{"id":166017,"date":"2022-10-16T12:58:31","date_gmt":"2022-10-16T11:58:31","guid":{"rendered":"https:\/\/datascientest.com\/es\/?p=166017"},"modified":"2023-10-30T17:39:12","modified_gmt":"2023-10-30T16:39:12","slug":"word-embedding","status":"publish","type":"post","link":"https:\/\/datascientest.com\/es\/word-embedding","title":{"rendered":"Word Embedding"},"content":{"rendered":"\t\t<div data-elementor-type=\"wp-post\" data-elementor-id=\"166017\" class=\"elementor elementor-166017\" data-elementor-post-type=\"post\">\n\t\t\t\t\t\t\t<div class=\"elementor-element elementor-element-65d72b3 e-flex e-con-boxed e-con\" data-id=\"65d72b3\" 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-6eb0d44 elementor-widget elementor-widget-text-editor\" data-id=\"6eb0d44\" 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<h2><strong>En un <a href=\"https:\/\/datascientest.com\/es\/nlp-natural-language-processing-introduccion\"><span style=\"text-decoration: underline\">art\u00edculo anterior<\/span><\/a>, definimos NLP &#8211; Procesamiento del Lenguaje Natural. En este art\u00edculo, nos centraremos en uno de sus principales m\u00e9todos, el Word Embedding. El Word Embedding (incrustaci\u00f3n de palabras) designa un conjunto de m\u00e9todos de aprendizaje destinados a representar las palabras de un texto mediante vectores num\u00e9ricos reales. En este art\u00edculo, vas a explorar tres de los m\u00e9todos principales para representar una palabra como vector :<\/strong><\/h2><ul><li><h2><strong>M\u00e9todo 1 : One Hot Encoding<\/strong><\/h2><\/li><li><h2><strong>M\u00e9todo 2 : Image Embedding<\/strong><\/h2><\/li><li><h2><strong>M\u00e9todo 3\u00a0: Word Embedding<\/strong><\/h2><\/li><\/ul>\t\t\t\t\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t\t\t<div class=\"elementor-element elementor-element-cc62c58 elementor-widget elementor-widget-image\" data-id=\"cc62c58\" 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=\"300\" height=\"285\" src=\"https:\/\/datascientest.com\/es\/files\/2020\/09\/Frise-300x285.png\" class=\"attachment-medium size-medium wp-image-7985\" alt=\"word embedding\" srcset=\"https:\/\/datascientest.com\/es\/files\/2020\/09\/Frise-300x285.png 300w, https:\/\/datascientest.com\/es\/files\/2020\/09\/Frise-1024x972.png 1024w, https:\/\/datascientest.com\/es\/files\/2020\/09\/Frise-768x729.png 768w, https:\/\/datascientest.com\/es\/files\/2020\/09\/Frise-1536x1457.png 1536w, https:\/\/datascientest.com\/es\/files\/2020\/09\/Frise.png 1778w\" sizes=\"(max-width: 300px) 100vw, 300px\" \/>\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\t<\/div>\n\t\t\t\t<\/div>\n\t\t<div class=\"elementor-element elementor-element-52bf5ef e-flex e-con-boxed e-con\" data-id=\"52bf5ef\" 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-67fb032 elementor-widget elementor-widget-heading\" data-id=\"67fb032\" 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><h3 class=\"elementor-heading-title elementor-size-default\">One hot encoding<\/h3>\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t\t\t<div class=\"elementor-element elementor-element-3ad22c1 elementor-widget elementor-widget-text-editor\" data-id=\"3ad22c1\" 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 representaci\u00f3n vectorial m\u00e1s cl\u00e1sica de las palabras es la one hot encoding. Se asigna una dimensi\u00f3n a cada palabra del vocabulario. Cada palabra del vocabulario se representa como un vector binario con todos sus valores a cero, excepto el \u00edndice 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-ac4d55e elementor-widget elementor-widget-image\" data-id=\"ac4d55e\" 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\/@athif.shaffy\/one-hot-encoding-of-text-b69124bef0a7\">\n\t\t\t\t\t\t\t<img decoding=\"async\" width=\"800\" height=\"420\" src=\"https:\/\/datascientest.com\/es\/files\/2020\/08\/1-1024x537.png\" class=\"attachment-large size-large wp-image-6970\" alt=\"\" srcset=\"https:\/\/datascientest.com\/es\/files\/2020\/08\/1-1024x537.png 1024w, https:\/\/datascientest.com\/es\/files\/2020\/08\/1-300x157.png 300w, https:\/\/datascientest.com\/es\/files\/2020\/08\/1.png 1235w\" sizes=\"(max-width: 800px) 100vw, 800px\" \/>\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\"><\/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-3076814 elementor-widget elementor-widget-text-editor\" data-id=\"3076814\" 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\">Para ilustrar la codificaci\u00f3n, analicemos la siguiente frase :<\/span><\/p><p style=\"padding-left: 360px\"><span style=\"color: #000000;font-family: 'Courier New';font-size: 14px;font-style: normal;font-weight: 400\">\u00abI think therefore I am\u00bb<br \/><\/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-c644c2b elementor-widget elementor-widget-text-editor\" data-id=\"c644c2b\" 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>El principio es asignar un \u00edndice a cada palabra del vocabulario. El <strong>vocabulario<\/strong> se presenta entonces en forma de diccionario :<\/p><pre style=\"padding-left: 280px\"><span style=\"font-weight: 400\">{'am': 0, 'i': 1, 'therefore': 2, 'think': 3}<\/span><\/pre>\t\t\t\t\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t\t\t<div class=\"elementor-element elementor-element-6ef83f3 elementor-widget elementor-widget-text-editor\" data-id=\"6ef83f3\" 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>Aqu\u00ed, <strong>el vocabulario est\u00e1 compuesto por las 4 palabras \u00fanicas de nuestro corpus<\/strong>. El m\u00e9todo consiste entonces en representar la palabra del vocabulario como un vector de dimensi\u00f3n 4 (tama\u00f1o del vocabulario) que tiene todos sus valores a cero excepto el \u00edndice de la palabra.<\/p><p style=\"padding-left: 400px\"><em><span style=\"font-weight: 400\">Onehot(<\/span><span style=\"font-weight: 400\">&#8216;i&#8217;)<\/span><span style=\"font-weight: 400\">=<\/span><span style=\"font-weight: 400\">0<\/span> <span style=\"font-weight: 400\">1<\/span> <span style=\"font-weight: 400\">0<\/span> <span style=\"font-weight: 400\">0<\/span><\/em><\/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-5eef41e elementor-widget elementor-widget-text-editor\" data-id=\"5eef41e\" 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>Con esta representaci\u00f3n, <strong>todas las palabras tienen la misma distancia y similitud<\/strong>. Por tanto, la codificaci\u00f3n <strong>one hot<\/strong> solo proporciona informaci\u00f3n seg\u00fan la cual una <strong>palabra es diferente de otr<\/strong>a.<\/p>\t\t\t\t\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<div class=\"elementor-element elementor-element-bb5ea8d e-flex e-con-boxed e-con\" data-id=\"bb5ea8d\" 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-ef4bbfb elementor-widget elementor-widget-heading\" data-id=\"ef4bbfb\" data-element_type=\"widget\" data-widget_type=\"heading.default\">\n\t\t\t\t<div class=\"elementor-widget-container\">\n\t\t\t<h3 class=\"elementor-heading-title elementor-size-default\">Image Embedding<\/h3>\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t\t\t<div class=\"elementor-element elementor-element-0151d2a elementor-widget elementor-widget-text-editor\" data-id=\"0151d2a\" 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>El tama\u00f1o de una imagen se define por su n\u00famero de p\u00edxeles. Como vimos en un art\u00edculo anterior [enlace a la secci\u00f3n CNN del dosier DL], utilizamos <strong>convoluciones para extraer las caracter\u00edsticas m\u00e1s relevantes que el valor de los p\u00edxeles<\/strong>. Por ejemplo, los n\u00facleos utilizados para detectar bordes podr\u00edan ser \u00fatiles para clasificar determinadas formas geom\u00e9tricas.<\/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-012a17d elementor-widget elementor-widget-image\" data-id=\"012a17d\" 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:\/\/towardsdatascience.com\/a-comprehensive-guide-to-convolutional-neural-networks-the-eli5-way-3bd2b1164a53\">\n\t\t\t\t\t\t\t<img decoding=\"async\" width=\"800\" height=\"275\" src=\"https:\/\/datascientest.com\/es\/files\/2020\/08\/2-1-1024x352.png\" class=\"attachment-large size-large wp-image-6971\" alt=\"\" srcset=\"https:\/\/datascientest.com\/es\/files\/2020\/08\/2-1-1024x352.png 1024w, https:\/\/datascientest.com\/es\/files\/2020\/08\/2-1-300x103.png 300w, https:\/\/datascientest.com\/es\/files\/2020\/08\/2-1-768x264.png 768w, https:\/\/datascientest.com\/es\/files\/2020\/08\/2-1.png 1337w\" sizes=\"(max-width: 800px) 100vw, 800px\" \/>\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\">Red neuronal convolucional<\/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-eaae77d elementor-widget elementor-widget-text-editor\" data-id=\"eaae77d\" 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>El image embedding es capaz de utilizar las convoluciones\/pooling para codificar la imagen y extraer las <strong>relaciones de linealidad entre las propiedades (estilo art\u00edstico, forma espec\u00edfica, etc.) y las nuevas caracter\u00edsticas de nuestra imagen<\/strong>.<\/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-abb4188 elementor-widget elementor-widget-image\" data-id=\"abb4188\" 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:\/\/www.oreilly.com\/library\/view\/practical-deep-learning\/9781492034858\/ch04.html\">\n\t\t\t\t\t\t\t<img decoding=\"async\" width=\"300\" height=\"296\" src=\"https:\/\/datascientest.com\/es\/files\/2020\/08\/3-1-300x296.png\" class=\"attachment-medium size-medium wp-image-6972\" alt=\"\" srcset=\"https:\/\/datascientest.com\/es\/files\/2020\/08\/3-1-300x296.png 300w, https:\/\/datascientest.com\/es\/files\/2020\/08\/3-1-1024x1009.png 1024w, https:\/\/datascientest.com\/es\/files\/2020\/08\/3-1-768x757.png 768w, https:\/\/datascientest.com\/es\/files\/2020\/08\/3-1.png 1440w\" sizes=\"(max-width: 300px) 100vw, 300px\" \/>\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\">ACP en el embedding de im\u00e1genes<\/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\t\t<\/div>\n\t\t<div class=\"elementor-element elementor-element-d19a93f e-flex e-con-boxed e-con\" data-id=\"d19a93f\" 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-b1fd2fc elementor-widget elementor-widget-heading\" data-id=\"b1fd2fc\" data-element_type=\"widget\" data-widget_type=\"heading.default\">\n\t\t\t\t<div class=\"elementor-widget-container\">\n\t\t\t<h3 class=\"elementor-heading-title elementor-size-default\">Word Embedding<\/h3>\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t\t\t<div class=\"elementor-element elementor-element-ca82295 elementor-widget elementor-widget-text-editor\" data-id=\"ca82295\" 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>Por analog\u00eda, <strong>el word embedding es capaz de capturar el contexto, la similitud sem\u00e1ntica y sint\u00e1ctica (g\u00e9nero, sin\u00f3nimos, etc.) de una palabra reduciendo el tama\u00f1o<\/strong>. Por ejemplo, cabr\u00eda esperar que las palabras \u00abperro\u00bb y \u00abgato\u00bb estuvieran representadas por vectores relativamente cercanos en el espacio vectorial donde se definen esos vectores.<\/p><p>Al igual que con las im\u00e1genes, queremos que <strong>el modelo elija las caracter\u00edsticas m\u00e1s relevantes para representar la palabra<\/strong>. Por ejemplo, la caracter\u00edstica \u00abser vivo\u00bb podr\u00eda ser interesante para diferenciar \u00abperro\u00bb y \u00abordenador\u00bb, y para acercar \u00abperro\u00bb y \u00abgato\u00bb.<\/p>\t\t\t\t\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<div class=\"elementor-element elementor-element-920fe84 e-flex e-con-boxed e-con\" data-id=\"920fe84\" 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-3f3269a elementor-widget elementor-widget-heading\" data-id=\"3f3269a\" data-element_type=\"widget\" data-widget_type=\"heading.default\">\n\t\t\t\t<div class=\"elementor-widget-container\">\n\t\t\t<h3 class=\"elementor-heading-title elementor-size-default\">Matrice d\u2019embedding<\/h3>\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t\t\t<div class=\"elementor-element elementor-element-8609285 elementor-widget elementor-widget-text-editor\" data-id=\"8609285\" 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\">El m\u00e9todo de embedding que se suele utilizar para reducir la dimensi\u00f3n de un vector es utilizar el resultado que devuelve una capa densa como embedding, 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-6ef325a elementor-widget elementor-widget-image\" data-id=\"6ef325a\" 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=\"332\" height=\"162\" src=\"https:\/\/datascientest.com\/es\/files\/2020\/08\/2-3.png\" class=\"attachment-large size-large wp-image-6976\" alt=\"\" srcset=\"https:\/\/datascientest.com\/es\/files\/2020\/08\/2-3.png 332w, https:\/\/datascientest.com\/es\/files\/2020\/08\/2-3-300x146.png 300w\" sizes=\"(max-width: 332px) 100vw, 332px\" \/>\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-76f37d3 elementor-widget elementor-widget-text-editor\" data-id=\"76f37d3\" 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 de vector :<\/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-6d8824e elementor-widget elementor-widget-image\" data-id=\"6d8824e\" 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=\"313\" height=\"53\" src=\"https:\/\/datascientest.com\/es\/files\/2020\/08\/5.png\" class=\"attachment-large size-large wp-image-6977\" alt=\"\" srcset=\"https:\/\/datascientest.com\/es\/files\/2020\/08\/5.png 313w, https:\/\/datascientest.com\/es\/files\/2020\/08\/5-300x51.png 300w\" sizes=\"(max-width: 313px) 100vw, 313px\" \/>\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-3743f85 elementor-widget elementor-widget-image\" data-id=\"3743f85\" 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\t<a href=\"https:\/\/medium.com\/datadriveninvestor\/deep-learning-autoencoders-db265359943e\">\n\t\t\t\t\t\t\t<img decoding=\"async\" width=\"254\" height=\"300\" src=\"https:\/\/datascientest.com\/es\/files\/2020\/08\/4-254x300.png\" class=\"attachment-medium size-medium wp-image-6978\" alt=\"\" srcset=\"https:\/\/datascientest.com\/es\/files\/2020\/08\/4-254x300.png 254w, https:\/\/datascientest.com\/es\/files\/2020\/08\/4.png 454w\" sizes=\"(max-width: 254px) 100vw, 254px\" \/>\t\t\t\t\t\t\t\t<\/a>\n\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-7d82a44 elementor-widget elementor-widget-text-editor\" data-id=\"7d82a44\" 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>Ahora que hemos definido el m\u00e9todo de reducci\u00f3n de la dimensi\u00f3n (compresi\u00f3n de la informaci\u00f3n), \u00bfc\u00f3mo entrenamos la matriz de embedding <strong>W<\/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\t\t<\/div>\n\t\t<div class=\"elementor-element elementor-element-1cbd1a4 e-flex e-con-boxed e-con\" data-id=\"1cbd1a4\" 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-4c1cec2 elementor-widget elementor-widget-heading\" data-id=\"4c1cec2\" data-element_type=\"widget\" data-widget_type=\"heading.default\">\n\t\t\t\t<div class=\"elementor-widget-container\">\n\t\t\t<h3 class=\"elementor-heading-title elementor-size-default\">Entrenamiento de la matriz de embedding: problema de clasificaci\u00f3n<\/h3>\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t\t\t<div class=\"elementor-element elementor-element-24aba74 elementor-widget elementor-widget-text-editor\" data-id=\"24aba74\" 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>Una primera forma de encontrar la <strong>matriz de embedding es entrenarla en un problema supervisado<\/strong>. Por tanto, utilizaremos <strong>esa representaci\u00f3n de palabras para resolver un problema de an\u00e1lisis de sentimientos<\/strong> en las rese\u00f1as de IMBD. La serie de datos contiene 25.000 cr\u00edticas de pel\u00edculas (m\u00e1s informaci\u00f3n sobre la serie de datos <a href=\"https:\/\/ai.stanford.edu\/~amaas\/data\/sentiment\/\"><span style=\"text-decoration: underline\"><strong>aqu\u00ed<\/strong><\/span><\/a>).<\/p><p>Entonces se puede <strong>entrenar la matriz W del word embedding a la vez que se entrena el problema de clasificaci\u00f3n<\/strong>.<\/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-3a550ef elementor-widget elementor-widget-heading\" data-id=\"3a550ef\" data-element_type=\"widget\" data-widget_type=\"heading.default\">\n\t\t\t\t<div class=\"elementor-widget-container\">\n\t\t\t<h4 class=\"elementor-heading-title elementor-size-default\">Formateo de los datos :<\/h4>\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t\t\t<div class=\"elementor-element elementor-element-8fb5832 elementor-widget elementor-widget-text-editor\" data-id=\"8fb5832\" 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\">Para formatear los datos, es necesario vectorizar el corpus de texto, transformando cada rese\u00f1a en una secuencia de enteros (cada n\u00famero entero es el \u00edndice de una palabra) :<\/span><\/p><p style=\"padding-left: 120px\"><span style=\"font-size: 10.5pt;font-family: 'Courier New';color: #000000;background-color: #ffffff;font-weight: 400;font-style: normal;font-variant: normal;text-decoration: none;vertical-align: baseline\">tokenizer.texts_to_sequences([&#8216;hello my dear readers&#8217;]) <\/span><span style=\"color: #000000;font-family: 'Courier New';font-size: 10.5pt;font-style: normal;font-weight: 400\">-&gt; [[4422, 10, 2974, 6117]]<\/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-d6ae3cc elementor-widget elementor-widget-image\" data-id=\"d6ae3cc\" 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=\"610\" src=\"https:\/\/datascientest.com\/es\/files\/2020\/08\/2-2.png\" class=\"attachment-large size-large wp-image-6973\" alt=\"\" srcset=\"https:\/\/datascientest.com\/es\/files\/2020\/08\/2-2.png 940w, https:\/\/datascientest.com\/es\/files\/2020\/08\/2-2-300x229.png 300w, https:\/\/datascientest.com\/es\/files\/2020\/08\/2-2-768x586.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-a30d0df elementor-widget elementor-widget-text-editor\" data-id=\"a30d0df\" 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\">Nuestro modelo ser\u00e1 un simple bag of word con un m\u00e9todo de embedding :<\/span><\/p><ol><li><span style=\"font-weight: 400\"> La capa de embedding transformar\u00e1 cada \u00edndice de palabras en un vector de embedding. La matriz W del embedding se aprender\u00e1 a medida que se entrene el modelo. Las dimensiones resultantes son: (lote, secuencia, embedding).<\/span><\/li><li><span style=\"font-weight: 400\"> A continuaci\u00f3n, la capa GlobalAveragePooling1D devuelve un vector de salida de longitud fija para cada ejemplo, sacando la media de la dimensi\u00f3n de la secuencia. Esta transformaci\u00f3n consiste en hacer una bag of word y permite que el modelo gestione entradas de longitud variable.<\/span><\/li><li><span style=\"font-weight: 400\"> Por \u00faltimo, como estamos ante un problema de clasificaci\u00f3n (rese\u00f1a positiva o negativa), es necesario a\u00f1adir capas densas para clasificar el sentimiento de la rese\u00f1a.<\/span><\/li><\/ol>\t\t\t\t\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<div class=\"elementor-element elementor-element-275a6e0 e-flex e-con-boxed e-con\" data-id=\"275a6e0\" 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-3e7d113 elementor-widget elementor-widget-heading\" data-id=\"3e7d113\" data-element_type=\"widget\" data-widget_type=\"heading.default\">\n\t\t\t\t<div class=\"elementor-widget-container\">\n\t\t\t<h3 class=\"elementor-heading-title elementor-size-default\">\u00bfY si pasamos a la pr\u00e1ctica?<\/h3>\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t\t\t<div class=\"elementor-element elementor-element-629026f elementor-widget elementor-widget-shortcode\" data-id=\"629026f\" 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\"><\/div>\n\t\t\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t\t\t<div class=\"elementor-element elementor-element-9579239 elementor-widget elementor-widget-text-editor\" data-id=\"9579239\" 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\">De este modo, hemos conseguido en la serie de datos de prueba una precisi\u00f3n de 0,88. Esta puntuaci\u00f3n es dif\u00edcil de conseguir con ayuda de los m\u00e9todos cl\u00e1sicos. Adem\u00e1s, tambi\u00e9n podr\u00edamos haber utilizado un m\u00e9todo tf-idf (en lugar de la bag of word) para transformar nuestra secuencia en un vector.<\/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\t\t<\/div>\n\t\t<div class=\"elementor-element elementor-element-c2df658 e-flex e-con-boxed e-con\" data-id=\"c2df658\" 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-c519e72 elementor-widget elementor-widget-heading\" data-id=\"c519e72\" data-element_type=\"widget\" data-widget_type=\"heading.default\">\n\t\t\t\t<div class=\"elementor-widget-container\">\n\t\t\t<h3 class=\"elementor-heading-title elementor-size-default\">Conclusi\u00f3n<\/h3>\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t\t\t<div class=\"elementor-element elementor-element-2c3e8e5 elementor-widget elementor-widget-text-editor\" data-id=\"2c3e8e5\" 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\">Un modelo de este tipo suele dar mejores resultados que los enfoques tradicionales. Tambi\u00e9n permite reducir el tama\u00f1o del problema y, por tanto, la tarea de aprendizaje. Sin embargo, como solo damos informaci\u00f3n sobre el sentimiento, al word embedding le cuesta captar cualquier otra relaci\u00f3n.<\/span><\/p><p><span style=\"font-weight: 400\">En un pr\u00f3ximo art\u00edculo, entrenaremos la matriz de embedding de forma no supervisada utilizando el conocido algoritmo word2vec. Como el entrenamiento se realiza sin supervisi\u00f3n, evitaremos el sesgo asociado a la resoluci\u00f3n de un problema supervisado.<\/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-e93f080 elementor-widget elementor-widget-text-editor\" data-id=\"e93f080\" 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\">\u00bfTe ha gustado este art\u00edculo? \u00bfQuieres saber m\u00e1s sobre la Data Science?<\/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-fbe3247 elementor-align-center button-principale elementor-widget elementor-widget-button\" data-id=\"fbe3247\" 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 elementor-animation-grow\" 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\">\u00a1Inscr\u00edbete ya en alguno de nuestros cursos!<\/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\t\t<\/div>\n\t\t\t\t\t\t\t<\/div>\n\t\t","protected":false},"excerpt":{"rendered":"<p>En un art\u00edculo anterior, definimos NLP &#8211; Procesamiento del Lenguaje Natural. En este art\u00edculo, nos centraremos en uno de sus principales m\u00e9todos, el Word Embedding. El Word Embedding (incrustaci\u00f3n de palabras) designa un conjunto de m\u00e9todos de aprendizaje destinados a representar las palabras de un texto mediante vectores num\u00e9ricos reales. En este art\u00edculo, vas a [&hellip;]<\/p>\n","protected":false},"author":63,"featured_media":166019,"comment_status":"open","ping_status":"open","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>Word Embedding<\/title>\n<meta name=\"description\" content=\"Descubra word embedding, uno de los principales m\u00e9todos utilizados para el NLP - Natural Language Processing. \u00a1Te lo explicamos!\" \/>\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\/word-embedding\" \/>\n<meta property=\"og:locale\" content=\"es_ES\" \/>\n<meta property=\"og:type\" content=\"article\" \/>\n<meta property=\"og:title\" content=\"Word Embedding\" \/>\n<meta property=\"og:description\" content=\"En un art\u00edculo anterior, definimos NLP - Procesamiento del Lenguaje Natural. En este art\u00edculo, nos centraremos en uno de sus principales m\u00e9todos, el Word\" \/>\n<meta property=\"og:url\" content=\"https:\/\/datascientest.com\/es\/word-embedding\" \/>\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=\"2022-10-16T11:58:31+00:00\" \/>\n<meta property=\"article:modified_time\" content=\"2023-10-30T16:39:12+00:00\" \/>\n<meta property=\"og:image\" content=\"https:\/\/datascientest.com\/es\/wp-content\/blogs.dir\/7\/files\/2022\/10\/word-embedding.png\" \/>\n\t<meta property=\"og:image:width\" content=\"900\" \/>\n\t<meta property=\"og:image:height\" content=\"450\" \/>\n\t<meta property=\"og:image:type\" content=\"image\/png\" \/>\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=\"\" \/>\n\t<meta name=\"twitter:label2\" content=\"Tiempo de lectura\" \/>\n\t<meta name=\"twitter:data2\" content=\"6 minutos\" \/>\n<script type=\"application\/ld+json\" class=\"yoast-schema-graph\">{\"@context\":\"https:\/\/schema.org\",\"@graph\":[{\"@type\":\"Article\",\"@id\":\"https:\/\/datascientest.com\/es\/word-embedding#article\",\"isPartOf\":{\"@id\":\"https:\/\/datascientest.com\/es\/word-embedding\"},\"author\":{\"name\":\"\",\"@id\":\"\"},\"headline\":\"Word Embedding\",\"datePublished\":\"2022-10-16T11:58:31+00:00\",\"dateModified\":\"2023-10-30T16:39:12+00:00\",\"mainEntityOfPage\":{\"@id\":\"https:\/\/datascientest.com\/es\/word-embedding\"},\"wordCount\":1069,\"commentCount\":0,\"publisher\":{\"@id\":\"https:\/\/datascientest.com\/es\/#organization\"},\"articleSection\":[\"Data Science\"],\"inLanguage\":\"es\",\"potentialAction\":[{\"@type\":\"CommentAction\",\"name\":\"Comment\",\"target\":[\"https:\/\/datascientest.com\/es\/word-embedding#respond\"]}],\"copyrightYear\":\"2022\",\"copyrightHolder\":{\"@id\":\"https:\/\/datascientest.com\/#organization\"}},{\"@type\":\"WebPage\",\"@id\":\"https:\/\/datascientest.com\/es\/word-embedding\",\"url\":\"https:\/\/datascientest.com\/es\/word-embedding\",\"name\":\"Word Embedding\",\"isPartOf\":{\"@id\":\"https:\/\/datascientest.com\/es\/#website\"},\"datePublished\":\"2022-10-16T11:58:31+00:00\",\"dateModified\":\"2023-10-30T16:39:12+00:00\",\"description\":\"Descubra word embedding, uno de los principales m\u00e9todos utilizados para el NLP - Natural Language Processing. \u00a1Te lo explicamos!\",\"inLanguage\":\"es\",\"potentialAction\":[{\"@type\":\"ReadAction\",\"target\":[\"https:\/\/datascientest.com\/es\/word-embedding\"]}]},{\"@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\":\"\",\"url\":\"https:\/\/datascientest.com\/es\/author\"}]}<\/script>\n<!-- \/ Yoast SEO Premium plugin. -->","yoast_head_json":{"title":"Word Embedding","description":"Descubra word embedding, uno de los principales m\u00e9todos utilizados para el NLP - Natural Language Processing. \u00a1Te lo explicamos!","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\/word-embedding","og_locale":"es_ES","og_type":"article","og_title":"Word Embedding","og_description":"En un art\u00edculo anterior, definimos NLP - Procesamiento del Lenguaje Natural. En este art\u00edculo, nos centraremos en uno de sus principales m\u00e9todos, el Word","og_url":"https:\/\/datascientest.com\/es\/word-embedding","og_site_name":"Formaci\u00f3n en ciencia de datos | DataScientest.com","article_publisher":"https:\/\/www.facebook.com\/DataScientestEN","article_published_time":"2022-10-16T11:58:31+00:00","article_modified_time":"2023-10-30T16:39:12+00:00","og_image":[{"width":900,"height":450,"url":"https:\/\/datascientest.com\/es\/wp-content\/blogs.dir\/7\/files\/2022\/10\/word-embedding.png","type":"image\/png"}],"twitter_card":"summary_large_image","twitter_creator":"@DataScientest__","twitter_site":"@DataScientest__","twitter_misc":{"Escrito por":"","Tiempo de lectura":"6 minutos"},"schema":{"@context":"https:\/\/schema.org","@graph":[{"@type":"Article","@id":"https:\/\/datascientest.com\/es\/word-embedding#article","isPartOf":{"@id":"https:\/\/datascientest.com\/es\/word-embedding"},"author":{"name":"","@id":""},"headline":"Word Embedding","datePublished":"2022-10-16T11:58:31+00:00","dateModified":"2023-10-30T16:39:12+00:00","mainEntityOfPage":{"@id":"https:\/\/datascientest.com\/es\/word-embedding"},"wordCount":1069,"commentCount":0,"publisher":{"@id":"https:\/\/datascientest.com\/es\/#organization"},"articleSection":["Data Science"],"inLanguage":"es","potentialAction":[{"@type":"CommentAction","name":"Comment","target":["https:\/\/datascientest.com\/es\/word-embedding#respond"]}],"copyrightYear":"2022","copyrightHolder":{"@id":"https:\/\/datascientest.com\/#organization"}},{"@type":"WebPage","@id":"https:\/\/datascientest.com\/es\/word-embedding","url":"https:\/\/datascientest.com\/es\/word-embedding","name":"Word Embedding","isPartOf":{"@id":"https:\/\/datascientest.com\/es\/#website"},"datePublished":"2022-10-16T11:58:31+00:00","dateModified":"2023-10-30T16:39:12+00:00","description":"Descubra word embedding, uno de los principales m\u00e9todos utilizados para el NLP - Natural Language Processing. \u00a1Te lo explicamos!","inLanguage":"es","potentialAction":[{"@type":"ReadAction","target":["https:\/\/datascientest.com\/es\/word-embedding"]}]},{"@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":"","url":"https:\/\/datascientest.com\/es\/author"}]}},"_links":{"self":[{"href":"https:\/\/datascientest.com\/es\/wp-json\/wp\/v2\/posts\/166017"}],"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\/63"}],"replies":[{"embeddable":true,"href":"https:\/\/datascientest.com\/es\/wp-json\/wp\/v2\/comments?post=166017"}],"version-history":[{"count":0,"href":"https:\/\/datascientest.com\/es\/wp-json\/wp\/v2\/posts\/166017\/revisions"}],"wp:featuredmedia":[{"embeddable":true,"href":"https:\/\/datascientest.com\/es\/wp-json\/wp\/v2\/media\/166019"}],"wp:attachment":[{"href":"https:\/\/datascientest.com\/es\/wp-json\/wp\/v2\/media?parent=166017"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/datascientest.com\/es\/wp-json\/wp\/v2\/categories?post=166017"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/datascientest.com\/es\/wp-json\/wp\/v2\/tags?post=166017"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}