p><p style=\"text-align: center;\"><span style=\"font-weight: 400;\">arithmetic_vector = word2vec[index_word1] &#8211; word2vec[index_word2] + word2vec [index_word3]<\/span><\/p><p><span style=\"font-weight: 400;\">Aqu\u00ed, la palabra \u00abqueen\u00bb no est\u00e1 muy representada en nuestra serie de datos, lo que explica la escasa representaci\u00f3n. Por esta raz\u00f3n, nos <\/span><b>centraremos en la propiedad num\u00e9rica <\/b><span style=\"font-weight: 400;\">:<\/span><\/p><p style=\"text-align: center;\"><i><span style=\"font-weight: 400;\">Men<\/span><\/i><span style=\"font-weight: 400;\">\u00a0\u2212\u00a0<\/span><span style=\"font-weight: 400;\">\ud835\udc40\ud835\udc4e\ud835\udc5b<\/span><span style=\"font-weight: 400;\">\u00a0+\u00a0<\/span><span style=\"font-weight: 400;\">\ud835\udc4a\ud835\udc5c\ud835\udc5a\ud835\udc4e\ud835\udc5b<\/span><span style=\"font-weight: 400;\">\u00a0=\u00a0<\/span><span style=\"font-weight: 400;\">Women<\/span><\/p>\t\t\t\t\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t\t\t\t<\/div>\n\t\t<\/div>\n\t\t\t\t\t\t\t<\/div>\n\t\t<\/section>\n\t\t\t\t<section class=\"elementor-section elementor-top-section elementor-element elementor-element-eab4b3b elementor-section-boxed elementor-section-height-default elementor-section-height-default\" data-id=\"eab4b3b\" data-element_type=\"section\">\n\t\t\t\t\t\t<div class=\"elementor-container elementor-column-gap-default\">\n\t\t\t\t\t<div class=\"elementor-column elementor-col-100 elementor-top-column elementor-element elementor-element-5656fb2\" data-id=\"5656fb2\" data-element_type=\"column\">\n\t\t\t<div class=\"elementor-widget-wrap elementor-element-populated\">\n\t\t\t\t\t\t\t\t<div class=\"elementor-element elementor-element-a419e26 elementor-widget elementor-widget-heading\" data-id=\"a419e26\" data-element_type=\"widget\" data-widget_type=\"heading.default\">\n\t\t\t\t<div class=\"elementor-widget-container\">\n\t\t\t<p class=\"elementor-heading-title elementor-size-default\">Utilizando la operaci\u00f3n definida anteriormente y una m\u00e9trica de similitud coseno, <b>las 5 palabras m\u00e1s cercanas son :<\/b><\/p>\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t\t\t<div class=\"elementor-element elementor-element-d5b4c1c elementor-widget elementor-widget-text-editor\" data-id=\"d5b4c1c\" data-element_type=\"widget\" data-widget_type=\"text-editor.default\">\n\t\t\t\t<div class=\"elementor-widget-container\">\n\t\t\t\t\t\t\t<p><span style=\"font-weight: 400;\">women\u00a0 &#8212;\u00a0 0.2889893054962158<\/span><\/p><p><span style=\"font-weight: 400;\">females\u00a0 &#8212;\u00a0 0.272260844707489<\/span><\/p><p><span style=\"font-weight: 400;\">strangers\u00a0 &#8212;\u00a0 0.24558939039707184<\/span><\/p><p><span style=\"font-weight: 400;\">teens\u00a0 &#8212;\u00a0 0.2443128377199173<\/span><\/p><p><span style=\"font-weight: 400;\">daughters\u00a0 &#8212;\u00a0 0.24117740988731384<\/span><\/p>\t\t\t\t\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t\t\t\t<\/div>\n\t\t<\/div>\n\t\t\t\t\t\t\t<\/div>\n\t\t<\/section>\n\t\t\t\t<section class=\"elementor-section elementor-top-section elementor-element elementor-element-2d6473e elementor-section-boxed elementor-section-height-default elementor-section-height-default\" data-id=\"2d6473e\" data-element_type=\"section\">\n\t\t\t\t\t\t<div class=\"elementor-container elementor-column-gap-default\">\n\t\t\t\t\t<div class=\"elementor-column elementor-col-100 elementor-top-column elementor-element elementor-element-752ed8a\" data-id=\"752ed8a\" data-element_type=\"column\">\n\t\t\t<div class=\"elementor-widget-wrap elementor-element-populated\">\n\t\t\t\t\t\t\t\t<div class=\"elementor-element elementor-element-ca1c672 elementor-widget elementor-widget-heading\" data-id=\"ca1c672\" data-element_type=\"widget\" data-widget_type=\"heading.default\">\n\t\t\t\t<div class=\"elementor-widget-container\">\n\t\t\t<p class=\"elementor-heading-title elementor-size-default\">El resultado para Zombies \u2212 Zombie + \ud835\udc4a\ud835\udc5c\ud835\udc5a\ud835\udc4e\ud835\udc5b :<\/p>\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t\t\t<div class=\"elementor-element elementor-element-bb11440 elementor-widget elementor-widget-text-editor\" data-id=\"bb11440\" data-element_type=\"widget\" data-widget_type=\"text-editor.default\">\n\t\t\t\t<div class=\"elementor-widget-container\">\n\t\t\t\t\t\t\t<p><span style=\"font-weight: 400;\">women\u00a0 &#8212;\u00a0 0.2547883093357086<\/span><\/p><p><span style=\"font-weight: 400;\">females\u00a0 &#8212;\u00a0 0.23258551955223083<\/span><\/p><p><span style=\"font-weight: 400;\">ladies\u00a0 &#8212;\u00a0 0.22764989733695984<\/span><\/p><p><span style=\"font-weight: 400;\">stripper\u00a0 &#8212;\u00a0 0.22274985909461975<\/span><\/p><p><span style=\"font-weight: 400;\">develops\u00a0 &#8212;\u00a0 0.2202150821685791<\/span><\/p>\t\t\t\t\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t\t\t\t<\/div>\n\t\t<\/div>\n\t\t\t\t\t\t\t<\/div>\n\t\t<\/section>\n\t\t\t\t<section class=\"elementor-section elementor-top-section elementor-element elementor-element-d869280 elementor-section-boxed elementor-section-height-default elementor-section-height-default\" data-id=\"d869280\" data-element_type=\"section\">\n\t\t\t\t\t\t<div class=\"elementor-container elementor-column-gap-default\">\n\t\t\t\t\t<div class=\"elementor-column elementor-col-100 elementor-top-column elementor-element elementor-element-9e8de93\" data-id=\"9e8de93\" data-element_type=\"column\">\n\t\t\t<div class=\"elementor-widget-wrap elementor-element-populated\">\n\t\t\t\t\t\t\t\t<div class=\"elementor-element elementor-element-623eee4 elementor-widget elementor-widget-heading\" data-id=\"623eee4\" data-element_type=\"widget\" data-widget_type=\"heading.default\">\n\t\t\t\t<div class=\"elementor-widget-container\">\n\t\t\t<p class=\"elementor-heading-title elementor-size-default\">El resultado para Men \u2212 Man + Soldier :\n<\/p>\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t\t\t<div class=\"elementor-element elementor-element-7f05a70 elementor-widget elementor-widget-text-editor\" data-id=\"7f05a70\" data-element_type=\"widget\" data-widget_type=\"text-editor.default\">\n\t\t\t\t<div class=\"elementor-widget-container\">\n\t\t\t\t\t\t\t<p><span style=\"font-weight: 400;\">soldiers\u00a0 &#8212;\u00a0 0.3547001779079437<\/span><\/p><p><span style=\"font-weight: 400;\">daughters\u00a0 &#8212;\u00a0 0.21896378695964813<\/span><\/p><p><span style=\"font-weight: 400;\">letters\u00a0 &#8212;\u00a0 0.21452251076698303<\/span><\/p><p><span style=\"font-weight: 400;\">backyard\u00a0 &#8212;\u00a0 0.21437858045101166<\/span><\/p><p><span style=\"font-weight: 400;\">veterans\u00a0 &#8212;\u00a0 0.21067838370800018<\/span><\/p>\t\t\t\t\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t\t\t\t<\/div>\n\t\t<\/div>\n\t\t\t\t\t\t\t<\/div>\n\t\t<\/section>\n\t\t\t\t<section class=\"elementor-section elementor-top-section elementor-element elementor-element-3389cf1 elementor-section-boxed elementor-section-height-default elementor-section-height-default\" data-id=\"3389cf1\" data-element_type=\"section\">\n\t\t\t\t\t\t<div class=\"elementor-container elementor-column-gap-default\">\n\t\t\t\t\t<div class=\"elementor-column elementor-col-100 elementor-top-column elementor-element elementor-element-86d3f31\" data-id=\"86d3f31\" data-element_type=\"column\">\n\t\t\t<div class=\"elementor-widget-wrap elementor-element-populated\">\n\t\t\t\t\t\t\t\t<div class=\"elementor-element elementor-element-617995a elementor-widget elementor-widget-heading\" data-id=\"617995a\" data-element_type=\"widget\" data-widget_type=\"heading.default\">\n\t\t\t\t<div class=\"elementor-widget-container\">\n\t\t\t<p class=\"elementor-heading-title elementor-size-default\">El resultado para Zombies \u2212 Zombie + monster :<\/p>\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t\t\t<div class=\"elementor-element elementor-element-2dd9339 elementor-widget elementor-widget-text-editor\" data-id=\"2dd9339\" data-element_type=\"widget\" data-widget_type=\"text-editor.default\">\n\t\t\t\t<div class=\"elementor-widget-container\">\n\t\t\t\t\t\t\t<p><span style=\"font-weight: 400;\">werewolves\u00a0 &#8212;\u00a0 0.2724993824958801<\/span><\/p><p><span style=\"font-weight: 400;\">monsters\u00a0 &#8212;\u00a0 0.25695472955703735<\/span><\/p><p><span style=\"font-weight: 400;\">creature\u00a0 &#8212;\u00a0 0.24453674256801605<\/span><\/p><p><span style=\"font-weight: 400;\">dragons\u00a0 &#8212;\u00a0 0.22363890707492828<\/span><\/p><p><span style=\"font-weight: 400;\">bloke\u00a0 &#8212;\u00a0 0.21858260035514832<\/span><\/p>\t\t\t\t\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t\t\t\t<\/div>\n\t\t<\/div>\n\t\t\t\t\t\t\t<\/div>\n\t\t<\/section>\n\t\t\t\t<section class=\"elementor-section elementor-top-section elementor-element elementor-element-075e430 elementor-section-boxed elementor-section-height-default elementor-section-height-default\" data-id=\"075e430\" data-element_type=\"section\">\n\t\t\t\t\t\t<div class=\"elementor-container elementor-column-gap-default\">\n\t\t\t\t\t<div class=\"elementor-column elementor-col-100 elementor-top-column elementor-element elementor-element-753fe22\" data-id=\"753fe22\" data-element_type=\"column\">\n\t\t\t<div class=\"elementor-widget-wrap elementor-element-populated\">\n\t\t\t\t\t\t\t\t<div class=\"elementor-element elementor-element-5f23597 elementor-widget elementor-widget-text-editor\" data-id=\"5f23597\" data-element_type=\"widget\" data-widget_type=\"text-editor.default\">\n\t\t\t\t<div class=\"elementor-widget-container\">\n\t\t\t\t\t\t\t<p><span style=\"font-weight: 400;\">Aqu\u00ed la palabra \u00abmonsters\u00bb y \u00abwerewolves\u00bb parecen estar muy cerca en el contexto de nuestra serie de datos.<\/span><\/p><p><span style=\"font-weight: 400;\">Utilizando un ACP, podemos encontrar la dimensi\u00f3n de la <\/span><b>propiedad num\u00e9rica <\/b><span style=\"font-weight: 400;\">:<\/span><\/p>\t\t\t\t\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t\t\t<div class=\"elementor-element elementor-element-5ca3508 elementor-widget elementor-widget-image\" data-id=\"5ca3508\" data-element_type=\"widget\" data-widget_type=\"image.default\">\n\t\t\t\t<div class=\"elementor-widget-container\">\n\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t<img decoding=\"async\" width=\"717\" height=\"683\" src=\"https:\/\/datascientest.com\/es\/files\/2020\/09\/image_word2vec.png\" class=\"attachment-large size-large wp-image-9715\" alt=\"propri\u00e9t\u00e9 de nombre\" srcset=\"https:\/\/datascientest.com\/es\/files\/2020\/09\/image_word2vec.png 717w, https:\/\/datascientest.com\/es\/files\/2020\/09\/image_word2vec-300x286.png 300w\" sizes=\"(max-width: 717px) 100vw, 717px\" \/>\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t\t\t<div class=\"elementor-element elementor-element-02994f2 elementor-widget elementor-widget-text-editor\" data-id=\"02994f2\" data-element_type=\"widget\" data-widget_type=\"text-editor.default\">\n\t\t\t\t<div class=\"elementor-widget-container\">\n\t\t\t\t\t\t\t<p><span style=\"font-weight: 400;\">Utilizando el mismo razonamiento para <\/span><b>captar el g\u00e9nero <\/b><span style=\"font-weight: 400;\">:<\/span><\/p>\t\t\t\t\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t\t\t<div class=\"elementor-element elementor-element-3bbb6ff elementor-widget elementor-widget-image\" data-id=\"3bbb6ff\" data-element_type=\"widget\" data-widget_type=\"image.default\">\n\t\t\t\t<div class=\"elementor-widget-container\">\n\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t<img decoding=\"async\" width=\"512\" height=\"488\" src=\"https:\/\/datascientest.com\/es\/files\/2020\/09\/word2vec_3.png\" class=\"attachment-medium_large size-medium_large wp-image-9908\" alt=\"word2vec\" srcset=\"https:\/\/datascientest.com\/es\/files\/2020\/09\/word2vec_3.png 512w, https:\/\/datascientest.com\/es\/files\/2020\/09\/word2vec_3-300x286.png 300w\" sizes=\"(max-width: 512px) 100vw, 512px\" \/>\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t\t\t<div class=\"elementor-element elementor-element-daf2245 elementor-widget elementor-widget-text-editor\" data-id=\"daf2245\" data-element_type=\"widget\" data-widget_type=\"text-editor.default\">\n\t\t\t\t<div class=\"elementor-widget-container\">\n\t\t\t\t\t\t\t<p><span style=\"font-weight: 400;\">Utilizando el mismo razonamiento entre los <\/span><b>verbos en infinitivo y los verbos terminados en -ed <\/b><span style=\"font-weight: 400;\">:<\/span><\/p>\t\t\t\t\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t\t\t\t<\/div>\n\t\t<\/div>\n\t\t\t\t\t\t\t<\/div>\n\t\t<\/section>\n\t\t\t\t<section class=\"elementor-section elementor-top-section elementor-element elementor-element-32c22ad elementor-section-boxed elementor-section-height-default elementor-section-height-default\" data-id=\"32c22ad\" data-element_type=\"section\">\n\t\t\t\t\t\t<div class=\"elementor-container elementor-column-gap-default\">\n\t\t\t\t\t<div class=\"elementor-column elementor-col-100 elementor-top-column elementor-element elementor-element-0dc24b2\" data-id=\"0dc24b2\" data-element_type=\"column\">\n\t\t\t<div class=\"elementor-widget-wrap elementor-element-populated\">\n\t\t\t\t\t\t\t\t<div class=\"elementor-element elementor-element-27916d0 elementor-widget elementor-widget-text-editor\" data-id=\"27916d0\" data-element_type=\"widget\" data-widget_type=\"text-editor.default\">\n\t\t\t\t<div class=\"elementor-widget-container\">\n\t\t\t\t\t\t\t<p><b>\u201cWord2vec embedding\u201d captura eficazmente las propiedades sem\u00e1nticas y aritm\u00e9ticas de una palabra. <\/b><span style=\"font-weight: 400;\">Tambi\u00e9n permite<\/span><b> reducir el tama\u00f1o del problema y, por tanto, la tarea de aprendizaje.<\/b><\/p><p><span style=\"font-weight: 400;\">Podemos imaginarnos el uso del algoritmo word2vec <\/span><b>para preentrenar la matriz de embedding del modelo de clasificaci\u00f3n.<\/b><span style=\"font-weight: 400;\"> Como resultado, nuestro modelo de clasificaci\u00f3n tendr\u00e1 una representaci\u00f3n mucho mejor de las palabras en la fase de aprendizaje de los sentimientos.<\/span><\/p><p><span style=\"font-weight: 400;\">\u00bf<\/span><a href=\"https:\/\/datascientest.com\/es\/nuestros-cursos-de-data\">Te gustar\u00eda acceder a un curso<\/a><span style=\"font-weight: 400;\"> m\u00e1s detallado sobre los diferentes puntos tratados en este art\u00edculo?\u00a0\u00a0<\/span><\/p>\t\t\t\t\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t\t\t<div class=\"elementor-element elementor-element-d7c4130 elementor-widget elementor-widget-image\" data-id=\"d7c4130\" data-element_type=\"widget\" data-widget_type=\"image.default\">\n\t\t\t\t<div class=\"elementor-widget-container\">\n\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t<img decoding=\"async\" width=\"512\" height=\"489\" src=\"https:\/\/datascientest.com\/es\/files\/2020\/09\/word2vec_2.png\" class=\"attachment-large size-large wp-image-9909\" alt=\"word2vec\" srcset=\"https:\/\/datascientest.com\/es\/files\/2020\/09\/word2vec_2.png 512w, https:\/\/datascientest.com\/es\/files\/2020\/09\/word2vec_2-300x287.png 300w\" sizes=\"(max-width: 512px) 100vw, 512px\" \/>\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t\t\t<div class=\"elementor-element elementor-element-55ef10b elementor-align-center elementor-widget elementor-widget-button\" data-id=\"55ef10b\" data-element_type=\"widget\" data-widget_type=\"button.default\">\n\t\t\t\t<div class=\"elementor-widget-container\">\n\t\t\t\t\t<div class=\"elementor-button-wrapper\">\n\t\t\t<a class=\"elementor-button elementor-button-link elementor-size-sm\" href=\"https:\/\/datascientest.com\/es\/nuestros-cursos-de-data\">\n\t\t\t\t\t\t<span class=\"elementor-button-content-wrapper\">\n\t\t\t\t\t\t<span class=\"elementor-button-text\">\u00a1Descubre todos nuestros m\u00f3dulos!<\/span>\n\t\t<\/span>\n\t\t\t\t\t<\/a>\n\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t\t\t\t<\/div>\n\t\t<\/div>\n\t\t\t\t\t\t\t<\/div>\n\t\t<\/section>\n\t\t<div class=\"elementor-element elementor-element-368750d e-flex e-con-boxed e-con\" data-id=\"368750d\" data-element_type=\"container\" data-settings=\"{&quot;content_width&quot;:&quot;boxed&quot;}\">\n\t\t\t\t\t<div class=\"e-con-inner\">\n\t\t\t\t<div class=\"elementor-element elementor-element-7db5ad1 elementor-widget elementor-widget-html\" data-id=\"7db5ad1\" data-element_type=\"widget\" data-widget_type=\"html.default\">\n\t\t\t\t<div class=\"elementor-widget-container\">\n\t\t\t<script type=\"application\/ld+json\">\r\n{\r\n  \"@context\": \"https:\/\/schema.org\",\r\n  \"@type\": \"FAQPage\",\r\n  \"mainEntity\": {\r\n    \"@type\": \"Question\",\r\n    \"name\": \"\u00bfC\u00f3mo funciona word2vec?\",\r\n    \"acceptedAnswer\": {\r\n      \"@type\": \"Answer\",\r\n      \"text\": \"Existen dos variantes de Word2vec, ambas utilizan una red neuronal de 3 capas (1 capa de entrada, 1 capa oculta, 1 capa de salida): Common Bag Of Words (CBOW) y Skip-gram. En la siguiente imagen, la palabra del recuadro azul se llama palabra objetivo y las palabras de los recuadros blancos se llaman palabras de contexto en una ventana de tama\u00f1o 5.\"\r\n    }\r\n  }\r\n}\r\n<\/script>\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t\t\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t\t\t\t\t\t<\/div>\n\t\t","protected":false},"excerpt":{"rendered":"<p>El Word Embedding designa un conjunto de m\u00e9todos de aprendizaje que pretende representar las palabras de un texto mediante vectores de n\u00fameros reales. Hoy vamos a presentarte la 3.\u00aa parte de nuestro dosier NLP. Esta secci\u00f3n pretende explicar c\u00f3mo funciona el famoso algoritmo Word2vec en Python y su implementaci\u00f3n. Word Embedding Como recordatorio, el Word [&hellip;]<\/p>\n","protected":false},"author":45,"featured_media":9927,"comment_status":"open","ping_status":"closed","sticky":false,"template":"elementor_theme","format":"standard","meta":{"content-type":"","inline_featured_image":false},"categories":[2427],"tags":[],"yoast_head":"<!-- This site is optimized with the Yoast SEO Premium plugin v21.7 (Yoast SEO v21.7) - https:\/\/yoast.com\/wordpress\/plugins\/seo\/ -->\n<title>Word2vec : NLP y Word Embedding<\/title>\n<meta name=\"description\" content=\"El Word Embedding designa un conjunto de m\u00e9todos de aprendizaje que pretende representar las palabras de un texto mediante vectores de n\u00fameros reales. Hoy vamos a presentarte la 3.\u00aa parte de nuestro dosier NLP.\" \/>\n<meta name=\"robots\" content=\"index, follow, max-snippet:-1, max-image-preview:large, max-video-preview:-1\" \/>\n<link rel=\"canonical\" href=\"https:\/\/datascientest.com\/es\/nlp-word-embedding-word2vec-es\" \/>\n<meta property=\"og:locale\" content=\"es_ES\" \/>\n<meta property=\"og:type\" content=\"article\" \/>\n<meta property=\"og:title\" content=\"Word2vec : NLP y Word Embedding\" \/>\n<meta property=\"og:description\" content=\"El Word Embedding designa un conjunto de m\u00e9todos de aprendizaje que pretende representar las palabras de un texto mediante vectores de n\u00fameros reales. Hoy\" \/>\n<meta property=\"og:url\" content=\"https:\/\/datascientest.com\/es\/nlp-word-embedding-word2vec-es\" \/>\n<meta property=\"og:site_name\" content=\"Formaci\u00f3n en ciencia de datos | DataScientest.com\" \/>\n<meta property=\"article:publisher\" content=\"https:\/\/www.facebook.com\/DataScientestEN\" \/>\n<meta property=\"article:published_time\" content=\"2022-05-17T13:50:13+00:00\" \/>\n<meta property=\"article:modified_time\" content=\"2023-10-30T16:15:37+00:00\" \/>\n<meta property=\"og:image\" content=\"https:\/\/datascientest.com\/es\/wp-content\/blogs.dir\/7\/files\/2020\/09\/word2vec.jpg\" \/>\n\t<meta property=\"og:image:width\" content=\"1520\" \/>\n\t<meta property=\"og:image:height\" content=\"600\" \/>\n\t<meta property=\"og:image:type\" content=\"image\/jpeg\" \/>\n<meta name=\"author\" content=\"Daniel\" \/>\n<meta name=\"twitter:card\" content=\"summary_large_image\" \/>\n<meta name=\"twitter:creator\" content=\"@DataScientest__\" \/>\n<meta name=\"twitter:site\" content=\"@DataScientest__\" \/>\n<meta name=\"twitter:label1\" content=\"Escrito por\" \/>\n\t<meta name=\"twitter:data1\" content=\"Daniel\" \/>\n\t<meta name=\"twitter:label2\" content=\"Tiempo de lectura\" \/>\n\t<meta name=\"twitter:data2\" content=\"7 minutos\" \/>\n<script type=\"application\/ld+json\" class=\"yoast-schema-graph\">{\"@context\":\"https:\/\/schema.org\",\"@graph\":[{\"@type\":\"Article\",\"@id\":\"https:\/\/datascientest.com\/es\/nlp-word-embedding-word2vec-es#article\",\"isPartOf\":{\"@id\":\"https:\/\/datascientest.com\/es\/nlp-word-embedding-word2vec-es\"},\"author\":{\"name\":\"Daniel\",\"@id\":\"https:\/\/datascientest.com\/es\/#\/schema\/person\/5a86e30c5090234fb43dd8baa83c44b0\"},\"headline\":\"Word2vec : NLP y Word Embedding\",\"datePublished\":\"2022-05-17T13:50:13+00:00\",\"dateModified\":\"2023-10-30T16:15:37+00:00\",\"mainEntityOfPage\":{\"@id\":\"https:\/\/datascientest.com\/es\/nlp-word-embedding-word2vec-es\"},\"wordCount\":1057,\"commentCount\":0,\"publisher\":{\"@id\":\"https:\/\/datascientest.com\/es\/#organization\"},\"articleSection\":[\"Data Science\"],\"inLanguage\":\"es\",\"potentialAction\":[{\"@type\":\"CommentAction\",\"name\":\"Comment\",\"target\":[\"https:\/\/datascientest.com\/es\/nlp-word-embedding-word2vec-es#respond\"]}],\"copyrightYear\":\"2022\",\"copyrightHolder\":{\"@id\":\"https:\/\/datascientest.com\/#organization\"}},{\"@type\":\"WebPage\",\"@id\":\"https:\/\/datascientest.com\/es\/nlp-word-embedding-word2vec-es\",\"url\":\"https:\/\/datascientest.com\/es\/nlp-word-embedding-word2vec-es\",\"name\":\"Word2vec : NLP y Word Embedding\",\"isPartOf\":{\"@id\":\"https:\/\/datascientest.com\/es\/#website\"},\"datePublished\":\"2022-05-17T13:50:13+00:00\",\"dateModified\":\"2023-10-30T16:15:37+00:00\",\"description\":\"El Word Embedding designa un conjunto de m\u00e9todos de aprendizaje que pretende representar las palabras de un texto mediante vectores de n\u00fameros reales. Hoy vamos a presentarte la 3.\u00aa parte de nuestro dosier NLP.\",\"inLanguage\":\"es\",\"potentialAction\":[{\"@type\":\"ReadAction\",\"target\":[\"https:\/\/datascientest.com\/es\/nlp-word-embedding-word2vec-es\"]}]},{\"@type\":\"WebSite\",\"@id\":\"https:\/\/datascientest.com\/es\/#website\",\"url\":\"https:\/\/datascientest.com\/es\/\",\"name\":\"Formaci\u00f3n en ciencia de datos | DataScientest.com\",\"description\":\"L\u00edder en formaci\u00f3n en Ciencia de Datos\",\"publisher\":{\"@id\":\"https:\/\/datascientest.com\/es\/#organization\"},\"potentialAction\":[{\"@type\":\"SearchAction\",\"target\":{\"@type\":\"EntryPoint\",\"urlTemplate\":\"https:\/\/datascientest.com\/es\/?s={search_term_string}\"},\"query-input\":\"required name=search_term_string\"}],\"inLanguage\":\"es\"},{\"@type\":\"Organization\",\"@id\":\"https:\/\/datascientest.com\/es\/#organization\",\"name\":\"DataScientest\",\"url\":\"https:\/\/datascientest.com\/es\/\",\"logo\":{\"@type\":\"ImageObject\",\"inLanguage\":\"es\",\"@id\":\"https:\/\/datascientest.com\/es\/#\/schema\/logo\/image\/\",\"url\":\"https:\/\/datascientest.com\/es\/wp-content\/blogs.dir\/7\/files\/2024\/02\/DataScientest_icon_blue-2.png\",\"contentUrl\":\"https:\/\/datascientest.com\/es\/wp-content\/blogs.dir\/7\/files\/2024\/02\/DataScientest_icon_blue-2.png\",\"width\":301,\"height\":301,\"caption\":\"DataScientest\"},\"image\":{\"@id\":\"https:\/\/datascientest.com\/es\/#\/schema\/logo\/image\/\"},\"sameAs\":[\"https:\/\/www.facebook.com\/DataScientestEN\",\"https:\/\/twitter.com\/DataScientest__\",\"https:\/\/www.linkedin.com\/company\/datascientest-spain\/\",\"https:\/\/www.tiktok.com\/@datascientest\"]},{\"@type\":\"Person\",\"@id\":\"https:\/\/datascientest.com\/es\/#\/schema\/person\/5a86e30c5090234fb43dd8baa83c44b0\",\"name\":\"Daniel\",\"image\":{\"@type\":\"ImageObject\",\"inLanguage\":\"es\",\"@id\":\"https:\/\/datascientest.com\/es\/#\/schema\/person\/image\/\",\"url\":\"https:\/\/secure.gravatar.com\/avatar\/837acad4f2dc47e85d81cce837261670?s=96&d=mm&r=g\",\"contentUrl\":\"https:\/\/secure.gravatar.com\/avatar\/837acad4f2dc47e85d81cce837261670?s=96&d=mm&r=g\",\"caption\":\"Daniel\"},\"sameAs\":[\"https:\/\/www.linkedin.com\/school\/datascientest\/\",\"user\"],\"jobTitle\":\"ing\u00e9nieur logiciel\",\"worksFor\":\"DataScientest\",\"url\":\"https:\/\/datascientest.com\/es\/author\/team-redac\"}]}<\/script>\n<!-- \/ Yoast SEO Premium plugin. -->","yoast_head_json":{"title":"Word2vec : NLP y Word Embedding","description":"El Word Embedding designa un conjunto de m\u00e9todos de aprendizaje que pretende representar las palabras de un texto mediante vectores de n\u00fameros reales. Hoy vamos a presentarte la 3.\u00aa parte de nuestro dosier NLP.","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:\/\/datascientest.com\/es\/nlp-word-embedding-word2vec-es","og_locale":"es_ES","og_type":"article","og_title":"Word2vec : NLP y Word Embedding","og_description":"El Word Embedding designa un conjunto de m\u00e9todos de aprendizaje que pretende representar las palabras de un texto mediante vectores de n\u00fameros reales. Hoy","og_url":"https:\/\/datascientest.com\/es\/nlp-word-embedding-word2vec-es","og_site_name":"Formaci\u00f3n en ciencia de datos | DataScientest.com","article_publisher":"https:\/\/www.facebook.com\/DataScientestEN","article_published_time":"2022-05-17T13:50:13+00:00","article_modified_time":"2023-10-30T16:15:37+00:00","og_image":[{"width":1520,"height":600,"url":"https:\/\/datascientest.com\/es\/wp-content\/blogs.dir\/7\/files\/2020\/09\/word2vec.jpg","type":"image\/jpeg"}],"author":"Daniel","twitter_card":"summary_large_image","twitter_creator":"@DataScientest__","twitter_site":"@DataScientest__","twitter_misc":{"Escrito por":"Daniel","Tiempo de lectura":"7 minutos"},"schema":{"@context":"https:\/\/schema.org","@graph":[{"@type":"Article","@id":"https:\/\/datascientest.com\/es\/nlp-word-embedding-word2vec-es#article","isPartOf":{"@id":"https:\/\/datascientest.com\/es\/nlp-word-embedding-word2vec-es"},"author":{"name":"Daniel","@id":"https:\/\/datascientest.com\/es\/#\/schema\/person\/5a86e30c5090234fb43dd8baa83c44b0"},"headline":"Word2vec : NLP y Word Embedding","datePublished":"2022-05-17T13:50:13+00:00","dateModified":"2023-10-30T16:15:37+00:00","mainEntityOfPage":{"@id":"https:\/\/datascientest.com\/es\/nlp-word-embedding-word2vec-es"},"wordCount":1057,"commentCount":0,"publisher":{"@id":"https:\/\/datascientest.com\/es\/#organization"},"articleSection":["Data Science"],"inLanguage":"es","potentialAction":[{"@type":"CommentAction","name":"Comment","target":["https:\/\/datascientest.com\/es\/nlp-word-embedding-word2vec-es#respond"]}],"copyrightYear":"2022","copyrightHolder":{"@id":"https:\/\/datascientest.com\/#organization"}},{"@type":"WebPage","@id":"https:\/\/datascientest.com\/es\/nlp-word-embedding-word2vec-es","url":"https:\/\/datascientest.com\/es\/nlp-word-embedding-word2vec-es","name":"Word2vec : NLP y Word Embedding","isPartOf":{"@id":"https:\/\/datascientest.com\/es\/#website"},"datePublished":"2022-05-17T13:50:13+00:00","dateModified":"2023-10-30T16:15:37+00:00","description":"El Word Embedding designa un conjunto de m\u00e9todos de aprendizaje que pretende representar las palabras de un texto mediante vectores de n\u00fameros reales. Hoy vamos a presentarte la 3.\u00aa parte de nuestro dosier NLP.","inLanguage":"es","potentialAction":[{"@type":"ReadAction","target":["https:\/\/datascientest.com\/es\/nlp-word-embedding-word2vec-es"]}]},{"@type":"WebSite","@id":"https:\/\/datascientest.com\/es\/#website","url":"https:\/\/datascientest.com\/es\/","name":"Formaci\u00f3n en ciencia de datos | DataScientest.com","description":"L\u00edder en formaci\u00f3n en Ciencia de Datos","publisher":{"@id":"https:\/\/datascientest.com\/es\/#organization"},"potentialAction":[{"@type":"SearchAction","target":{"@type":"EntryPoint","urlTemplate":"https:\/\/datascientest.com\/es\/?s={search_term_string}"},"query-input":"required name=search_term_string"}],"inLanguage":"es"},{"@type":"Organization","@id":"https:\/\/datascientest.com\/es\/#organization","name":"DataScientest","url":"https:\/\/datascientest.com\/es\/","logo":{"@type":"ImageObject","inLanguage":"es","@id":"https:\/\/datascientest.com\/es\/#\/schema\/logo\/image\/","url":"https:\/\/datascientest.com\/es\/wp-content\/blogs.dir\/7\/files\/2024\/02\/DataScientest_icon_blue-2.png","contentUrl":"https:\/\/datascientest.com\/es\/wp-content\/blogs.dir\/7\/files\/2024\/02\/DataScientest_icon_blue-2.png","width":301,"height":301,"caption":"DataScientest"},"image":{"@id":"https:\/\/datascientest.com\/es\/#\/schema\/logo\/image\/"},"sameAs":["https:\/\/www.facebook.com\/DataScientestEN","https:\/\/twitter.com\/DataScientest__","https:\/\/www.linkedin.com\/company\/datascientest-spain\/","https:\/\/www.tiktok.com\/@datascientest"]},{"@type":"Person","@id":"https:\/\/datascientest.com\/es\/#\/schema\/person\/5a86e30c5090234fb43dd8baa83c44b0","name":"Daniel","image":{"@type":"ImageObject","inLanguage":"es","@id":"https:\/\/datascientest.com\/es\/#\/schema\/person\/image\/","url":"https:\/\/secure.gravatar.com\/avatar\/837acad4f2dc47e85d81cce837261670?s=96&d=mm&r=g","contentUrl":"https:\/\/secure.gravatar.com\/avatar\/837acad4f2dc47e85d81cce837261670?s=96&d=mm&r=g","caption":"Daniel"},"sameAs":["https:\/\/www.linkedin.com\/school\/datascientest\/","user"],"jobTitle":"ing\u00e9nieur logiciel","worksFor":"DataScientest","url":"https:\/\/datascientest.com\/es\/author\/team-redac"}]}},"_links":{"self":[{"href":"https:\/\/datascientest.com\/es\/wp-json\/wp\/v2\/posts\/159494"}],"collection":[{"href":"https:\/\/datascientest.com\/es\/wp-json\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/datascientest.com\/es\/wp-json\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/datascientest.com\/es\/wp-json\/wp\/v2\/users\/45"}],"replies":[{"embeddable":true,"href":"https:\/\/datascientest.com\/es\/wp-json\/wp\/v2\/comments?post=159494"}],"version-history":[{"count":0,"href":"https:\/\/datascientest.com\/es\/wp-json\/wp\/v2\/posts\/159494\/revisions"}],"wp:featuredmedia":[{"embeddable":true,"href":"https:\/\/datascientest.com\/es\/wp-json\/wp\/v2\/media\/9927"}],"wp:attachment":[{"href":"https:\/\/datascientest.com\/es\/wp-json\/wp\/v2\/media?parent=159494"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/datascientest.com\/es\/wp-json\/wp\/v2\/categories?post=159494"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/datascientest.com\/es\/wp-json\/wp\/v2\/tags?post=159494"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}