<?xml version="1.0" encoding="utf-8" standalone="yes"?>
<rss version="2.0" xmlns:atom="http://www.w3.org/2005/Atom" xmlns:content="http://purl.org/rss/1.0/modules/content/">
  <channel>
    <title>Python on Localization Times</title>
    <link>https://localizationtimes.com/tags/python/</link>
    <description>Recent content in Python on Localization Times</description>
    <image>
      <title>Localization Times</title>
      <url>https://localizationtimes.com/%3Clink%20or%20path%20of%20image%20for%20opengraph,%20twitter-cards%3E</url>
      <link>https://localizationtimes.com/%3Clink%20or%20path%20of%20image%20for%20opengraph,%20twitter-cards%3E</link>
    </image>
    <generator>Hugo -- gohugo.io</generator>
    <language>en</language>
    <lastBuildDate>Sat, 05 Jul 2025 00:00:00 +0000</lastBuildDate><atom:link href="https://localizationtimes.com/tags/python/index.xml" rel="self" type="application/rss+xml" />
    <item>
      <title>Building Multilingual Glossaries With AI Support</title>
      <link>https://localizationtimes.com/blogs/building-glossaries-out-of-translation-memories/</link>
      <pubDate>Sat, 05 Jul 2025 00:00:00 +0000</pubDate>
      
      <guid>https://localizationtimes.com/blogs/building-glossaries-out-of-translation-memories/</guid>
      <description>Intro Recently, I was requested to find a way to build multilingual glossaries leveraging translation memory content. My client had translated an entire year of educational content using professional translators in seven different languages.
The challenge was bipartite:
Build all the required glossaries in a relatively short timeframe. Have a final human review step to validate the terms without breaking the bank. In other words, I had to create the glossary programmatically, using a pre-built list of English terms (source language), and then look for their translations, if any, in translation memories following an &amp;ldquo;exact match&amp;rdquo; approach.</description>
    </item>
    
  </channel>
</rss>
