<?xml version="1.0" encoding="UTF-8"?><urlset xmlns="http://www.sitemaps.org/schemas/sitemap/0.9"><url><loc>https://mbrenndoerfer.com/writing/vocabulary-problem-subword-tokenization-challenges/the-vocabulary-problem</loc><lastmod>2026-01-28T18:31:54.000Z</lastmod></url><url><loc>https://mbrenndoerfer.com/writing/vocabulary-problem-subword-tokenization-challenges/the-out-of-vocabulary-problem</loc><lastmod>2026-01-28T18:31:54.000Z</lastmod></url><url><loc>https://mbrenndoerfer.com/writing/vocabulary-problem-subword-tokenization-challenges/vocabulary-size-explosion</loc><lastmod>2026-01-28T18:31:54.000Z</lastmod></url><url><loc>https://mbrenndoerfer.com/writing/vocabulary-problem-subword-tokenization-challenges/the-curse-of-rare-words</loc><lastmod>2026-01-28T18:31:54.000Z</lastmod></url><url><loc>https://mbrenndoerfer.com/writing/vocabulary-problem-subword-tokenization-challenges/morphological-productivity</loc><lastmod>2026-01-28T18:31:54.000Z</lastmod></url><url><loc>https://mbrenndoerfer.com/writing/vocabulary-problem-subword-tokenization-challenges/technical-and-domain-specific-text</loc><lastmod>2026-01-28T18:31:54.000Z</lastmod></url><url><loc>https://mbrenndoerfer.com/writing/vocabulary-problem-subword-tokenization-challenges/why-character-level-tokenization-doesn-t-fully-solve-it</loc><lastmod>2026-01-28T18:31:54.000Z</lastmod></url><url><loc>https://mbrenndoerfer.com/writing/vocabulary-problem-subword-tokenization-challenges/the-case-for-subword-units</loc><lastmod>2026-01-28T18:31:54.000Z</lastmod></url><url><loc>https://mbrenndoerfer.com/writing/vocabulary-problem-subword-tokenization-challenges/limitations-of-subword-tokenization</loc><lastmod>2026-01-28T18:31:54.000Z</lastmod></url><url><loc>https://mbrenndoerfer.com/writing/vocabulary-problem-subword-tokenization-challenges/looking-ahead-subword-tokenization-algorithms</loc><lastmod>2026-01-28T18:31:54.000Z</lastmod></url><url><loc>https://mbrenndoerfer.com/writing/vocabulary-problem-subword-tokenization-challenges/summary</loc><lastmod>2026-01-28T18:31:54.000Z</lastmod></url><url><loc>https://mbrenndoerfer.com/writing/vocabulary-problem-subword-tokenization-challenges/quiz</loc><lastmod>2026-01-28T18:31:54.000Z</lastmod></url></urlset>