<?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>Linguistics on Utkarsh Garg</title>
    <link>/tags/linguistics/</link>
    <description>Recent content in Linguistics on Utkarsh Garg</description>
    <generator>Hugo -- 0.151.2</generator>
    <language>en-us</language>
    <lastBuildDate>Tue, 26 May 2026 00:00:00 +0000</lastBuildDate>
    <atom:link href="/tags/linguistics/index.xml" rel="self" type="application/rss+xml" />
    <item>
      <title>Word Translation Without Parallel Data: A Beautiful Application of GANs and Linear Algebra</title>
      <link>/posts/word-translation-without-parallel-data-a-beautiful-application-of-gans-and-linear-algebra/</link>
      <pubDate>Tue, 26 May 2026 00:00:00 +0000</pubDate>
      <guid>/posts/word-translation-without-parallel-data-a-beautiful-application-of-gans-and-linear-algebra/</guid>
      <description>Three beauties meet in this paper. Words in one language end up internally aligned by meaning. For languages with shared structure, that arrangement is shaped almost the same way across both. A GAN and an SVD recover the rotation between them, strongly for close pairs, weakly for distant ones, with no parallel text.</description>
    </item>
  </channel>
</rss>
