<style>/*
<link href='//cdnjs.cloudflare.com/ajax/libs/highlight.js/9.15.6/styles/atom-one-dark-reasonable.min.css' rel='stylesheet'/>
<script src='//cdnjs.cloudflare.com/ajax/libs/highlight.js/9.15.6/highlight.min.js'></script>
<script src='//cdnjs.cloudflare.com/ajax/libs/highlight.js/9.15.6/languages/r.min.js'></script>
<script>hljs.initHighlightingOnLoad();</script>
<link href='https://www.blogger.com/dyn-css/authorization.css?targetBlogID=1030619672955979982&zx=01c18356-1b06-40a4-a97d-96d5c6c16a6d' media='none' onload='if(media!='all')media='all'' rel='stylesheet'/><noscript><link href='https://www.blogger.com/dyn-css/authorization.css?targetBlogID=1030619672955979982&zx=01c18356-1b06-40a4-a97d-96d5c6c16a6d' rel='stylesheet'/></noscript>
<meta name='google-adsense-platform-account' content='ca-host-pub-1556223355139109'/>
<meta name='google-adsense-platform-domain' content='blogspot.com'/>

<!-- data-ad-client=ca-pub-6226434833206940 -->

</head><body>*/</style>

Day 8 - Developing a Neural Machine Translation System from Scratch Part 2

Avnish Yadav

4 Sept, 2018

Hello guys,

This is day 8 of my #100DayOfMLCode challenge. Today, I am uploading 2nd part of developing a Neural Machine Translation System from German to English and English to German.

Cleaning the Text

Splitting the Text

I will provide step by step explanation on completing my project.
Thanks.

project

Add Comment

<style>/*
<script type="text/javascript" src="https://www.blogger.com/static/v1/widgets/745881458-widgets.js"></script>
<script type='text/javascript'>
window['__wavt'] = 'AOuZoY6N3r0nrz3FOb0UB1ufGKIoyHQiqQ:1734791831030';_WidgetManager._Init('//www.blogger.com/rearrange?blogID\x3d1030619672955979982','//www.avnishyadav.com/2018/09/day-8-developing-neural-machine.html','1030619672955979982');
_WidgetManager._SetDataContext([{'name': 'blog', 'data': {'blogId': '1030619672955979982', 'title': 'Avnish Yadav', 'url': 'https://www.avnishyadav.com/2018/09/day-8-developing-neural-machine.html', 'canonicalUrl': 'https://www.avnishyadav.com/2018/09/day-8-developing-neural-machine.html', 'homepageUrl': 'https://www.avnishyadav.com/', 'searchUrl': 'https://www.avnishyadav.com/search', 'canonicalHomepageUrl': 'https://www.avnishyadav.com/', 'blogspotFaviconUrl': 'https://www.avnishyadav.com/favicon.ico', 'bloggerUrl': 'https://www.blogger.com', 'hasCustomDomain': true, 'httpsEnabled': true, 'enabledCommentProfileImages': true, 'gPlusViewType': 'FILTERED_POSTMOD', 'adultContent': false, 'analyticsAccountNumber': '', 'encoding': 'UTF-8', 'locale': 'en-GB', 'localeUnderscoreDelimited': 'en_gb', 'languageDirection': 'ltr', 'isPrivate': false, 'isMobile': false, 'isMobileRequest': false, 'mobileClass': '', 'isPrivateBlog': false, 'isDynamicViewsAvailable': true, 'feedLinks': '\x3clink rel\x3d\x22alternate\x22 type\x3d\x22application/atom+xml\x22 title\x3d\x22Avnish Yadav - Atom\x22 href\x3d\x22https://www.avnishyadav.com/feeds/posts/default\x22 /\x3e\n\x3clink rel\x3d\x22alternate\x22 type\x3d\x22application/rss+xml\x22 title\x3d\x22Avnish Yadav - RSS\x22 href\x3d\x22https://www.avnishyadav.com/feeds/posts/default?alt\x3drss\x22 /\x3e\n\x3clink rel\x3d\x22service.post\x22 type\x3d\x22application/atom+xml\x22 title\x3d\x22Avnish Yadav - Atom\x22 href\x3d\x22https://www.blogger.com/feeds/1030619672955979982/posts/default\x22 /\x3e\n\n\x3clink rel\x3d\x22alternate\x22 type\x3d\x22application/atom+xml\x22 title\x3d\x22Avnish Yadav - Atom\x22 href\x3d\x22https://www.avnishyadav.com/feeds/7244771766538049381/comments/default\x22 /\x3e\n', 'meTag': '', 'adsenseClientId': 'ca-pub-6226434833206940', 'adsenseHostId': 'ca-host-pub-1556223355139109', 'adsenseHasAds': true, 'adsenseAutoAds': false, 'boqCommentIframeForm': true, 'loginRedirectParam': '', 'view': '', 'dynamicViewsCommentsSrc': '//www.blogblog.com/dynamicviews/4224c15c4e7c9321/js/comments.js', 'dynamicViewsScriptSrc': '//www.blogblog.com/dynamicviews/361ce9cf7a112c52', 'plusOneApiSrc': 'https://apis.google.com/js/platform.js', 'disableGComments': true, 'interstitialAccepted': false, 'sharing': {'platforms': [{'name': 'Get link', 'key': 'link', 'shareMessage': 'Get link', 'target': ''}, {'name': 'Facebook', 'key': 'facebook', 'shareMessage': 'Share to Facebook', 'target': 'facebook'}, {'name': 'BlogThis!', 'key': 'blogThis', 'shareMessage': 'BlogThis!', 'target': 'blog'}, {'name': 'X', 'key': 'twitter', 'shareMessage': 'Share to X', 'target': 'twitter'}, {'name': 'Pinterest', 'key': 'pinterest', 'shareMessage': 'Share to Pinterest', 'target': 'pinterest'}, {'name': 'Email', 'key': 'email', 'shareMessage': 'Email', 'target': 'email'}], 'disableGooglePlus': true, 'googlePlusShareButtonWidth': 0, 'googlePlusBootstrap': '\x3cscript type\x3d\x22text/javascript\x22\x3ewindow.___gcfg \x3d {\x27lang\x27: \x27en_GB\x27};\x3c/script\x3e'}, 'hasCustomJumpLinkMessage': false, 'jumpLinkMessage': 'Read more', 'pageType': 'item', 'postId': '7244771766538049381', 'postImageThumbnailUrl': 'https://blogger.googleusercontent.com/img/b/R29vZ2xl/AVvXsEhp4N-AVKbPkFHcBA-pa9e0qTstx-BZ1TOoTLp_GOzMv_ojmlZGk_bi8ek-AI45iZvRaLQmyhXnJ6Hx1_EEoGSQwYTAlCBi4BsJnBIEo1AtpCN2pbv5j8ZJ4dT2BwEaWoAMdkxpzop4cdsn/s72-c/Day-8.jpg', 'postImageUrl': 'https://blogger.googleusercontent.com/img/b/R29vZ2xl/AVvXsEhp4N-AVKbPkFHcBA-pa9e0qTstx-BZ1TOoTLp_GOzMv_ojmlZGk_bi8ek-AI45iZvRaLQmyhXnJ6Hx1_EEoGSQwYTAlCBi4BsJnBIEo1AtpCN2pbv5j8ZJ4dT2BwEaWoAMdkxpzop4cdsn/s640/Day-8.jpg', 'pageName': 'Day 8 - Developing a Neural Machine Translation System from Scratch Part 2', 'pageTitle': 'Avnish Yadav: Day 8 - Developing a Neural Machine Translation System from Scratch Part 2', 'metaDescription': ''}}, {'name': 'features', 'data': {}}, {'name': 'messages', 'data': {'edit': 'Edit', 'linkCopiedToClipboard': 'Link copied to clipboard', 'ok': 'Ok', 'postLink': 'Post link'}}, {'name': 'template', 'data': {'name': 'custom', 'localizedName': 'Custom', 'isResponsive': true, 'isAlternateRendering': false, 'isCustom': true}}, {'name': 'view', 'data': {'classic': {'name': 'classic', 'url': '?view\x3dclassic'}, 'flipcard': {'name': 'flipcard', 'url': '?view\x3dflipcard'}, 'magazine': {'name': 'magazine', 'url': '?view\x3dmagazine'}, 'mosaic': {'name': 'mosaic', 'url': '?view\x3dmosaic'}, 'sidebar': {'name': 'sidebar', 'url': '?view\x3dsidebar'}, 'snapshot': {'name': 'snapshot', 'url': '?view\x3dsnapshot'}, 'timeslide': {'name': 'timeslide', 'url': '?view\x3dtimeslide'}, 'isMobile': false, 'title': 'Day 8 - Developing a Neural Machine Translation System from Scratch Part 2', 'description': 'A blog about Machine learning, Salesforce,  Web Designing, Programming, Electronics, Tech Info and latest news related to Physics and Computers.', 'featuredImage': 'https://blogger.googleusercontent.com/img/b/R29vZ2xl/AVvXsEhp4N-AVKbPkFHcBA-pa9e0qTstx-BZ1TOoTLp_GOzMv_ojmlZGk_bi8ek-AI45iZvRaLQmyhXnJ6Hx1_EEoGSQwYTAlCBi4BsJnBIEo1AtpCN2pbv5j8ZJ4dT2BwEaWoAMdkxpzop4cdsn/s640/Day-8.jpg', 'url': 'https://www.avnishyadav.com/2018/09/day-8-developing-neural-machine.html', 'type': 'item', 'isSingleItem': true, 'isMultipleItems': false, 'isError': false, 'isPage': false, 'isPost': true, 'isHomepage': false, 'isArchive': false, 'isLabelSearch': false, 'postId': 7244771766538049381}}, {'name': 'widgets', 'data': [{'title': 'Upload Image', 'type': 'Image', 'sectionId': 'upload-image', 'id': 'Image10'}, {'title': 'Search This Blog', 'type': 'BlogSearch', 'sectionId': 'upload-image', 'id': 'BlogSearch1'}, {'type': 'AdSense', 'sectionId': 'upload-image', 'id': 'AdSense1'}, {'type': 'AdSense', 'sectionId': 'upload-image', 'id': 'AdSense2'}, {'type': 'Attribution', 'sectionId': 'upload-image', 'id': 'Attribution1'}, {'title': 'Popular Posts', 'type': 'PopularPosts', 'sectionId': 'upload-image', 'id': 'PopularPosts1', 'posts': [{'title': 'How to Build a Simple CSV Parser with Lightning Web Components', 'id': 392193078338306824}, {'title': 'Adding and Removing Styles  on a Lightning Component during runtime.', 'id': 6696642424647228466}, {'title': 'Record search in the lightning component using Javascript', 'id': 3905288771382147194}]}, {'title': '', 'type': 'PageList', 'sectionId': 'upload-image', 'id': 'PageList1'}, {'title': 'Logo', 'type': 'HTML', 'sectionId': 'header-main', 'id': 'HTML10'}, {'title': 'Icons, Dark, Search', 'type': 'LinkList', 'sectionId': 'header-main', 'id': 'LinkList10'}, {'title': 'Menu', 'type': 'LinkList', 'sectionId': 'header-main', 'id': 'LinkList11'}, {'title': 'Avnish\x27s Blog', 'type': 'HTML', 'sectionId': 'before-blog', 'id': 'HTML2'}, {'title': 'Featured Post', 'type': 'FeaturedPost', 'sectionId': 'before-blog', 'id': 'FeaturedPost1', 'postId': '564482976678445809'}, {'type': 'AdSense', 'sectionId': 'before-post', 'id': 'AdSense4'}, {'title': 'Blog Posts', 'type': 'Blog', 'sectionId': 'blog-post', 'id': 'Blog1', 'posts': [{'id': '7244771766538049381', 'title': 'Day 8 - Developing a Neural Machine Translation System from Scratch Part 2', 'featuredImage': 'https://blogger.googleusercontent.com/img/b/R29vZ2xl/AVvXsEhp4N-AVKbPkFHcBA-pa9e0qTstx-BZ1TOoTLp_GOzMv_ojmlZGk_bi8ek-AI45iZvRaLQmyhXnJ6Hx1_EEoGSQwYTAlCBi4BsJnBIEo1AtpCN2pbv5j8ZJ4dT2BwEaWoAMdkxpzop4cdsn/s640/Day-8.jpg', 'showInlineAds': false}], 'headerByline': {'regionName': 'header1', 'items': [{'name': 'share', 'label': ''}, {'name': 'author', 'label': 'by'}, {'name': 'timestamp', 'label': 'd MMM, yyyy'}]}, 'footerBylines': [{'regionName': 'footer1', 'items': [{'name': 'comments', 'label': 'Comment'}]}, {'regionName': 'footer2', 'items': [{'name': 'labels', 'label': ''}]}], 'allBylineItems': [{'name': 'share', 'label': ''}, {'name': 'author', 'label': 'by'}, {'name': 'timestamp', 'label': 'd MMM, yyyy'}, {'name': 'comments', 'label': 'Comment'}, {'name': 'labels', 'label': ''}]}, {'type': 'AdSense', 'sectionId': 'ads-post', 'id': 'AdSense6'}, {'title': '#You may also like', 'type': 'HTML', 'sectionId': 'ads-post', 'id': 'HTML15'}, {'type': 'AdSense', 'sectionId': 'ads-post', 'id': 'AdSense5'}, {'type': 'AdSense', 'sectionId': 'after-blog', 'id': 'AdSense7'}, {'title': 'Youtube - Subscribe Us', 'type': 'HTML', 'sectionId': 'sidebar-static', 'id': 'HTML3'}, {'title': 'Popular Posts', 'type': 'PopularPosts', 'sectionId': 'sidebar-static', 'id': 'PopularPosts10', 'posts': [{'title': 'How do I write a C program to implement a SRTF (Shortest Remaining Time First) scheduling algorithm, along with displaying the Gantt chart?', 'id': 3881567259149966802}, {'title': 'Simple Speech Recognition in Python', 'id': 2259871367337308242}, {'title': 'Meta Tag Explained', 'id': 8176947953431626135}, {'title': 'Trigger to count number of Contacts associated with an Account', 'id': 6639085565003346730}, {'title': 'Adding and Removing Styles  on a Lightning Component during runtime.', 'id': 6696642424647228466}, {'title': 'Day 10 - Simple Speech to Text Converter Using Speech Recognization in Python', 'id': 4487570960785074297}, {'title': 'How To Make Dynamic Search Using Salesforce Lightning and Regular Expression', 'id': 911989698166709763}, {'title': 'Day 16 - Face recognition under 25 lines', 'id': 4925865616963523724}, {'title': 'LEARN PHP IN 10 DAYS', 'id': 3797819043996052083}, {'title': 'Record search in the lightning component using Javascript', 'id': 3905288771382147194}]}, {'type': 'AdSense', 'sectionId': 'sidebar-static', 'id': 'AdSense8'}, {'title': 'Categories', 'type': 'Label', 'sectionId': 'sidebar-static', 'id': 'Label10'}, {'title': 'Hashtag', 'type': 'Label', 'sectionId': 'sidebar-static', 'id': 'Label11'}, {'title': 'Blog Archive', 'type': 'BlogArchive', 'sectionId': 'sidebar-static', 'id': 'BlogArchive10'}, {'title': '#Recent Post', 'type': 'HTML', 'sectionId': 'sidebar-static', 'id': 'HTML19'}, {'type': 'AdSense', 'sectionId': 'sidebar-sticky', 'id': 'AdSense9'}, {'title': 'About Us', 'type': 'HTML', 'sectionId': 'footer-widget', 'id': 'HTML21'}, {'type': 'AdSense', 'sectionId': 'footer-widget', 'id': 'AdSense10'}, {'title': 'Follow Us', 'type': 'LinkList', 'sectionId': 'footer-widget', 'id': 'LinkList14'}, {'title': 'Newsletter', 'type': 'HTML', 'sectionId': 'footer-widget', 'id': 'HTML22'}, {'title': 'Copyright', 'type': 'HTML', 'sectionId': 'copyright', 'id': 'HTML23'}, {'title': 'SVG Icons', 'type': 'HTML', 'sectionId': 'jet-options', 'id': 'HTML24'}]}]);
_WidgetManager._RegisterWidget('_ImageView', new _WidgetInfo('Image10', 'upload-image', document.getElementById('Image10'), {'resize': false}, 'displayModeFull'));
_WidgetManager._RegisterWidget('_BlogSearchView', new _WidgetInfo('BlogSearch1', 'upload-image', document.getElementById('BlogSearch1'), {}, 'displayModeFull'));
_WidgetManager._RegisterWidget('_AdSenseView', new _WidgetInfo('AdSense1', 'upload-image', document.getElementById('AdSense1'), {}, 'displayModeFull'));
_WidgetManager._RegisterWidget('_AdSenseView', new _WidgetInfo('AdSense2', 'upload-image', document.getElementById('AdSense2'), {}, 'displayModeFull'));
_WidgetManager._RegisterWidget('_AttributionView', new _WidgetInfo('Attribution1', 'upload-image', document.getElementById('Attribution1'), {}, 'displayModeFull'));
_WidgetManager._RegisterWidget('_PopularPostsView', new _WidgetInfo('PopularPosts1', 'upload-image', document.getElementById('PopularPosts1'), {}, 'displayModeFull'));
_WidgetManager._RegisterWidget('_PageListView', new _WidgetInfo('PageList1', 'upload-image', document.getElementById('PageList1'), {'title': '', 'links': [{'isCurrentPage': false, 'href': 'https://avnishyadav25.blogspot.com/', 'title': 'Home'}, {'isCurrentPage': false, 'href': 'http://avnishyadav25.blogspot.com/p/about-me.html', 'title': 'ABOUT ME'}, {'isCurrentPage': false, 'href': 'https://avnishyadav25.blogspot.com/search/label/machine%20learning', 'title': 'MACHINE LEARNING'}, {'isCurrentPage': false, 'href': 'https://avnishyadav25.blogspot.com/search/label/salesforce', 'title': 'SALESFORCE'}, {'isCurrentPage': false, 'href': 'http://avnishyadav25.blogspot.com/p/contact-me.html', 'title': 'CONTACT ME'}], 'mobile': false, 'showPlaceholder': true, 'hasCurrentPage': false}, 'displayModeFull'));
_WidgetManager._RegisterWidget('_HTMLView', new _WidgetInfo('HTML10', 'header-main', document.getElementById('HTML10'), {}, 'displayModeFull'));
_WidgetManager._RegisterWidget('_LinkListView', new _WidgetInfo('LinkList10', 'header-main', document.getElementById('LinkList10'), {}, 'displayModeFull'));
_WidgetManager._RegisterWidget('_LinkListView', new _WidgetInfo('LinkList11', 'header-main', document.getElementById('LinkList11'), {}, 'displayModeFull'));
_WidgetManager._RegisterWidget('_HTMLView', new _WidgetInfo('HTML2', 'before-blog', document.getElementById('HTML2'), {}, 'displayModeFull'));
_WidgetManager._RegisterWidget('_FeaturedPostView', new _WidgetInfo('FeaturedPost1', 'before-blog', document.getElementById('FeaturedPost1'), {}, 'displayModeFull'));
_WidgetManager._RegisterWidget('_AdSenseView', new _WidgetInfo('AdSense4', 'before-post', document.getElementById('AdSense4'), {}, 'displayModeFull'));
_WidgetManager._RegisterWidget('_BlogView', new _WidgetInfo('Blog1', 'blog-post', document.getElementById('Blog1'), {'cmtInteractionsEnabled': false, 'lightboxEnabled': true, 'lightboxModuleUrl': 'https://www.blogger.com/static/v1/jsbin/2656912462-lbx__en_gb.js', 'lightboxCssUrl': 'https://www.blogger.com/static/v1/v-css/1964470060-lightbox_bundle.css'}, 'displayModeFull'));
_WidgetManager._RegisterWidget('_AdSenseView', new _WidgetInfo('AdSense6', 'ads-post', document.getElementById('AdSense6'), {}, 'displayModeFull'));
_WidgetManager._RegisterWidget('_HTMLView', new _WidgetInfo('HTML15', 'ads-post', document.getElementById('HTML15'), {}, 'displayModeFull'));
_WidgetManager._RegisterWidget('_AdSenseView', new _WidgetInfo('AdSense5', 'ads-post', document.getElementById('AdSense5'), {}, 'displayModeFull'));
_WidgetManager._RegisterWidget('_AdSenseView', new _WidgetInfo('AdSense7', 'after-blog', document.getElementById('AdSense7'), {}, 'displayModeFull'));
_WidgetManager._RegisterWidget('_HTMLView', new _WidgetInfo('HTML3', 'sidebar-static', document.getElementById('HTML3'), {}, 'displayModeFull'));
_WidgetManager._RegisterWidget('_PopularPostsView', new _WidgetInfo('PopularPosts10', 'sidebar-static', document.getElementById('PopularPosts10'), {}, 'displayModeFull'));
_WidgetManager._RegisterWidget('_AdSenseView', new _WidgetInfo('AdSense8', 'sidebar-static', document.getElementById('AdSense8'), {}, 'displayModeFull'));
_WidgetManager._RegisterWidget('_LabelView', new _WidgetInfo('Label10', 'sidebar-static', document.getElementById('Label10'), {}, 'displayModeFull'));
_WidgetManager._RegisterWidget('_LabelView', new _WidgetInfo('Label11', 'sidebar-static', document.getElementById('Label11'), {}, 'displayModeFull'));
_WidgetManager._RegisterWidget('_BlogArchiveView', new _WidgetInfo('BlogArchive10', 'sidebar-static', document.getElementById('BlogArchive10'), {'languageDirection': 'ltr', 'loadingMessage': 'Loading\x26hellip;'}, 'displayModeFull'));
_WidgetManager._RegisterWidget('_HTMLView', new _WidgetInfo('HTML19', 'sidebar-static', document.getElementById('HTML19'), {}, 'displayModeFull'));
_WidgetManager._RegisterWidget('_AdSenseView', new _WidgetInfo('AdSense9', 'sidebar-sticky', document.getElementById('AdSense9'), {}, 'displayModeFull'));
_WidgetManager._RegisterWidget('_HTMLView', new _WidgetInfo('HTML21', 'footer-widget', document.getElementById('HTML21'), {}, 'displayModeFull'));
_WidgetManager._RegisterWidget('_AdSenseView', new _WidgetInfo('AdSense10', 'footer-widget', document.getElementById('AdSense10'), {}, 'displayModeFull'));
_WidgetManager._RegisterWidget('_LinkListView', new _WidgetInfo('LinkList14', 'footer-widget', document.getElementById('LinkList14'), {}, 'displayModeFull'));
_WidgetManager._RegisterWidget('_HTMLView', new _WidgetInfo('HTML22', 'footer-widget', document.getElementById('HTML22'), {}, 'displayModeFull'));
_WidgetManager._RegisterWidget('_HTMLView', new _WidgetInfo('HTML23', 'copyright', document.getElementById('HTML23'), {}, 'displayModeFull'));
_WidgetManager._RegisterWidget('_HTMLView', new _WidgetInfo('HTML24', 'jet-options', document.getElementById('HTML24'), {}, 'displayModeFull'));
</script>
</body>*/</style>