{"id":5451,"date":"2022-09-03T08:34:00","date_gmt":"2022-09-03T08:34:00","guid":{"rendered":"https:\/\/phrase.com\/?p=5451"},"modified":"2023-12-06T13:13:50","modified_gmt":"2023-12-06T12:13:50","slug":"machine-translation-glossaries","status":"publish","type":"post","link":"https:\/\/phrase.com\/blog\/posts\/machine-translation-glossaries\/","title":{"rendered":"Machine Translation Glossaries: Why They Matter and How to Use Them"},"content":{"rendered":"\n<div id=\"acf\/text-block_747fdaf53c4b787fed411a78e6800956\" class=\"pxblock pxblock--text spacing--default bg--white\">\n\n\t\n\t<div class=\"container\">\n\t\t<div class=\"wysiwyg animate-in\">\n\t\t\t<p>As <a href=\"https:\/\/phrase.com\/blog\/posts\/artificial-intelligence\/\">artificial intelligence<\/a> takes center stage more and more, machine translation (MT) emphasizes the importance of precision and recall for its success. Every translation holds significance, and the effectiveness of MT engines is greatly influenced by the accuracy and curation of the information provided.<\/p>\n<p><span style=\"font-weight: 400;\">One of the simplest ways to <a href=\"https:\/\/phrase.com\/blog\/posts\/machine-translation-customization\/\">customize machine translation<\/a> is using machine translation glossaries. Learn what they are, why they matter, and how to leverage them to improve MT output in the long run.<\/span><\/p>\n<div id=\"ez-toc-container\" class=\"ez-toc-v2_0_69_1 counter-hierarchy ez-toc-counter ez-toc-grey ez-toc-container-direction\">\n<div class=\"ez-toc-title-container\">\n<p class=\"ez-toc-title\" style=\"cursor:inherit\">Overview<\/p>\n<span class=\"ez-toc-title-toggle\"><a href=\"#\" class=\"ez-toc-pull-right ez-toc-btn ez-toc-btn-xs ez-toc-btn-default ez-toc-toggle\" aria-label=\"Toggle Table of Content\"><span class=\"ez-toc-js-icon-con\"><span class=\"\"><span class=\"eztoc-hide\" style=\"display:none;\">Toggle<\/span><span class=\"ez-toc-icon-toggle-span\"><svg style=\"fill: #999;color:#999\" xmlns=\"http:\/\/www.w3.org\/2000\/svg\" class=\"list-377408\" width=\"20px\" height=\"20px\" viewBox=\"0 0 24 24\" fill=\"none\"><path d=\"M6 6H4v2h2V6zm14 0H8v2h12V6zM4 11h2v2H4v-2zm16 0H8v2h12v-2zM4 16h2v2H4v-2zm16 0H8v2h12v-2z\" fill=\"currentColor\"><\/path><\/svg><svg style=\"fill: #999;color:#999\" class=\"arrow-unsorted-368013\" xmlns=\"http:\/\/www.w3.org\/2000\/svg\" width=\"10px\" height=\"10px\" viewBox=\"0 0 24 24\" version=\"1.2\" baseProfile=\"tiny\"><path d=\"M18.2 9.3l-6.2-6.3-6.2 6.3c-.2.2-.3.4-.3.7s.1.5.3.7c.2.2.4.3.7.3h11c.3 0 .5-.1.7-.3.2-.2.3-.5.3-.7s-.1-.5-.3-.7zM5.8 14.7l6.2 6.3 6.2-6.3c.2-.2.3-.5.3-.7s-.1-.5-.3-.7c-.2-.2-.4-.3-.7-.3h-11c-.3 0-.5.1-.7.3-.2.2-.3.5-.3.7s.1.5.3.7z\"\/><\/svg><\/span><\/span><\/span><\/a><\/span><\/div>\n<nav><ul class='ez-toc-list ez-toc-list-level-1 ' ><li class='ez-toc-page-1 ez-toc-heading-level-2'><a class=\"ez-toc-link ez-toc-heading-1\" href=\"https:\/\/phrase.com\/blog\/posts\/machine-translation-glossaries\/#what-are-machine-translation-glossaries\" title=\"What are machine translation glossaries?\">What are machine translation glossaries?<\/a><\/li><li class='ez-toc-page-1 ez-toc-heading-level-2'><a class=\"ez-toc-link ez-toc-heading-2\" href=\"https:\/\/phrase.com\/blog\/posts\/machine-translation-glossaries\/#why-are-mt-glossaries-important\" title=\"Why are MT glossaries important?\">Why are MT glossaries important?<\/a><\/li><li class='ez-toc-page-1 ez-toc-heading-level-2'><a class=\"ez-toc-link ez-toc-heading-3\" href=\"https:\/\/phrase.com\/blog\/posts\/machine-translation-glossaries\/#how-do-mt-glossaries-work\" title=\"How do MT glossaries work?\">How do MT glossaries work?<\/a><\/li><li class='ez-toc-page-1 ez-toc-heading-level-2'><a class=\"ez-toc-link ez-toc-heading-4\" href=\"https:\/\/phrase.com\/blog\/posts\/machine-translation-glossaries\/#best-practices-for-using-mt-glossaries\" title=\"Best practices for using MT glossaries\">Best practices for using MT glossaries<\/a><ul class='ez-toc-list-level-3' ><li class='ez-toc-heading-level-3'><a class=\"ez-toc-link ez-toc-heading-5\" href=\"https:\/\/phrase.com\/blog\/posts\/machine-translation-glossaries\/#what-terms-are-suitable-for-mt-glossaries\" title=\"What terms are suitable for MT glossaries?\">What terms are suitable for MT glossaries?<\/a><\/li><li class='ez-toc-page-1 ez-toc-heading-level-3'><a class=\"ez-toc-link ez-toc-heading-6\" href=\"https:\/\/phrase.com\/blog\/posts\/machine-translation-glossaries\/#what-terms-are-less-suitable-for-mt-glossaries\" title=\"What terms are less suitable for MT glossaries?\">What terms are less suitable for MT glossaries?<\/a><\/li><\/ul><\/li><li class='ez-toc-page-1 ez-toc-heading-level-2'><a class=\"ez-toc-link ez-toc-heading-7\" href=\"https:\/\/phrase.com\/blog\/posts\/machine-translation-glossaries\/#managing-mt-glossaries-for-all-engines-directly-within-a-translation-management-system\" title=\"Managing MT glossaries for all engines directly within a translation management system\">Managing MT glossaries for all engines directly within a translation management system<\/a><\/li><li class='ez-toc-page-1 ez-toc-heading-level-2'><a class=\"ez-toc-link ez-toc-heading-8\" href=\"https:\/\/phrase.com\/blog\/posts\/machine-translation-glossaries\/#how-does-glossary-support-work-with-each-mt-engine-in-phrase\" title=\"How does glossary support work with each MT engine in Phrase?\">How does glossary support work with each MT engine in Phrase?<\/a><\/li><li class='ez-toc-page-1 ez-toc-heading-level-2'><a class=\"ez-toc-link ez-toc-heading-9\" href=\"https:\/\/phrase.com\/blog\/posts\/machine-translation-glossaries\/#looking-to-the-future\" title=\"Looking to the future\">Looking to the future<\/a><\/li><\/ul><\/nav><\/div>\n<h2><span class=\"ez-toc-section\" id=\"what-are-machine-translation-glossaries\"><\/span>What are machine translation glossaries?<span class=\"ez-toc-section-end\"><\/span><\/h2>\n<p><span style=\"font-weight: 400;\">Glossaries, in the context of <a href=\"https:\/\/phrase.com\/blog\/posts\/machine-translation\/\">machine translation<\/a>, are a collection of words and phrases with a preferred machine translation. They\u2019re sometimes referred to as:<\/span><\/p>\n<ul>\n<li style=\"font-weight: 400;\" aria-level=\"1\"><span style=\"font-weight: 400;\">Custom terminology<\/span><\/li>\n<li style=\"font-weight: 400;\" aria-level=\"1\"><span style=\"font-weight: 400;\">Custom vocabulary<\/span><\/li>\n<li style=\"font-weight: 400;\" aria-level=\"1\"><span style=\"font-weight: 400;\">Custom dictionaries, etc.<\/span><\/li>\n<\/ul>\n<p><span style=\"font-weight: 400;\">MT glossaries are similar to term bases, but instead of being used by linguists, they are designed to be used by machine translation software.<\/span><\/p>\n<p><span style=\"font-weight: 400;\">When attached to MT engines, glossaries help improve the quality of the MT output by ensuring that the MT engines correctly apply pre-determined terminology.<\/span><\/p>\n<p><span style=\"font-weight: 400;\">Before a source text is translated by an MT engine, it will compare the attached glossary file to the source text to identify terms that have a preferred translation and apply those.<\/span><\/p>\n<p><span style=\"font-weight: 400;\">It\u2019s important to note that an MT glossary doesn\u2019t re-train an engine\u2014it simply overrides any appropriate term with a predetermined translation.<\/span><\/p>\n<h2><span class=\"ez-toc-section\" id=\"why-are-mt-glossaries-important\"><\/span>Why are MT glossaries important?<span class=\"ez-toc-section-end\"><\/span><\/h2>\n<p><a href=\"https:\/\/www.memsource.com\/blog\/machine-translation-tools\/\"><span style=\"font-weight: 400;\">Machine translation software<\/span><\/a><span style=\"font-weight: 400;\"> has dramatically improved in output quality over the past few years. Nevertheless, it still lacks the contextual understanding of a human translator.<\/span><\/p>\n<p><span style=\"font-weight: 400;\">This means it can make some very basic errors, especially when handling an ambiguous word or a term that has a specific meaning in a given context.<\/span><\/p>\n<p><span style=\"font-weight: 400;\">Since glossaries are adapted to a domain\u2019s or company\u2019s specific terminology, they help machine translation output be far more accurate than if the engine just drew from general-purpose data sets.<\/span><\/p>\n<h2><span class=\"ez-toc-section\" id=\"how-do-mt-glossaries-work\"><\/span>How do MT glossaries work?<span class=\"ez-toc-section-end\"><\/span><\/h2>\n<p><span style=\"font-weight: 400;\">The steps that an MT engine usually follows are:<\/span><\/p>\n<ul>\n<li style=\"font-weight: 400;\" aria-level=\"1\"><span style=\"font-weight: 400;\">Receive a source text<\/span><\/li>\n<li style=\"font-weight: 400;\" aria-level=\"1\"><span style=\"font-weight: 400;\">Translate the source text<\/span><\/li>\n<li style=\"font-weight: 400;\" aria-level=\"1\"><span style=\"font-weight: 400;\">Display the output translation<\/span><\/li>\n<\/ul>\n<p><span style=\"font-weight: 400;\">With an MT glossary included, MT engines add an intermediate step to the process:<\/span><\/p>\n<ul>\n<li style=\"font-weight: 400;\" aria-level=\"1\"><span style=\"font-weight: 400;\">Receive source text<\/span><\/li>\n<li style=\"font-weight: 400;\" aria-level=\"1\"><span style=\"font-weight: 400;\">Translate the source text<\/span><\/li>\n<li style=\"font-weight: 400;\" aria-level=\"1\"><span style=\"font-weight: 400;\">Search and replace the translation with your preferred terminology<\/span><\/li>\n<li style=\"font-weight: 400;\" aria-level=\"1\"><span style=\"font-weight: 400;\">Present the output translation<\/span><\/li>\n<\/ul>\n<p><span style=\"font-weight: 400;\">Put another way, with the help of glossaries, the MT engine searches for matches and automatically applies them while translating.<\/span><\/p>\n<p><span style=\"font-weight: 400;\">For example, suppose you have a brand for a Bluetooth speaker called \u201cConnected,\u201d and you want to translate the following sentence into Spanish: \u201cYour Connected device was not detected.\u201d<\/span><\/p>\n<p><span style=\"font-weight: 400;\">Without an MT glossary, your MT engine would produce something like the following result: \u201cNo se ha detectado tu dispositivo conectado\u201d (literal back-translation into English: \u201cYour connected device was not detected\u201d). As you can see, the brand name \u201cConnected\u201d has been translated as \u201cconectado,\u201d which would be incorrect in this case.<\/span><\/p>\n<p><span style=\"font-weight: 400;\">If you add the brand name \u201cConnected\u201d to your MT glossary, you can enforce the non-translatability of the term. In that case, the MT engine will produce this result: \u201cNo se ha detectado tu dispositivo Connected.\u201d This is spot on\u2014using an MT glossary significantly improves accuracy by automatically providing the desired translation.<\/span><\/p>\n\t\t<\/div>\n\t<\/div>\n<\/div>\n\n\n\n<div id=\"acf\/blog-cta-block_319066b7364ab337bd576c0fb01a205a\" class=\"pxblock pxblock--blog-cta bg--grey image--orientation-portrait\">\n\t<div class=\"block-container\">\n\t\t\t\t\t<div class=\"image image--align-middle\">\n\t\t\t\t<img loading=\"lazy\" decoding=\"async\" width=\"1811\" height=\"2560\" src=\"https:\/\/phrase.com\/wp-content\/uploads\/2022\/09\/present-future-machine-translation-study-cover-scaled.jpg\" class=\"attachment-original size-original\" alt=\"The present and future of machine translation study cover.jpg | Phrase\" srcset=\"https:\/\/phrase.com\/wp-content\/uploads\/2022\/09\/present-future-machine-translation-study-cover-scaled.jpg 1811w, https:\/\/phrase.com\/wp-content\/uploads\/2022\/09\/present-future-machine-translation-study-cover-212x300.jpg 212w, https:\/\/phrase.com\/wp-content\/uploads\/2022\/09\/present-future-machine-translation-study-cover-724x1024.jpg 724w, https:\/\/phrase.com\/wp-content\/uploads\/2022\/09\/present-future-machine-translation-study-cover-768x1086.jpg 768w, https:\/\/phrase.com\/wp-content\/uploads\/2022\/09\/present-future-machine-translation-study-cover-1086x1536.jpg 1086w, https:\/\/phrase.com\/wp-content\/uploads\/2022\/09\/present-future-machine-translation-study-cover-1448x2048.jpg 1448w\" sizes=\"(max-width: 1811px) 100vw, 1811px\" \/>\t\t\t<\/div>\n\t\t\t\t<div class=\"content\">\n\t\t\t<p class=\"subhead\">Download for free<\/p>\n<p class=\"h6\">Your up-to-the-minute guide to machine translation<\/p>\n<p class=\"small\">Learn about new technologies to improve machine translation output quality, the latest on MT post-editing pricing models, and how to best shop for machine translation.<\/p>\n<p><a class=\"btn btn--outline\" href=\"https:\/\/phrase.com\/resources\/the-present-and-future-of-machine-translation\/\">Download guide<\/a><\/p>\n\t\t<\/div>\n\t<\/div>\n<\/div>\n\n\n\n<div id=\"acf\/text-block_97a509014c830ce121640ade4bc57862\" class=\"pxblock pxblock--text spacing--default bg--white\">\n\n\t\n\t<div class=\"container\">\n\t\t<div class=\"wysiwyg animate-in\">\n\t\t\t<h2><span class=\"ez-toc-section\" id=\"best-practices-for-using-mt-glossaries\"><\/span>Best practices for using MT glossaries<span class=\"ez-toc-section-end\"><\/span><\/h2>\n<p><span style=\"font-weight: 400;\">To ensure MT glossaries remain reliable and always up to date, here are a few best practices to follow:<\/span><\/p>\n<ul>\n<li style=\"font-weight: 400;\" aria-level=\"1\"><b>Keep it simple: <\/b><span style=\"font-weight: 400;\">Small glossaries, focusing only on the most essential terms, tend to be more effective\u2014massive glossaries could even harm your translation output.<\/span><\/li>\n<li style=\"font-weight: 400;\" aria-level=\"1\"><b>Limit customizations to words that you only want to be translated in one way:<\/b><span style=\"font-weight: 400;\"> The translation suggested by the MT engine should match exactly what you want.<\/span><\/li>\n<li style=\"font-weight: 400;\" aria-level=\"1\"><b>Ensure glossaries are free of errors:<\/b><span style=\"font-weight: 400;\"> Keep your terms free of spelling mistakes, formatting errors, or incorrect translations.<\/span><\/li>\n<li style=\"font-weight: 400;\" aria-level=\"1\"><b>Avoid having duplicate terms:<\/b><span style=\"font-weight: 400;\"> MT engines can struggle to apply the correct term if multiple instances are found.<\/span><\/li>\n<li style=\"font-weight: 400;\" aria-level=\"1\"><b>Post-edit essential translations: <\/b><span style=\"font-weight: 400;\">While glossaries can enhance translation quality, don\u2019t trust them blindly\u2014high-quality human checks on your MT output are always the best guarantee of accuracy. This process is called \u201cpost-editing.\u201d<\/span><\/li>\n<li style=\"font-weight: 400;\" aria-level=\"1\"><b>Be mindful of your language pair: <\/b><span style=\"font-weight: 400;\">In morphologically complex languages, like Finnish, Arabic, or Turkish, words may change shape depending on the context\u2014so customizations for these languages may not always produce the best results.<\/span><\/li>\n<li style=\"font-weight: 400;\" aria-level=\"1\"><b>Review documentation: <\/b><span style=\"font-weight: 400;\">Although the basic glossary functionality is similar across MT engines, the specifics might differ; it may be helpful to read the available documentation to find out how to best work with a given engine.<\/span><\/li>\n<li style=\"font-weight: 400;\" aria-level=\"1\"><b>Not all kinds of terms are appropriate for glossaries:<\/b><span style=\"font-weight: 400;\"> For the best results, focus on compound nouns; examples often include product names, like \u201cPostmates\u201d or other specific terms like \u201cWeWork.\u201d<\/span><\/li>\n<\/ul>\n<h3><span class=\"ez-toc-section\" id=\"what-terms-are-suitable-for-mt-glossaries\"><\/span>What terms are suitable for MT glossaries?<span class=\"ez-toc-section-end\"><\/span><\/h3>\n<p><span style=\"font-weight: 400;\">To maximize the impact and accuracy of MT glossaries, it\u2019s important to use them for specific types of terms:<\/span><\/p>\n<ul>\n<li style=\"font-weight: 400;\" aria-level=\"1\"><span style=\"font-weight: 400;\">Product names like \u201cFord Mondeo,\u201d \u201cSamsung Galaxy Note 5,\u201d etc.<\/span><\/li>\n<li style=\"font-weight: 400;\" aria-level=\"1\"><span style=\"font-weight: 400;\">Company names like \u201cApple,\u201d \u201cMicrosoft,\u201d etc.<\/span><\/li>\n<li style=\"font-weight: 400;\" aria-level=\"1\"><span style=\"font-weight: 400;\">Ambiguous words, e.g., homonyms (multiple-meaning words) like \u201ccrane\u201d (a machine vs. an animal) or \u201clead\u201d (the metal vs. a potential client)<\/span><\/li>\n<li style=\"font-weight: 400;\" aria-level=\"1\"><span style=\"font-weight: 400;\">Abbreviations: A shortened form of a word or phrase that\u2019s frequently used in the industry or domain of interest, e.g., TMS for \u201ctranslation management system\u201d<\/span><\/li>\n<li style=\"font-weight: 400;\" aria-level=\"1\"><span style=\"font-weight: 400;\">Borrowed words: Foreign words that the MT engine will likely keep in the original language, like the French \u201cc\u00f4te de boeuf\u201d dish, but which you want to translate nevertheless\u2014in this case, \u201crib eye\u201d<\/span><\/li>\n<\/ul>\n<h3><span class=\"ez-toc-section\" id=\"what-terms-are-less-suitable-for-mt-glossaries\"><\/span><span style=\"font-weight: 400;\">What terms are less suitable for MT glossaries?<\/span><span class=\"ez-toc-section-end\"><\/span><\/h3>\n<p><span style=\"font-weight: 400;\">At the same time, some morphological categories are less suitable to be documented and used in a machine translation glossary:<\/span><\/p>\n<ul>\n<li style=\"font-weight: 400;\" aria-level=\"1\"><span style=\"font-weight: 400;\">Verbs: MT glossaries can\u2019t conjugate them correctly in grammatical person, number, gender, tense, aspect, mood, voice, degree of formality, clusivity, transitivity, or valency.<\/span><\/li>\n<li style=\"font-weight: 400;\" aria-level=\"1\"><span style=\"font-weight: 400;\">Inflected languages with many cases and grammatical genders: MT glossaries can\u2019t currently change the form or ending of some words when the way in which they\u2019re used in sentences changes.<\/span><\/li>\n<\/ul>\n<h2><span class=\"ez-toc-section\" id=\"managing-mt-glossaries-for-all-engines-directly-within-a-translation-management-system\"><\/span>Managing MT glossaries for all engines directly within a translation management system<span class=\"ez-toc-section-end\"><\/span><\/h2>\n<p><span style=\"font-weight: 400;\">Translation management systems (TMS)<\/span><span style=\"font-weight: 400;\"> allow localization managers not only to centralize and automate the localization workflow but also make full use of well-established translation technology like translation memories and glossaries.<\/span><\/p>\n<p><span style=\"font-weight: 400;\">Modern TMS solutions, like Phrase, enable the use and management of glossaries without the need to upload and manage them with each individual MT provider.<\/span><\/p>\n<p><span style=\"font-weight: 400;\">In Phrase, you can directly upload, edit, and use MT glossaries for all supported engines, which can significantly reduce the amount of deployment and management time.<\/span><\/p>\n<h2><span class=\"ez-toc-section\" id=\"how-does-glossary-support-work-with-each-mt-engine-in-phrase\"><\/span>How does glossary support work with each MT engine in Phrase?<span class=\"ez-toc-section-end\"><\/span><\/h2>\n<p><span style=\"font-weight: 400;\">MT glossaries are available as a part of <\/span><a href=\"https:\/\/phrase.com\/platform\/ai\/\"><span style=\"font-weight: 400;\">Phrase Language AI<\/span><\/a><span style=\"font-weight: 400;\">, the suite&#8217;s machine translation add-on. Besides MT glossaries, <\/span><span style=\"font-weight: 400;\">Phrase Language AI<\/span><span style=\"font-weight: 400;\"> subscribers can take advantage of a number of fully managed machine translation and advanced AI-powered features like Quality Performance Score and MT autoselect.<\/span><\/p>\n<p><span style=\"font-weight: 400;\">Through <\/span><span style=\"font-weight: 400;\">Phrase Language AI<\/span><span style=\"font-weight: 400;\">, users can also add their own MT glossaries, which they can apply to fully managed MT engines:<\/span><\/p>\n<ul>\n<li style=\"font-weight: 400;\" aria-level=\"1\"><a href=\"https:\/\/phrase.com\/blog\/posts\/is-google-translate-accurate\/\"><span style=\"font-weight: 400;\">Google Translate<\/span><\/a><\/li>\n<li style=\"font-weight: 400;\" aria-level=\"1\"><span style=\"font-weight: 400;\">Amazon Translate<\/span><\/li>\n<li style=\"font-weight: 400;\" aria-level=\"1\"><a href=\"https:\/\/phrase.com\/blog\/posts\/deepl\/\"><span style=\"font-weight: 400;\">DeepL<\/span><\/a><\/li>\n<li aria-level=\"1\"><a href=\"https:\/\/phrase.com\/platform\/nextmt\/\">Phrase NextMT<\/a><\/li>\n<li style=\"font-weight: 400;\" aria-level=\"1\"><span style=\"font-weight: 400;\">Microsoft Translator<\/span><\/li>\n<li style=\"font-weight: 400;\" aria-level=\"1\"><span style=\"font-weight: 400;\">Rozetta Translate<\/span><\/li>\n<li style=\"font-weight: 400;\" aria-level=\"1\"><span style=\"font-weight: 400;\">Tencent TranSmart<\/span><\/li>\n<\/ul>\n<p><span style=\"font-weight: 400;\">As soon as you create a custom glossary, you need to attach it to an existing MT profile. You can create multiple MT glossaries and use them for different translation projects.<\/span><\/p>\n\t\t<\/div>\n\t<\/div>\n<\/div>\n\n\n\n<div id=\"acf\/blog-cta-block_5ea79fd12600a0459729b30c5f6f8e3b\" class=\"pxblock pxblock--blog-cta bg--grey image--orientation-square\">\n\t<div class=\"block-container\">\n\t\t\t\t\t<div class=\"image image--align-middle\">\n\t\t\t\t<img loading=\"lazy\" decoding=\"async\" width=\"1204\" height=\"1204\" src=\"https:\/\/phrase.com\/wp-content\/uploads\/2023\/03\/machine-transtion-report-key-visual.png\" class=\"attachment-original size-original\" alt=\"Machine transtion report key visual | Phrase\" srcset=\"https:\/\/phrase.com\/wp-content\/uploads\/2023\/03\/machine-transtion-report-key-visual.png 1204w, https:\/\/phrase.com\/wp-content\/uploads\/2023\/03\/machine-transtion-report-key-visual-300x300.png 300w, https:\/\/phrase.com\/wp-content\/uploads\/2023\/03\/machine-transtion-report-key-visual-1024x1024.png 1024w, https:\/\/phrase.com\/wp-content\/uploads\/2023\/03\/machine-transtion-report-key-visual-150x150.png 150w, https:\/\/phrase.com\/wp-content\/uploads\/2023\/03\/machine-transtion-report-key-visual-768x768.png 768w\" sizes=\"(max-width: 1204px) 100vw, 1204px\" \/>\t\t\t<\/div>\n\t\t\t\t<div class=\"content\">\n\t\t\t<p class=\"h4\">Interactive MT report: Uncover top performers<\/p>\n<p class=\"small\">Find out how leading machine translation engines perform for different content types using the latest data in our quarterly machine translation report.<\/p>\n<p><a class=\"btn btn--outline\" href=\"https:\/\/phrase.com\/resources\/machine-translation-report\/\">Get MT insights<\/a><\/p>\n\t\t<\/div>\n\t<\/div>\n<\/div>\n\n\n\n<div id=\"acf\/text-block_05be7e6df684930505e17245d28a5849\" class=\"pxblock pxblock--text spacing--default bg--white\">\n\n\t\n\t<div class=\"container\">\n\t\t<div class=\"wysiwyg animate-in\">\n\t\t\t<h2><span class=\"ez-toc-section\" id=\"looking-to-the-future\"><\/span>Looking to the future<span class=\"ez-toc-section-end\"><\/span><\/h2>\n<p><span style=\"font-weight: 400;\">MT glossaries are a simple and effective way to increase machine translation output quality. This is especially true for:<\/span><\/p>\n<ul>\n<li style=\"font-weight: 400;\" aria-level=\"1\"><span style=\"font-weight: 400;\">Domains with low-frequency terms of translation memories that aren\u2019t very large or well-curated<\/span><\/li>\n<li style=\"font-weight: 400;\" aria-level=\"1\"><span style=\"font-weight: 400;\">Small to mid-sized companies without big enough datasets to use custom MT<\/span><\/li>\n<li style=\"font-weight: 400;\" aria-level=\"1\"><span style=\"font-weight: 400;\">Bigger companies that have compiled substantial amounts of terminology data over several years or decades\u2014the data isn\u2019t consistent or language or style best practices have evolved or changed<\/span><\/li>\n<\/ul>\n<p><span style=\"font-weight: 400;\">Nevertheless, MT glossaries come with limitations as well. At some point, an MT glossary can get so large that it can hinder localization managers who manage it\u2014regular updates may become a headache and have a higher risk of accidentally introducing errors.<\/span><\/p>\n<p><span style=\"font-weight: 400;\">Equally important, most MT glossaries available on the market still have a search-and-replace functionality. With the continuous improvement in MT technology, engines are expected to get even better and let everyone use glossary terms with morphologically correct inflections.<\/span><\/p>\n<p><span style=\"font-weight: 400;\">To make the most of their machine translation efforts, localization managers should always prioritize their needs and available resources before deciding if custom machine translation glossaries are right for their use case.<\/span><\/p>\n\t\t<\/div>\n\t<\/div>\n<\/div>\n\n\n\n<div id=\"acf\/blog-cta-block_640cf203ca17b\" class=\"pxblock pxblock--blog-cta bg--green image--orientation-square\">\n\t<div class=\"block-container\">\n\t\t\t\t<div class=\"content\">\n\t\t\t<p class=\"h4\" style=\"text-align: center;\">Unlock the power of machine translation<\/p>\n<p class=\"small\" style=\"text-align: center;\">Discover advanced machine translation management features within our enterprise-ready TMS <span style=\"font-weight: 400;\">and create new business opportunities worldwide more quickly and efficiently.<\/span><\/p>\n<p style=\"text-align: center;\"><a class=\"btn btn--outline\" href=\"https:\/\/phrase.com\/solutions\/machine-translation\/\">Explore solutions<\/a><\/p>\n\t\t<\/div>\n\t<\/div>\n<\/div>\n","protected":false},"excerpt":{"rendered":"<p>Using machine translation glossaries is one of the simplest ways to customize machine translation (MT). Learn how to leverage them to improve your MT output in the long run.<\/p>\n","protected":false},"author":61,"featured_media":2602,"comment_status":"open","ping_status":"open","sticky":false,"template":"","format":"standard","meta":{"_acf_changed":false,"_stopmodifiedupdate":true,"_modified_date":"","_searchwp_excluded":"","footnotes":""},"categories":[41],"class_list":["post-5451","post","type-post","status-publish","format-standard","has-post-thumbnail","hentry","category-machine-translation"],"acf":[],"_links":{"self":[{"href":"https:\/\/phrase.com\/wp-json\/wp\/v2\/posts\/5451"}],"collection":[{"href":"https:\/\/phrase.com\/wp-json\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/phrase.com\/wp-json\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/phrase.com\/wp-json\/wp\/v2\/users\/61"}],"replies":[{"embeddable":true,"href":"https:\/\/phrase.com\/wp-json\/wp\/v2\/comments?post=5451"}],"version-history":[{"count":28,"href":"https:\/\/phrase.com\/wp-json\/wp\/v2\/posts\/5451\/revisions"}],"predecessor-version":[{"id":86263,"href":"https:\/\/phrase.com\/wp-json\/wp\/v2\/posts\/5451\/revisions\/86263"}],"wp:featuredmedia":[{"embeddable":true,"href":"https:\/\/phrase.com\/wp-json\/wp\/v2\/media\/2602"}],"wp:attachment":[{"href":"https:\/\/phrase.com\/wp-json\/wp\/v2\/media?parent=5451"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/phrase.com\/wp-json\/wp\/v2\/categories?post=5451"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}