{"id":104916,"date":"2025-04-30T15:42:41","date_gmt":"2025-04-30T13:42:41","guid":{"rendered":"https:\/\/phrase.com\/?p=104916"},"modified":"2025-04-30T15:42:45","modified_gmt":"2025-04-30T13:42:45","slug":"mastering-tm-and-phrase-qps-thresholds-for-localization-automation","status":"publish","type":"post","link":"https:\/\/phrase.com\/blog\/posts\/mastering-tm-and-phrase-qps-thresholds-for-localization-automation\/","title":{"rendered":"Mastering TM and Phrase QPS Thresholds for Localization Automation"},"content":{"rendered":"\n<p>Phrase TMS is a bit like a spaceship cockpit\u2013full of buttons, sliders, and settings. While many of these have only a minor effect on your localization workflow, a few can seriously help you alter the course of the ship. These include the TM (<a href=\"https:\/\/phrase.com\/blog\/posts\/translation-memory\/\">Translation Memory<\/a>) Threshold and. Phrase QPS (<a href=\"https:\/\/phrase.com\/phrase-quality-technologies\/quality-performance-score\/\">Phrase Quality Performance Score<\/a>) Threshold.<\/p>\n\n\n\n<p>These settings have a huge influence on what your pre-translation delivers and, in turn, how well you manage your Time, Cost, and Quality. If you want to level up your localization game, learning how to fine-tune these two \u201cdials\u201d is a must.<\/p>\n\n\n\n<p>To make fine-tuning these settings easier (and eliminate the guesswork), the Phrase team has been digging into the data. Over the past few quarters, we\u2019ve been tracking billions of data points tied to segment behavior, crunching the numbers, and turning those measurements into actionable insights. <\/p>\n\n\n\n<p>The goal? To help you set the perfect TM and Phrase QPS Thresholds with confidence.<\/p>\n\n\n\n<p>In the fall, we rolled out the TM Threshold dashboard along with smart recommendations. <\/p>\n\n\n\n<p>At the beginning of April, we added a powerful upgrade that lets you slice the data by commonly used project metadata like <em>Domain, Subdomain<\/em>, and <em>Target Locale<\/em>. And just this March, we followed it up with the Phrase QPS Insights dashboard, your new co-pilot for finding the right balance between savings and risks.<\/p>\n\n\n\n<div id=\"ez-toc-container\" class=\"ez-toc-v2_0_80 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\/mastering-tm-and-phrase-qps-thresholds-for-localization-automation\/#the-industry-has-taken-a-big-step-forward\" >The industry has taken a big step forward<\/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\/mastering-tm-and-phrase-qps-thresholds-for-localization-automation\/#tm-threshold-as-a-thermometer-for-automation\" >TM Threshold as a thermometer for automation<\/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\/mastering-tm-and-phrase-qps-thresholds-for-localization-automation\/#phrase-qps-threshold\" >Phrase QPS Threshold<\/a><ul class='ez-toc-list-level-3' ><li class='ez-toc-heading-level-3'><a class=\"ez-toc-link ez-toc-heading-4\" href=\"https:\/\/phrase.com\/blog\/posts\/mastering-tm-and-phrase-qps-thresholds-for-localization-automation\/#step-1-understand-how-mt-quality-affects-human-effort\" >Step 1: Understand how MT quality affects human effort<\/a><\/li><li class='ez-toc-page-1 ez-toc-heading-level-3'><a class=\"ez-toc-link ez-toc-heading-5\" href=\"https:\/\/phrase.com\/blog\/posts\/mastering-tm-and-phrase-qps-thresholds-for-localization-automation\/#step-2-explore-the-impact-of-lowering-your-phrase-qps-threshold\" >Step 2: Explore the impact of lowering your Phrase QPS Threshold<\/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\/mastering-tm-and-phrase-qps-thresholds-for-localization-automation\/#step-3-track-your-automation-progress-over-time\" >Step 3. Track your automation progress over time<\/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\/mastering-tm-and-phrase-qps-thresholds-for-localization-automation\/#turning-insights-into-actions\" >Turning insights into actions<\/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\/mastering-tm-and-phrase-qps-thresholds-for-localization-automation\/#want-to-take-it-even-further\" >Want to take it even further?<\/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\/mastering-tm-and-phrase-qps-thresholds-for-localization-automation\/#unlock-the-full-potential-of-your-localization-data\" >Unlock the full potential of your localization data<\/a><\/li><\/ul><\/nav><\/div>\n<h2 class=\"wp-block-heading\" id=\"h-the-industry-has-taken-a-big-step-forward\"><span class=\"ez-toc-section\" id=\"the-industry-has-taken-a-big-step-forward\"><\/span>The industry has taken a big step forward<span class=\"ez-toc-section-end\"><\/span><\/h2>\n\n\n\n<p>And yes, it\u2019s already making a difference. <\/p>\n\n\n\n<p>Before we rolled out the TM Threshold initiative, that setting hadn\u2019t budged in years. Most projects were stuck at an average threshold of <strong>76<\/strong> &#8211; low, and more importantly, completely flat. <\/p>\n\n\n\n<p>Even as machine translation steadily improved, the \u201chand-off\u201d point between TM and MT (Machine Translation) stayed the same. Loc teams kept leaning heavily on TM, even when MT could have delivered better results. <\/p>\n\n\n\n<p>But now, with real data and guidance in place, we\u2019re finally seeing that balance shift. For the first time, the average TM Threshold has crossed the 80 mark. It jumped a full 10 points, landing around <strong>86<\/strong>.&nbsp;<\/p>\n\n\n\n<figure class=\"wp-block-image size-full\"><img loading=\"lazy\" decoding=\"async\" width=\"1600\" height=\"996\" src=\"https:\/\/phrase.com\/wp-content\/uploads\/2025\/04\/1.png\" alt=\"TM Theshold graph\" class=\"wp-image-105122\" srcset=\"https:\/\/phrase.com\/wp-content\/uploads\/2025\/04\/1.png 1600w, https:\/\/phrase.com\/wp-content\/uploads\/2025\/04\/1-300x187.png 300w, https:\/\/phrase.com\/wp-content\/uploads\/2025\/04\/1-1024x637.png 1024w, https:\/\/phrase.com\/wp-content\/uploads\/2025\/04\/1-768x478.png 768w, https:\/\/phrase.com\/wp-content\/uploads\/2025\/04\/1-1536x956.png 1536w\" sizes=\"auto, (max-width: 1600px) 100vw, 1600px\" \/><\/figure>\n\n\n\n<p>That\u2019s a huge improvement, but it\u2019s just the beginning. The industry has taken a big step forward. Now, let\u2019s not stop halfway. There\u2019s still a lot of untapped potential in MT.<\/p>\n\n\n\n<p>Why does this bother me? Because fuzzy matches <em>always<\/em> need human review. And if you&#8217;re relying on them, you can forget about fully automating your translations. <\/p>\n\n\n\n<p>A TM can only serve up the translation of the most similar segment it\u2019s seen, so you know it\u2019s not a translation of your current segment. <\/p>\n\n\n\n<p>Take this example: last week, your TM stored a translation for <em>\u201cThe jury found the dependent guilty.\u201d<\/em> Today, a brand-new segment comes in: <em>\u201cThe jury found the defendant not guilty.\u201d<\/em> <\/p>\n\n\n\n<p>The fuzzy score will be high, but you absolutely want a linguist reviewing that. Otherwise, someone could end up doing time they don\u2019t deserve.<\/p>\n\n\n\n<h2 class=\"wp-block-heading\" id=\"h-tm-threshold-as-a-thermometer-for-automation\"><span class=\"ez-toc-section\" id=\"tm-threshold-as-a-thermometer-for-automation\"><\/span>TM Threshold as a thermometer for automation<span class=\"ez-toc-section-end\"><\/span><\/h2>\n\n\n\n<p>Here\u2019s the thing: MT doesn\u2019t come with that baggage. It always produces a complete translation, every time. You <em>can<\/em> choose to have humans review it, but you don\u2019t <em>have<\/em> to. <\/p>\n\n\n\n<p>That\u2019s what makes MT so powerful for automation. And that\u2019s why your TM Threshold setting is more than just a number; it\u2019s a reflection of your automation mindset. The higher it is, the more you\u2019re leaning into automation. <\/p>\n\n\n\n<p>I like to think of the TM Threshold as a thermometer for automation. If you\u2019re hanging out in the 70s, it\u2019s still pretty chilly. In the 80s? You\u2019re warming up for the automation game. Hit the 90s, and now we\u2019re talking. Anything above 95? That\u2019s pro-level; you\u2019re really letting MT do its thing.<\/p>\n\n\n\n<p>So open up your TM Threshold in Analytics and see where MT outperforms TM fuzzies. Where MT saves you valuable editing time.<\/p>\n\n\n\n<figure class=\"wp-block-image size-full\"><img loading=\"lazy\" decoding=\"async\" width=\"1338\" height=\"724\" src=\"https:\/\/phrase.com\/wp-content\/uploads\/2025\/04\/TM-match-category-1.png\" alt=\"TM match category graph\" class=\"wp-image-105130\" srcset=\"https:\/\/phrase.com\/wp-content\/uploads\/2025\/04\/TM-match-category-1.png 1338w, https:\/\/phrase.com\/wp-content\/uploads\/2025\/04\/TM-match-category-1-300x162.png 300w, https:\/\/phrase.com\/wp-content\/uploads\/2025\/04\/TM-match-category-1-1024x554.png 1024w, https:\/\/phrase.com\/wp-content\/uploads\/2025\/04\/TM-match-category-1-768x416.png 768w\" sizes=\"auto, (max-width: 1338px) 100vw, 1338px\" \/><\/figure>\n\n\n\n<h2 class=\"wp-block-heading\" id=\"h-phrase-qps-threshold\"><span class=\"ez-toc-section\" id=\"phrase-qps-threshold\"><\/span>Phrase QPS Threshold<span class=\"ez-toc-section-end\"><\/span><\/h2>\n\n\n\n<p>You can choose to have humans review MT output, but you don\u2019t have to. This is exactly where the Phrase <strong>QPS Threshold<\/strong> comes in. Phrase QPS estimates the quality of MT at the segment level, helping decide which segments are good enough to be auto-confirmed. But more about that next time. In other words, it\u2019s your smart filter for automation: catching low-quality translations before they slip through, and sparing your team from reviewing everything manually.<\/p>\n\n\n\n<p>The tricky part? Figuring out where to set that threshold. <\/p>\n\n\n\n<p>That\u2019s why, in March, we introduced <strong>the Phrase QPS Insights dashboard<\/strong>; a new tool to help you find the sweet spot between cost savings and quality risk.<\/p>\n\n\n\n<figure class=\"wp-block-image size-full\"><img loading=\"lazy\" decoding=\"async\" width=\"1600\" height=\"1449\" src=\"https:\/\/phrase.com\/wp-content\/uploads\/2025\/04\/QPS-insights.jpg\" alt=\"\" class=\"wp-image-105136\" srcset=\"https:\/\/phrase.com\/wp-content\/uploads\/2025\/04\/QPS-insights.jpg 1600w, https:\/\/phrase.com\/wp-content\/uploads\/2025\/04\/QPS-insights-300x272.jpg 300w, https:\/\/phrase.com\/wp-content\/uploads\/2025\/04\/QPS-insights-1024x927.jpg 1024w, https:\/\/phrase.com\/wp-content\/uploads\/2025\/04\/QPS-insights-768x696.jpg 768w, https:\/\/phrase.com\/wp-content\/uploads\/2025\/04\/QPS-insights-1536x1391.jpg 1536w\" sizes=\"auto, (max-width: 1600px) 100vw, 1600px\" \/><\/figure>\n\n\n\n<h3 class=\"wp-block-heading has-text-align-left\" id=\"h-step-1-understand-how-mt-quality-affects-human-effort\"><span class=\"ez-toc-section\" id=\"step-1-understand-how-mt-quality-affects-human-effort\"><\/span>Step 1: Understand how MT quality affects human effort<span class=\"ez-toc-section-end\"><\/span><\/h3>\n\n\n\n<p>Use the first 4 charts to explore how different Phrase QPS scores correlate with editing activity and effort.<\/p>\n\n\n\n<p>See where your segments fall on the Phrase QPS scale, how often linguists step in to make changes, and how much time they actually spend doing it. This is your starting point for understanding when MT is doing its job.<\/p>\n\n\n\n<ul class=\"wp-block-list wp-block-list\">\n<li><strong>Chart 1 <\/strong>shows the distribution of segment volumes based on their Phrase QPS score.<\/li>\n\n\n\n<li><strong>Chart 2<\/strong> shows the percentage of segments that were edited by linguists. Higher Phrase QPS scores are expected to have fewer edits.<\/li>\n\n\n\n<li><strong>Chart 3<\/strong> shows how much time linguists spend editing segments.<\/li>\n\n\n\n<li><strong>Chart 4<\/strong><em> <\/em>includes both edited and unedited segments (segments with 0 editing time). This provides a clearer picture of the overall effort spent on all processed segments, combining insights from the previous two charts.<\/li>\n<\/ul>\n\n\n\n<h3 class=\"wp-block-heading\" id=\"h-step-2-explore-the-impact-of-lowering-your-phrase-qps-threshold\"><span class=\"ez-toc-section\" id=\"step-2-explore-the-impact-of-lowering-your-phrase-qps-threshold\"><\/span>Step 2: Explore the impact of lowering your Phrase QPS Threshold<span class=\"ez-toc-section-end\"><\/span><\/h3>\n\n\n\n<p>See how adjusting the threshold can unlock automation and reduce manual work.<\/p>\n\n\n\n<p>Charts 5 and 6 help you estimate the payoff of lowering your Phrase QPS threshold &#8211; more auto-confirmed words and less editing time.\u00a0<\/p>\n\n\n\n<ul class=\"wp-block-list wp-block-list\">\n<li><strong>Chart 5<\/strong><em> <\/em>estimates the number of auto-confirmed words that won\u2019t require human verification if the Phrase QPS threshold is lowered. For example, if the Phrase QPS threshold decreases from 95 to 90, the average number of auto-approved words may increase from 950 to 1,750.<\/li>\n<\/ul>\n\n\n\n<figure class=\"wp-block-image size-full is-resized\"><img loading=\"lazy\" decoding=\"async\" width=\"512\" height=\"243\" src=\"https:\/\/phrase.com\/wp-content\/uploads\/2025\/04\/Phrase-QPS-insights.png\" alt=\"Phrase QPS insights chart\" class=\"wp-image-104945\" style=\"width:712px;height:auto\" srcset=\"https:\/\/phrase.com\/wp-content\/uploads\/2025\/04\/Phrase-QPS-insights.png 512w, https:\/\/phrase.com\/wp-content\/uploads\/2025\/04\/Phrase-QPS-insights-300x142.png 300w\" sizes=\"auto, (max-width: 512px) 100vw, 512px\" \/><\/figure>\n\n\n\n<ul class=\"wp-block-list wp-block-list\">\n<li><strong>Chart 6<\/strong> shows how much editing time could be saved if the Phrase QPS threshold is reduced.<\/li>\n<\/ul>\n\n\n\n<h3 class=\"wp-block-heading\" id=\"h-step-3-track-your-automation-progress-over-time\"><span class=\"ez-toc-section\" id=\"step-3-track-your-automation-progress-over-time\"><\/span>Step 3. Track your automation progress over time<span class=\"ez-toc-section-end\"><\/span><\/h3>\n\n\n\n<p>Measure how your strategy is paying off by watching the shift from edited to auto-confirmed MT segments.<\/p>\n\n\n\n<p>Chart 5 helps you keep an eye on long-term trends. As you tweak your Phrase QPS threshold and improve your MT setup, you should see fewer edits and more segments flying through untouched. It&#8217;s your progress report for automation maturity.<\/p>\n\n\n\n<h2 class=\"wp-block-heading\" id=\"h-turning-insights-into-actions\"><span class=\"ez-toc-section\" id=\"turning-insights-into-actions\"><\/span>Turning insights into actions<span class=\"ez-toc-section-end\"><\/span><\/h2>\n\n\n\n<p>Mastering TM and Phrase QPS Thresholds is about moving from guesswork to informed decision-making. With segment-level insights at your fingertips, you can fine-tune where automation makes sense, where it saves time, and where it still needs a human touch.\u00a0<\/p>\n\n\n\n<p>Fine-tuning these settings helps reduce manual work, improve consistency, and scale more effectively. It&#8217;s a shift toward localization that&#8217;s faster, leaner, and based on evidence\u2014not assumptions. <\/p>\n\n\n\n<p>The tools are there. The data is clear. Now it\u2019s about using them to work smarter, not harder.<\/p>\n\n\n\n<h2 class=\"wp-block-heading\" id=\"h-want-to-take-it-even-further\"><span class=\"ez-toc-section\" id=\"want-to-take-it-even-further\"><\/span>Want to take it even further?<span class=\"ez-toc-section-end\"><\/span><\/h2>\n\n\n\n<p>These insights are powered by segment-level metrics. With <a href=\"https:\/\/phrase.com\/phrase-data\/\"><strong>Phrase Data Premium<\/strong><\/a>, you get access to the raw, segment-level data behind it all. <\/p>\n\n\n\n<p>That means fully custom insights tailored to your workflows, languages, domains, and teams. If you\u2019re ready to make sharper, more strategic decisions, this is how you get there.<br><br><\/p>\n\n\n\n<div class=\"wp-block-columns is-style-default is-layout-flex wp-container-core-columns-is-layout-28f84493 wp-block-columns-is-layout-flex\">\n<div class=\"wp-block-column has-green-10-background-color has-background has-global-padding is-layout-constrained wp-container-core-column-is-layout-31a95166 wp-block-column-is-layout-constrained\" style=\"border-style:none;border-width:0px;padding-top:var(--wp--preset--spacing--45);padding-bottom:var(--wp--preset--spacing--45);flex-basis:100%\">\n<h2 class=\"wp-block-heading has-text-align-center\" id=\"h-unlock-the-full-potential-of-your-localization-data\"><span class=\"ez-toc-section\" id=\"unlock-the-full-potential-of-your-localization-data\"><\/span>Unlock the full potential of your localization data<span class=\"ez-toc-section-end\"><\/span><\/h2>\n\n\n\n<div class=\"wp-block-buttons is-content-justification-center is-layout-flex wp-container-core-buttons-is-layout-a89b3969 wp-block-buttons-is-layout-flex\">\n<div class=\"wp-block-button is-style-phrase-green-filled\"><a class=\"wp-block-button__link wp-element-button\" href=\"https:\/\/phrase.com\/phrase-data\/\">Discover Phrase Data<\/a><\/div>\n<\/div>\n<\/div>\n<\/div>\n","protected":false},"excerpt":{"rendered":"<p>\u201cYour threshold settings are more than just numbers; they are a reflection of your automation mindset.\u201d<\/p>\n","protected":false},"author":72,"featured_media":105152,"comment_status":"closed","ping_status":"closed","sticky":false,"template":"post-refresh-updated","format":"standard","meta":{"_acf_changed":false,"_stopmodifiedupdate":false,"_modified_date":"","_searchwp_excluded":"","episode_type":"","audio_file":"","cover_image":"","cover_image_id":"","duration":"","filesize":"","filesize_raw":"","date_recorded":"","explicit":"","block":"","itunes_episode_number":"","itunes_title":"","itunes_season_number":"","itunes_episode_type":"","footnotes":""},"categories":[41],"class_list":["post-104916","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\/104916","targetHints":{"allow":["GET"]}}],"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\/72"}],"replies":[{"embeddable":true,"href":"https:\/\/phrase.com\/wp-json\/wp\/v2\/comments?post=104916"}],"version-history":[{"count":20,"href":"https:\/\/phrase.com\/wp-json\/wp\/v2\/posts\/104916\/revisions"}],"predecessor-version":[{"id":105162,"href":"https:\/\/phrase.com\/wp-json\/wp\/v2\/posts\/104916\/revisions\/105162"}],"wp:featuredmedia":[{"embeddable":true,"href":"https:\/\/phrase.com\/wp-json\/wp\/v2\/media\/105152"}],"wp:attachment":[{"href":"https:\/\/phrase.com\/wp-json\/wp\/v2\/media?parent=104916"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/phrase.com\/wp-json\/wp\/v2\/categories?post=104916"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}