{"id":165131,"date":"2023-02-02T20:59:35","date_gmt":"2023-02-02T19:59:35","guid":{"rendered":"https:\/\/datascientest.com\/de\/?p=165131"},"modified":"2023-10-29T20:13:46","modified_gmt":"2023-10-29T19:13:46","slug":"word2vec","status":"publish","type":"post","link":"https:\/\/datascientest.com\/de\/word2vec","title":{"rendered":"Word2vec : NLP &amp; Word Embedding"},"content":{"rendered":"\t\t<div data-elementor-type=\"wp-post\" data-elementor-id=\"165131\" class=\"elementor elementor-165131\" data-elementor-post-type=\"post\">\n\t\t\t\t\t\t\t<div class=\"elementor-element elementor-element-9a7e7cd e-flex e-con-boxed e-con\" data-id=\"9a7e7cd\" 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-073b1b0 elementor-widget elementor-widget-menu-anchor\" data-id=\"073b1b0\" 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=\"1\" 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-d3bd837 elementor-widget elementor-widget-text-editor\" data-id=\"d3bd837\" 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><b>Word Embedding bezeichnet eine Reihe von Lernmethoden, die darauf abzielen, W\u00f6rter in einem Text durch Vektoren reeller Zahlen darzustellen.\u00a0 Heute pr\u00e4sentieren wir dir den dritten Teil unseres NLP-Dossiers.<\/b><\/h2><p><b>Hast du die ersten Episoden verpasst? Keine Sorge, hier sind sie:<\/b><\/p><ol><li>\u00a0 <a href=\"https:\/\/datascientest.com\/de\/nlp-natural-language-processing-eine-einfuhrung\">Einf\u00fchrung in NLP<\/a><\/li><li><span style=\"font-weight: 400;\"> \u00a0 <\/span><a href=\"#1\">Word embedding<b> &#8211;<\/b> Word2vec<\/a><ol><li>\u00a0 <a href=\"#2\">Definition von word embedding<\/a><\/li><li>\u00a0 <a href=\"#3\">Embedding mit Word2vec<\/a><\/li><li>\u00a0 <a href=\"#4\">Metrisch in diesem Raum<\/a><\/li><\/ol><\/li><li>\u00a0 <a href=\"https:\/\/datascientest.com\/de\/nlp-word-translation\">NLP &#8211; Wort\u00fcbersetzung<\/a><\/li><li>\u00a0 <a href=\"https:\/\/datascientest.com\/de\/nlp-twitter-stimmungsanalyse\">NLP Twitter &#8211; Gef\u00fchlsanalyse<\/a><\/li><\/ol><p><span style=\"font-weight: 400;\">Dieser Abschnitt soll die Funktionsweise erkl\u00e4ren und den ber\u00fchmten <\/span><b>Word2vec-Algorithmus in Python <\/b><span style=\"font-weight: 400;\">implementieren.<\/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-d089770 elementor-widget elementor-widget-menu-anchor\" data-id=\"d089770\" 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=\"2\" class=\"elementor-menu-anchor\"><\/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<div class=\"elementor-element elementor-element-c05fd3c e-flex e-con-boxed e-con\" data-id=\"c05fd3c\" 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-3b2d516 elementor-widget elementor-widget-heading\" data-id=\"3b2d516\" 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\">Word Embedding<\/h3>\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t\t\t<div class=\"elementor-element elementor-element-c3bce60 elementor-widget elementor-widget-text-editor\" data-id=\"c3bce60\" 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\">Zur Erinnerung: Word Embedding ist in der Lage, <\/span><b>den Kontext, die semantische und syntaktische \u00c4hnlichkeit (Genus, Synonyme, &#8230;) eines Wortes zu erfassen, indem es die Dimensionen verringert<\/b><span style=\"font-weight: 400\">.<\/span><\/p><p><span style=\"font-weight: 400\">Man k\u00f6nnte z. B. erwarten, dass die W\u00f6rter &#8222;bemerkenswert&#8220; und &#8222;bewundernswert&#8220; durch Vektoren dargestellt werden, die in dem Vektorraum, in dem diese Vektoren definiert sind, relativ wenig voneinander entfernt sind.<\/span><\/p><p><span style=\"font-weight: 400\">Die allgemein verwendete Einbettungsmethode, um die Gr\u00f6\u00dfe eines <\/span><b>Vektors zu reduzieren, besteht darin, das <\/b><span style=\"font-weight: 400\">Ergebnis zu verwenden, das eine dichte Schicht zur\u00fcckgibt, d. h. eine Einbettungsmatrix W mit der &#8222;one hot&#8220;-Darstellung des Wortes zu multiplizieren:<\/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-7a0fe53 elementor-widget elementor-widget-image\" data-id=\"7a0fe53\" 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=\"124\" src=\"https:\/\/datascientest.com\/de\/files\/2022\/11\/Capture-de\u0301cran-2020-09-18-a\u0300-09.23.47.webp\" class=\"attachment-full size-full wp-image-165134\" alt=\"\" \/>\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-ef14233 elementor-widget elementor-widget-text-editor\" data-id=\"ef14233\" 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\">In Vektorform : <\/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-53ea675 elementor-widget elementor-widget-image\" data-id=\"53ea675\" 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=\"41\" src=\"https:\/\/datascientest.com\/de\/files\/2022\/11\/Capture-de\u0301cran-2020-09-18-a\u0300-09.23.58.webp\" class=\"attachment-large size-large wp-image-165135\" alt=\"\" \/>\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-16276fd elementor-widget elementor-widget-image\" data-id=\"16276fd\" 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=\"448\" height=\"469\" src=\"https:\/\/datascientest.com\/de\/files\/2022\/11\/image5.png\" class=\"attachment-full size-full wp-image-165136\" alt=\"\" srcset=\"https:\/\/datascientest.com\/de\/files\/2022\/11\/image5.png 448w, https:\/\/datascientest.com\/de\/files\/2022\/11\/image5-287x300.png 287w\" sizes=\"(max-width: 448px) 100vw, 448px\" \/>\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\">Auto-Encoder<\/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-11cb3e4 elementor-widget elementor-widget-menu-anchor\" data-id=\"11cb3e4\" 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=\"3\" class=\"elementor-menu-anchor\"><\/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<div class=\"elementor-element elementor-element-62b17f4 e-flex e-con-boxed e-con\" data-id=\"62b17f4\" 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-89014cf elementor-widget elementor-widget-heading\" data-id=\"89014cf\" 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\">Embedding mit Word2vec<\/h3>\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t\t\t<div class=\"elementor-element elementor-element-5b29e3e elementor-widget elementor-widget-text-editor\" data-id=\"5b29e3e\" 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\">Um die Einschr\u00e4nkungen der ersten Methode zu vermeiden, ist es jedoch m\u00f6glich, die W-Matrix mithilfe des bekannten <\/span><b>Word2Vec-Algorithmus un\u00fcberwacht mit einfachem Text zu <\/b><span style=\"font-weight: 400\">trainieren.<\/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-fc98c10 e-flex e-con-boxed e-con\" data-id=\"fc98c10\" 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-6066285 elementor-widget elementor-widget-heading\" data-id=\"6066285\" 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\">Wie funktioniert Word2vec?<\/h3>\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t\t\t<div class=\"elementor-element elementor-element-686467e elementor-widget elementor-widget-text-editor\" data-id=\"686467e\" 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\">Es gibt zwei Varianten des Word2vec, beide verwenden ein neuronales Netz mit drei Schichten (1 Eingabeschicht, 1 verborgene Schicht, 1 Ausgabeschicht): Common Bag Of Words (CBOW) und Skip-gram.<\/span><\/p><p><span style=\"font-weight: 400\">In der folgenden Abbildung wird das <\/span><b>Wort im blauen Feld als Zielwort bezeichnet <\/b><span style=\"font-weight: 400\">und <\/span><b>die W\u00f6rter in den wei\u00dfen Feldern werden als Kontextw\u00f6rter <\/b><span style=\"font-weight: 400\">in <\/span><b>einem Fenster der Gr\u00f6\u00dfe 5 bezeichnet<\/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-9d509e1 elementor-widget elementor-widget-image\" data-id=\"9d509e1\" 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=\"945\" height=\"374\" src=\"https:\/\/datascientest.com\/de\/files\/2022\/11\/image3.png\" class=\"attachment-full size-full wp-image-165137\" alt=\"\" srcset=\"https:\/\/datascientest.com\/de\/files\/2022\/11\/image3.png 945w, https:\/\/datascientest.com\/de\/files\/2022\/11\/image3-300x119.png 300w, https:\/\/datascientest.com\/de\/files\/2022\/11\/image3-768x304.png 768w\" sizes=\"(max-width: 945px) 100vw, 945px\" \/>\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-33f28ec elementor-widget elementor-widget-text-editor\" data-id=\"33f28ec\" 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: Das Modell wird mit dem Kontext gef\u00fcttert <\/b><span style=\"font-weight: 400\">und sagt das Zielwort voraus. Das Ergebnis der verborgenen Schicht ist die neue Repr\u00e4sentation des Wortes <\/span><span style=\"font-weight: 400\">(\u210e1<\/span><span style=\"font-weight: 400\">, &#8230;, \u210e\ud835\udc41).<\/span><\/p><p><b>Skip Gram: Das Modell wird mit dem Zielwort gef\u00fcttert <\/b><span style=\"font-weight: 400\">und sagt die W\u00f6rter im Kontext voraus. Das Ergebnis der verborgenen Schicht ist die neue Darstellung des Wortes <\/span><span style=\"font-weight: 400\">(\u210e1<\/span><span style=\"font-weight: 400\">, &#8230;, \u210e\ud835\udc41).<\/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-7875cbe elementor-widget elementor-widget-image\" data-id=\"7875cbe\" 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=\"945\" height=\"568\" src=\"https:\/\/datascientest.com\/de\/files\/2022\/11\/image2.png\" class=\"attachment-full size-full wp-image-165141\" alt=\"\" srcset=\"https:\/\/datascientest.com\/de\/files\/2022\/11\/image2.png 945w, https:\/\/datascientest.com\/de\/files\/2022\/11\/image2-300x180.png 300w, https:\/\/datascientest.com\/de\/files\/2022\/11\/image2-768x462.png 768w\" sizes=\"(max-width: 945px) 100vw, 945px\" \/>\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-c5ba3a2 e-flex e-con-boxed e-con\" data-id=\"c5ba3a2\" 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-60cefcf elementor-widget elementor-widget-heading\" data-id=\"60cefcf\" 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\">Formatierung der Daten:<\/h3>\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t\t\t<div class=\"elementor-element elementor-element-8269e3f elementor-widget elementor-widget-text-editor\" data-id=\"8269e3f\" 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\">Hier werden wir <\/span><b>das CBOW-Modell vorstellen, <\/b><span style=\"font-weight: 400\">d. h. der <\/span><b>Kontext ist der Input <\/b><span style=\"font-weight: 400\">unseres Modells und das <\/span><b>Zielwort (blaues Wort) ist der Output<\/b><span style=\"font-weight: 400\">. Wir definieren ein Fenster mit der L\u00e4nge 5 f\u00fcr den Kontext (Eingabe).<\/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-54ff3e5 elementor-widget elementor-widget-image\" data-id=\"54ff3e5\" 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=\"945\" height=\"374\" src=\"https:\/\/datascientest.com\/de\/files\/2022\/11\/image9.png\" class=\"attachment-full size-full wp-image-165142\" alt=\"\" srcset=\"https:\/\/datascientest.com\/de\/files\/2022\/11\/image9.png 945w, https:\/\/datascientest.com\/de\/files\/2022\/11\/image9-300x119.png 300w, https:\/\/datascientest.com\/de\/files\/2022\/11\/image9-768x304.png 768w\" sizes=\"(max-width: 945px) 100vw, 945px\" \/>\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-68e0802 elementor-widget elementor-widget-image\" data-id=\"68e0802\" 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=\"945\" height=\"249\" src=\"https:\/\/datascientest.com\/de\/files\/2022\/11\/image1.png\" class=\"attachment-full size-full wp-image-165143\" alt=\"\" srcset=\"https:\/\/datascientest.com\/de\/files\/2022\/11\/image1.png 945w, https:\/\/datascientest.com\/de\/files\/2022\/11\/image1-300x79.png 300w, https:\/\/datascientest.com\/de\/files\/2022\/11\/image1-768x202.png 768w\" sizes=\"(max-width: 945px) 100vw, 945px\" \/>\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-7e5bd33 e-flex e-con-boxed e-con\" data-id=\"7e5bd33\" 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-4d31356 elementor-widget elementor-widget-heading\" data-id=\"4d31356\" 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\">Modell:<\/h3>\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t\t\t<div class=\"elementor-element elementor-element-332ab75 elementor-widget elementor-widget-text-editor\" data-id=\"332ab75\" 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\">Das CBOW-Modell hat \u00c4hnlichkeiten mit dem Klassifikationsmodell, das wir gerade im vorherigen Abschnitt implementiert haben. Unser Modell wird aus den folgenden Schichten bestehen:<\/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-f8d4f0e elementor-widget elementor-widget-image\" data-id=\"f8d4f0e\" 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=\"945\" height=\"880\" src=\"https:\/\/datascientest.com\/de\/files\/2022\/11\/image7.png\" class=\"attachment-full size-full wp-image-165144\" alt=\"\" srcset=\"https:\/\/datascientest.com\/de\/files\/2022\/11\/image7.png 945w, https:\/\/datascientest.com\/de\/files\/2022\/11\/image7-300x279.png 300w, https:\/\/datascientest.com\/de\/files\/2022\/11\/image7-768x715.png 768w\" sizes=\"(max-width: 945px) 100vw, 945px\" \/>\t\t\t\t\t\t\t\t\t\t\t<figcaption class=\"widget-image-caption wp-caption-text\">CBOW-Architektur<\/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-7ae5543 elementor-widget elementor-widget-text-editor\" data-id=\"7ae5543\" 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 style=\"font-weight: 400\"><span style=\"font-weight: 400\">Die Embedding-Schicht wird <\/span><b>jedes Wort im Kontext in einen Embedding-Vektor umwandeln<\/b><span style=\"font-weight: 400\">. Die W-Matrix des Embeddings wird im Laufe des Workouts des Modells erlernt. Die resultierenden Dimensionen sind: (lot, context_size, embedding).<\/span><\/li><li style=\"font-weight: 400\"><span style=\"font-weight: 400\">Anschlie\u00dfend k\u00f6nnen mit der GlobalAveragePooling1D-Schicht <\/span><b>die verschiedenen Einbettungen summiert werden, <\/b><span style=\"font-weight: 400\">um eine Ausgabegr\u00f6\u00dfe zu erhalten (batch_size, embedding).<\/span><\/li><li style=\"font-weight: 400\">Schlie\u00dflich kann der Dense-Layer mit der Gr\u00f6\u00dfe &#8222;voc_size&#8220; <b>das Zielwort vorhersagen<\/b><span>.<\/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-ba1f837 elementor-widget elementor-widget-shortcode\" data-id=\"ba1f837\" 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-b1fb452 elementor-widget elementor-widget-text-editor\" data-id=\"b1fb452\" 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\">Die Cross-Entropy-Loss-Funktion wird in der Regel zum Workout des Modells :<\/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-4554403 elementor-widget elementor-widget-shortcode\" data-id=\"4554403\" 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-53895f1 elementor-widget elementor-widget-menu-anchor\" data-id=\"53895f1\" 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=\"4\" class=\"elementor-menu-anchor\"><\/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<div class=\"elementor-element elementor-element-70d5cce e-flex e-con-boxed e-con\" data-id=\"70d5cce\" 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-9b13f07 elementor-widget elementor-widget-heading\" data-id=\"9b13f07\" 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\">Metrisch in diesem Raum:<\/h3>\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t\t\t<div class=\"elementor-element elementor-element-708620e elementor-widget elementor-widget-text-editor\" data-id=\"708620e\" 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\">Da das Modell nun trainiert ist, kann es interessant sein, den Abstand zwischen den W\u00f6rtern zu vergleichen.<\/span><\/p><p><b>Die &#8222;Cosine similarity&#8220; wird im Allgemeinen als <\/b><span style=\"font-weight: 400\">Metrik zur Messung der Entfernung verwendet, wenn die <\/span><b>Norm der Vektoren keine Rolle spielt.<\/b><span style=\"font-weight: 400\"> Diese Metrik erfasst die \u00c4hnlichkeit zwischen zwei W\u00f6rtern.<\/span><\/p><p><span style=\"font-weight: 400\">Je n\u00e4her die &#8222;cosine similarity&#8220; an 1 liegt, desto mehr <\/span><b>sind die beiden W\u00f6rter miteinander verwandt.<\/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-748a0e8 elementor-widget elementor-widget-image\" data-id=\"748a0e8\" 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=\"308\" src=\"https:\/\/datascientest.com\/de\/files\/2022\/11\/image4.png\" class=\"attachment-full size-full wp-image-165151\" alt=\"\" srcset=\"https:\/\/datascientest.com\/de\/files\/2022\/11\/image4.png 800w, https:\/\/datascientest.com\/de\/files\/2022\/11\/image4-300x116.png 300w, https:\/\/datascientest.com\/de\/files\/2022\/11\/image4-768x296.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-822a4e6 elementor-widget elementor-widget-text-editor\" data-id=\"822a4e6\" 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\">Mit dieser Metrik und in diesem Untervektorraum sind die 5 W\u00f6rter, die <\/span><b>am n\u00e4chsten an &#8222;body&#8220; liegen, :<\/b><\/p><pre><span style=\"font-weight: 400\">intestines - 0.30548161268234253<\/span><br \/><span style=\"font-weight: 400\">bodies - 0.2691531181335449<\/span><br \/><span style=\"font-weight: 400\">arm - 0.24878980219364166<\/span><br \/><span style=\"font-weight: 400\">chest - 0.2261650413274765<\/span><br \/><span style=\"font-weight: 400\">leg - 0.2193179428577423<\/span><\/pre><p><span style=\"font-weight: 400\">Die obigen Zahlen stellen die Cos-similar-Distanzen zwischen dem Wort &#8222;body&#8220; und den n\u00e4chstliegenden W\u00f6rtern dar.<\/span><\/p><p><span style=\"font-weight: 400\">Zum Wort &#8222;<\/span><b>Zombie<\/b><span style=\"font-weight: 400\">&#8222;:<\/span><\/p><pre><span style=\"font-weight: 400\">Slasher - 0.3172745406627655<\/span><br \/><span style=\"font-weight: 400\">cannibal - 0.28496912121772766<\/span><br \/><span style=\"font-weight: 400\">zombies - 0.2767203450202942<\/span><br \/><span style=\"font-weight: 400\">horror - 0.2607246935367584<\/span><br \/><span style=\"font-weight: 400\">zombi - 0.25878411531448364<\/span><\/pre><p><span style=\"font-weight: 400\">Zum Wort &#8222;<\/span><b>amazing<\/b><span style=\"font-weight: 400\">&#8222;:<\/span><\/p><pre><span style=\"font-weight: 400\">gl\u00e4nzend - 0.3372475802898407<\/span><br \/><span style=\"font-weight: 400\">extraordinary - 0.319326251745224<\/span><br \/><span style=\"font-weight: 400\">great - 0.29579296708106995<\/span><br \/><span style=\"font-weight: 400\">breathtaking - 0.2907085716724396<\/span><br \/><span style=\"font-weight: 400\">fantastic - 0.2871546149253845<\/span><\/pre><p><span style=\"font-weight: 400\">Zum Wort &#8222;<\/span><b>god<\/b><span style=\"font-weight: 400\">&#8222;:<\/span><\/p><pre><span style=\"font-weight: 400\">heavens - 0.268303781747818<\/span><br \/><span style=\"font-weight: 400\">jesus - 0.26807624101638794<\/span><br \/><span style=\"font-weight: 400\">goodness - 0.2618488669395447<\/span><br \/><span style=\"font-weight: 400\">gods - 0.24795521795749664<\/span><br \/><span style=\"font-weight: 400\">doom - 0.22242328524589539<\/span><\/pre>\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-e5af266 e-flex e-con-boxed e-con\" data-id=\"e5af266\" 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-25be77b elementor-widget elementor-widget-heading\" data-id=\"25be77b\" 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\">Arithmetische Eigenschaften:<\/h3>\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t\t\t<div class=\"elementor-element elementor-element-93e1914 elementor-widget elementor-widget-text-editor\" data-id=\"93e1914\" 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\">Wir k\u00f6nnen uns nun die Frage stellen, ob unser Untervektorraum der W\u00f6rter arithmetische Eigenschaften hat. Nehmen wir das folgende ber\u00fchmte Beispiel:<\/span><\/p><p style=\"text-align: center\"><span style=\"font-weight: 400\">\ud835\udc3e\ud835\udc56\ud835\udc5b\ud835\udc54 <\/span><span style=\"font-weight: 400\">&#8211; \ud835\udc40\ud835\udc4e\ud835\udc5b <\/span><span style=\"font-weight: 400\">+ <\/span><span style=\"font-weight: 400\">\ud835\udc4a\ud835\udc5c\ud835\udc5a\ud835\udc4e\ud835\udc5b <\/span><span style=\"font-weight: 400\">= <\/span><span style=\"font-weight: 400\">\ud835\udc44\ud835\udc62\ud835\udc52\ud835\udc52\ud835\udc5b<\/span><\/p><p><span style=\"font-weight: 400\">In diesem Beispiel <\/span><b>ist <\/b><span style=\"font-weight: 400\">die <\/span><b>arithmetische Eigenschaft das K\u00f6nigtum<\/b><span style=\"font-weight: 400\">. Wir m\u00f6chten \u00fcberpr\u00fcfen, ob sich diese Eigenschaft auf &#8222;woman&#8220; ausbreiten wird. Das hei\u00dft, wir werden nach den W\u00f6rtern suchen, die dem folgenden Vektor am n\u00e4chsten liegen:<\/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\">Hier ist das Wort &#8222;queen&#8220; in unserem Datensatz nicht sehr stark vertreten, was eine schlechte Darstellung erkl\u00e4rt. Aus diesem Grund werden wir uns stattdessen mit <\/span><b>der Zahleneigenschaft <\/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\">&#8211; \ud835\udc40\ud835\udc4e\ud835\udc5b + \ud835\udc4a\ud835\udc5c\ud835\udc5a\ud835\udc4e\ud835\udc5b <em>=<\/em> <em>Women<\/em><\/span><\/p><p><span style=\"font-weight: 400\">Unter Verwendung der oben definierten Operation und einer Metrik f\u00fcr die Kos\u00e4hnlichkeit sind die <\/span><b>f\u00fcnf \u00e4hnlichsten W\u00f6rter :<\/b><\/p><pre><span style=\"font-weight: 400\">women - 0.2889893054962158<\/span>\n<span style=\"font-weight: 400\">weiblich - 0.272260844707489<\/span>\n<span style=\"font-weight: 400\">strangers - 0.24558939039707184<\/span>\n<span style=\"font-weight: 400\">teens - 0.2443128377199173<\/span>\n<span style=\"font-weight: 400\">daughters - 0.24117740988731384<\/span><\/pre><p><span style=\"font-weight: 400\">Das Ergebnis f\u00fcr Zombies &#8211; Zombie + \ud835\udc4a\ud835\udc5c\ud835\udc5a\ud835\udc4e\ud835\udc5b :<\/span><\/p><pre><span style=\"font-weight: 400\">women - 0.2547883093357086<\/span>\n<span style=\"font-weight: 400\">weiblich - 0.23258551955223083<\/span>\n<span style=\"font-weight: 400\">ladies - 0.22764989733695984<\/span>\n<span style=\"font-weight: 400\">stripper - 0.22274985909461975<\/span>\n<span style=\"font-weight: 400\">develops - 0.2202150821685791<\/span><\/pre><p><span style=\"font-weight: 400\">Das Ergebnis f\u00fcr Men &#8211; Man + Soldier :<\/span><\/p><pre><span style=\"font-weight: 400\">soldiers - 0.3547001779079437<\/span>\n<span style=\"font-weight: 400\">daughters - 0.21896378695964813<\/span>\n<span style=\"font-weight: 400\">letters - 0.21452251076698303<\/span>\n<span style=\"font-weight: 400\">backyard - 0.21437858045101166<\/span>\n<span style=\"font-weight: 400\">veterans - 0.21067838370800018<\/span><\/pre><p><span style=\"font-weight: 400\">Das Ergebnis f\u00fcr Zombies &#8211; Zombie + Monster :<\/span><\/p><pre><span style=\"font-weight: 400\">werewolves - 0.2724993824958801<\/span><br \/><span style=\"font-weight: 400\">monsters - 0.25695472955703735<\/span><br \/><span style=\"font-weight: 400\">creature - 0.24453674256801605<\/span><br \/><span style=\"font-weight: 400\">Drachen - 0.22363890707492828<\/span><br \/><span style=\"font-weight: 400\">bloke - 0.21858260035514832<\/span><\/pre><p><span style=\"font-weight: 400\">Hier scheinen die W\u00f6rter &#8222;monsters&#8220; und &#8222;werewolves&#8220; im Zusammenhang mit unserem Datensatz sehr \u00e4hnlich zu sein.<\/span><\/p><p><span style=\"font-weight: 400\">Mithilfe einer PCA k\u00f6nnen wir die Dimension der <\/span><b>Zahleneigenschaft :<\/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-8d1529f elementor-widget elementor-widget-image\" data-id=\"8d1529f\" 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\/de\/files\/2022\/11\/image_word2vec.webp\" class=\"attachment-full size-full wp-image-165161\" alt=\"\" srcset=\"https:\/\/datascientest.com\/de\/files\/2022\/11\/image_word2vec.webp 717w, https:\/\/datascientest.com\/de\/files\/2022\/11\/image_word2vec-300x286.webp 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-c5df84d elementor-widget elementor-widget-text-editor\" data-id=\"c5df84d\" 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\">Mit der gleichen Argumentation wird das <\/span><b>Geschlecht erfasst:<\/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-3fb4dac elementor-widget elementor-widget-image\" data-id=\"3fb4dac\" 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\/de\/files\/2022\/11\/word2vec_3.webp\" class=\"attachment-full size-full wp-image-165162\" alt=\"\" srcset=\"https:\/\/datascientest.com\/de\/files\/2022\/11\/word2vec_3.webp 512w, https:\/\/datascientest.com\/de\/files\/2022\/11\/word2vec_3-300x286.webp 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-ec3fb4e elementor-widget elementor-widget-text-editor\" data-id=\"ec3fb4e\" 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\">Mit der gleichen Argumentation zwischen Verben im <\/span><b>Infinitiv und Verben, die auf -ed enden:<\/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-c891ac5 elementor-widget elementor-widget-image\" data-id=\"c891ac5\" 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\/de\/files\/2022\/11\/word2vec_2.webp\" class=\"attachment-full size-full wp-image-165163\" alt=\"\" srcset=\"https:\/\/datascientest.com\/de\/files\/2022\/11\/word2vec_2.webp 512w, https:\/\/datascientest.com\/de\/files\/2022\/11\/word2vec_2-300x287.webp 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-7b244e9 elementor-widget elementor-widget-text-editor\" data-id=\"7b244e9\" 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\">Das <\/span><b>&#8222;word2vec embedding&#8220; erfasst effektiv die semantischen und arithmetischen Eigenschaften eines Wortes<\/b><span style=\"font-weight: 400\">. Es <\/span><b>reduziert <\/b><span style=\"font-weight: 400\">au\u00dferdem <\/span><b>die Dimension des Problems und damit die Lernaufgabe<\/b><span style=\"font-weight: 400\">.<\/span><\/p><p><span style=\"font-weight: 400\">Wir k\u00f6nnen uns vorstellen, den word2vec-Algorithmus zu verwenden, um die <\/span><b>Einbettungsmatrix des Klassifikationsmodells vorab zu trainieren.<\/b><span style=\"font-weight: 400\"> Infolgedessen wird unser Klassifikationsmodell w\u00e4hrend der Lernphase der Gef\u00fchle eine viel bessere Darstellung der W\u00f6rter haben.<\/span><\/p><p><b>Hast du Lust, eine <\/b><span style=\"font-weight: 400\">ausf\u00fchrlichere <\/span><b>Schulung <\/b><span style=\"font-weight: 400\">zu den verschiedenen Aspekten, die in diesem Artikel behandelt werden, zu <\/span><b>beginnen?<\/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-f0455cd elementor-align-center button-principal elementor-widget elementor-widget-button\" data-id=\"f0455cd\" 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-md\" href=\"https:\/\/datascientest.com\/de\/unsere-aus-und-weiterbildungen\">\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\">Entdecke alle unsere Module!<\/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>Word Embedding bezeichnet eine Reihe von Lernmethoden, die darauf abzielen, W\u00f6rter in einem Text durch Vektoren reeller Zahlen darzustellen.&nbsp; Heute pr\u00e4sentieren wir dir den dritten Teil unseres NLP-Dossiers. Hast du die ersten Episoden verpasst? Keine Sorge, hier sind sie: &nbsp; Einf\u00fchrung in NLP &nbsp; Word embedding &#8211; Word2vec &nbsp; Definition von word embedding &nbsp; Embedding [&hellip;]<\/p>\n","protected":false},"author":47,"featured_media":165133,"comment_status":"open","ping_status":"open","sticky":false,"template":"elementor_theme","format":"standard","meta":{"content-type":"","inline_featured_image":false},"categories":[2454],"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 &amp; Word Embedding<\/title>\n<meta name=\"description\" content=\"Word Embedding bezeichnet eine Reihe von Lernmethoden, die darauf abzielen, W\u00f6rter in einem Text durch Vektoren reeller Zahlen darzustellen. Heute pr\u00e4sentieren wir dir den dritten Teil unseres NLP-Dossiers.\" \/>\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\/de\/word2vec\" \/>\n<meta property=\"og:locale\" content=\"de_DE\" \/>\n<meta property=\"og:type\" content=\"article\" \/>\n<meta property=\"og:title\" content=\"Word2vec : NLP &amp; Word Embedding\" \/>\n<meta property=\"og:description\" content=\"Word Embedding bezeichnet eine Reihe von Lernmethoden, die darauf abzielen, W\u00f6rter in einem Text durch Vektoren reeller Zahlen darzustellen.&nbsp; Heute\" \/>\n<meta property=\"og:url\" content=\"https:\/\/datascientest.com\/de\/word2vec\" \/>\n<meta property=\"og:site_name\" content=\"Weiterbildung Data Science | DataScientest.com\" \/>\n<meta property=\"article:publisher\" content=\"https:\/\/www.facebook.com\/DataScientestEN\" \/>\n<meta property=\"article:published_time\" content=\"2023-02-02T19:59:35+00:00\" \/>\n<meta property=\"article:modified_time\" content=\"2023-10-29T19:13:46+00:00\" \/>\n<meta property=\"og:image\" content=\"https:\/\/datascientest.com\/de\/wp-content\/blogs.dir\/8\/files\/2022\/11\/word2vec.webp\" \/>\n\t<meta property=\"og:image:width\" content=\"768\" \/>\n\t<meta property=\"og:image:height\" content=\"303\" \/>\n\t<meta property=\"og:image:type\" content=\"image\/webp\" \/>\n<meta name=\"author\" content=\"Adriano R\" \/>\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=\"Verfasst von\" \/>\n\t<meta name=\"twitter:data1\" content=\"Adriano R\" \/>\n\t<meta name=\"twitter:label2\" content=\"Gesch\u00e4tzte Lesezeit\" \/>\n\t<meta name=\"twitter:data2\" content=\"7 Minuten\" \/>\n<script type=\"application\/ld+json\" class=\"yoast-schema-graph\">{\"@context\":\"https:\/\/schema.org\",\"@graph\":[{\"@type\":\"Article\",\"@id\":\"https:\/\/datascientest.com\/de\/word2vec#article\",\"isPartOf\":{\"@id\":\"https:\/\/datascientest.com\/de\/word2vec\"},\"author\":{\"name\":\"Adriano R\",\"@id\":\"https:\/\/datascientest.com\/de\/#\/schema\/person\/3d2560836c47019eb12b7b77f3a15378\"},\"headline\":\"Word2vec : NLP &amp; Word Embedding\",\"datePublished\":\"2023-02-02T19:59:35+00:00\",\"dateModified\":\"2023-10-29T19:13:46+00:00\",\"mainEntityOfPage\":{\"@id\":\"https:\/\/datascientest.com\/de\/word2vec\"},\"wordCount\":898,\"commentCount\":0,\"publisher\":{\"@id\":\"https:\/\/datascientest.com\/de\/#organization\"},\"articleSection\":[\"Data Science\"],\"inLanguage\":\"de\",\"potentialAction\":[{\"@type\":\"CommentAction\",\"name\":\"Comment\",\"target\":[\"https:\/\/datascientest.com\/de\/word2vec#respond\"]}],\"copyrightYear\":\"2023\",\"copyrightHolder\":{\"@id\":\"https:\/\/datascientest.com\/#organization\"}},{\"@type\":\"WebPage\",\"@id\":\"https:\/\/datascientest.com\/de\/word2vec\",\"url\":\"https:\/\/datascientest.com\/de\/word2vec\",\"name\":\"Word2vec : NLP &amp; Word Embedding\",\"isPartOf\":{\"@id\":\"https:\/\/datascientest.com\/de\/#website\"},\"datePublished\":\"2023-02-02T19:59:35+00:00\",\"dateModified\":\"2023-10-29T19:13:46+00:00\",\"description\":\"Word Embedding bezeichnet eine Reihe von Lernmethoden, die darauf abzielen, W\u00f6rter in einem Text durch Vektoren reeller Zahlen darzustellen. Heute pr\u00e4sentieren wir dir den dritten Teil unseres NLP-Dossiers.\",\"inLanguage\":\"de\",\"potentialAction\":[{\"@type\":\"ReadAction\",\"target\":[\"https:\/\/datascientest.com\/de\/word2vec\"]}]},{\"@type\":\"WebSite\",\"@id\":\"https:\/\/datascientest.com\/de\/#website\",\"url\":\"https:\/\/datascientest.com\/de\/\",\"name\":\"Weiterbildung Data Science | DataScientest.com\",\"description\":\"F\u00fchrender Anbieter von Schulungen im Bereich Data Science\",\"publisher\":{\"@id\":\"https:\/\/datascientest.com\/de\/#organization\"},\"potentialAction\":[{\"@type\":\"SearchAction\",\"target\":{\"@type\":\"EntryPoint\",\"urlTemplate\":\"https:\/\/datascientest.com\/de\/?s={search_term_string}\"},\"query-input\":\"required name=search_term_string\"}],\"inLanguage\":\"de\"},{\"@type\":\"Organization\",\"@id\":\"https:\/\/datascientest.com\/de\/#organization\",\"name\":\"DataScientest\",\"url\":\"https:\/\/datascientest.com\/de\/\",\"logo\":{\"@type\":\"ImageObject\",\"inLanguage\":\"de\",\"@id\":\"https:\/\/datascientest.com\/de\/#\/schema\/logo\/image\/\",\"url\":\"https:\/\/datascientest.com\/de\/wp-content\/blogs.dir\/8\/files\/2024\/02\/DataScientest_icon_blue-2.png\",\"contentUrl\":\"https:\/\/datascientest.com\/de\/wp-content\/blogs.dir\/8\/files\/2024\/02\/DataScientest_icon_blue-2.png\",\"width\":301,\"height\":301,\"caption\":\"DataScientest\"},\"image\":{\"@id\":\"https:\/\/datascientest.com\/de\/#\/schema\/logo\/image\/\"},\"sameAs\":[\"https:\/\/www.facebook.com\/DataScientestEN\",\"https:\/\/twitter.com\/DataScientest__\",\"https:\/\/www.linkedin.com\/company\/datascientest-germany\/\",\"https:\/\/www.tiktok.com\/@datascientest\"]},{\"@type\":\"Person\",\"@id\":\"https:\/\/datascientest.com\/de\/#\/schema\/person\/3d2560836c47019eb12b7b77f3a15378\",\"name\":\"Adriano R\",\"image\":{\"@type\":\"ImageObject\",\"inLanguage\":\"de\",\"@id\":\"https:\/\/datascientest.com\/de\/#\/schema\/person\/image\/\",\"url\":\"https:\/\/secure.gravatar.com\/avatar\/fbfbc3a7811c63caf3333396a123058f?s=96&d=mm&r=g\",\"contentUrl\":\"https:\/\/secure.gravatar.com\/avatar\/fbfbc3a7811c63caf3333396a123058f?s=96&d=mm&r=g\",\"caption\":\"Adriano R\"},\"sameAs\":[\"user\"],\"url\":\"https:\/\/datascientest.com\/de\/author\/adriano-r\"}]}<\/script>\n<!-- \/ Yoast SEO Premium plugin. -->","yoast_head_json":{"title":"Word2vec : NLP &amp; Word Embedding","description":"Word Embedding bezeichnet eine Reihe von Lernmethoden, die darauf abzielen, W\u00f6rter in einem Text durch Vektoren reeller Zahlen darzustellen. Heute pr\u00e4sentieren wir dir den dritten Teil unseres NLP-Dossiers.","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\/de\/word2vec","og_locale":"de_DE","og_type":"article","og_title":"Word2vec : NLP &amp; Word Embedding","og_description":"Word Embedding bezeichnet eine Reihe von Lernmethoden, die darauf abzielen, W\u00f6rter in einem Text durch Vektoren reeller Zahlen darzustellen.&nbsp; Heute","og_url":"https:\/\/datascientest.com\/de\/word2vec","og_site_name":"Weiterbildung Data Science | DataScientest.com","article_publisher":"https:\/\/www.facebook.com\/DataScientestEN","article_published_time":"2023-02-02T19:59:35+00:00","article_modified_time":"2023-10-29T19:13:46+00:00","og_image":[{"width":768,"height":303,"url":"https:\/\/datascientest.com\/de\/wp-content\/blogs.dir\/8\/files\/2022\/11\/word2vec.webp","type":"image\/webp"}],"author":"Adriano R","twitter_card":"summary_large_image","twitter_creator":"@DataScientest__","twitter_site":"@DataScientest__","twitter_misc":{"Verfasst von":"Adriano R","Gesch\u00e4tzte Lesezeit":"7 Minuten"},"schema":{"@context":"https:\/\/schema.org","@graph":[{"@type":"Article","@id":"https:\/\/datascientest.com\/de\/word2vec#article","isPartOf":{"@id":"https:\/\/datascientest.com\/de\/word2vec"},"author":{"name":"Adriano R","@id":"https:\/\/datascientest.com\/de\/#\/schema\/person\/3d2560836c47019eb12b7b77f3a15378"},"headline":"Word2vec : NLP &amp; Word Embedding","datePublished":"2023-02-02T19:59:35+00:00","dateModified":"2023-10-29T19:13:46+00:00","mainEntityOfPage":{"@id":"https:\/\/datascientest.com\/de\/word2vec"},"wordCount":898,"commentCount":0,"publisher":{"@id":"https:\/\/datascientest.com\/de\/#organization"},"articleSection":["Data Science"],"inLanguage":"de","potentialAction":[{"@type":"CommentAction","name":"Comment","target":["https:\/\/datascientest.com\/de\/word2vec#respond"]}],"copyrightYear":"2023","copyrightHolder":{"@id":"https:\/\/datascientest.com\/#organization"}},{"@type":"WebPage","@id":"https:\/\/datascientest.com\/de\/word2vec","url":"https:\/\/datascientest.com\/de\/word2vec","name":"Word2vec : NLP &amp; Word Embedding","isPartOf":{"@id":"https:\/\/datascientest.com\/de\/#website"},"datePublished":"2023-02-02T19:59:35+00:00","dateModified":"2023-10-29T19:13:46+00:00","description":"Word Embedding bezeichnet eine Reihe von Lernmethoden, die darauf abzielen, W\u00f6rter in einem Text durch Vektoren reeller Zahlen darzustellen. Heute pr\u00e4sentieren wir dir den dritten Teil unseres NLP-Dossiers.","inLanguage":"de","potentialAction":[{"@type":"ReadAction","target":["https:\/\/datascientest.com\/de\/word2vec"]}]},{"@type":"WebSite","@id":"https:\/\/datascientest.com\/de\/#website","url":"https:\/\/datascientest.com\/de\/","name":"Weiterbildung Data Science | DataScientest.com","description":"F\u00fchrender Anbieter von Schulungen im Bereich Data Science","publisher":{"@id":"https:\/\/datascientest.com\/de\/#organization"},"potentialAction":[{"@type":"SearchAction","target":{"@type":"EntryPoint","urlTemplate":"https:\/\/datascientest.com\/de\/?s={search_term_string}"},"query-input":"required name=search_term_string"}],"inLanguage":"de"},{"@type":"Organization","@id":"https:\/\/datascientest.com\/de\/#organization","name":"DataScientest","url":"https:\/\/datascientest.com\/de\/","logo":{"@type":"ImageObject","inLanguage":"de","@id":"https:\/\/datascientest.com\/de\/#\/schema\/logo\/image\/","url":"https:\/\/datascientest.com\/de\/wp-content\/blogs.dir\/8\/files\/2024\/02\/DataScientest_icon_blue-2.png","contentUrl":"https:\/\/datascientest.com\/de\/wp-content\/blogs.dir\/8\/files\/2024\/02\/DataScientest_icon_blue-2.png","width":301,"height":301,"caption":"DataScientest"},"image":{"@id":"https:\/\/datascientest.com\/de\/#\/schema\/logo\/image\/"},"sameAs":["https:\/\/www.facebook.com\/DataScientestEN","https:\/\/twitter.com\/DataScientest__","https:\/\/www.linkedin.com\/company\/datascientest-germany\/","https:\/\/www.tiktok.com\/@datascientest"]},{"@type":"Person","@id":"https:\/\/datascientest.com\/de\/#\/schema\/person\/3d2560836c47019eb12b7b77f3a15378","name":"Adriano R","image":{"@type":"ImageObject","inLanguage":"de","@id":"https:\/\/datascientest.com\/de\/#\/schema\/person\/image\/","url":"https:\/\/secure.gravatar.com\/avatar\/fbfbc3a7811c63caf3333396a123058f?s=96&d=mm&r=g","contentUrl":"https:\/\/secure.gravatar.com\/avatar\/fbfbc3a7811c63caf3333396a123058f?s=96&d=mm&r=g","caption":"Adriano R"},"sameAs":["user"],"url":"https:\/\/datascientest.com\/de\/author\/adriano-r"}]}},"_links":{"self":[{"href":"https:\/\/datascientest.com\/de\/wp-json\/wp\/v2\/posts\/165131"}],"collection":[{"href":"https:\/\/datascientest.com\/de\/wp-json\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/datascientest.com\/de\/wp-json\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/datascientest.com\/de\/wp-json\/wp\/v2\/users\/47"}],"replies":[{"embeddable":true,"href":"https:\/\/datascientest.com\/de\/wp-json\/wp\/v2\/comments?post=165131"}],"version-history":[{"count":0,"href":"https:\/\/datascientest.com\/de\/wp-json\/wp\/v2\/posts\/165131\/revisions"}],"wp:featuredmedia":[{"embeddable":true,"href":"https:\/\/datascientest.com\/de\/wp-json\/wp\/v2\/media\/165133"}],"wp:attachment":[{"href":"https:\/\/datascientest.com\/de\/wp-json\/wp\/v2\/media?parent=165131"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/datascientest.com\/de\/wp-json\/wp\/v2\/categories?post=165131"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/datascientest.com\/de\/wp-json\/wp\/v2\/tags?post=165131"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}