Zenaique
Topics
Practice
Browse
Reference
Challenges
Pricing
Search…
⌘K
Topics
/
Tokenization
/
Word Boundary
Word Boundary
Subtopic
3 questions
Questions tagged with Word Boundary — part of Tokenization.
Format
Difficulty
Role
Experience
Companies
Sort
Newest
Quality
Difficulty ↑
Difficulty ↓
Questions
Why does SentencePiece prepend a special space symbol (▁) to tokens, and what would break without it?
Short Answer
Hard
·
Qual 4.0
Google
What interpretability and downstream task concerns arise from allowing cross-word boundary merges in BoundlessBPE?
Short Answer
Hard
·
Qual 4.0
What constraint does BoundlessBPE relax, and what improvement does it yield?
Flashcard
Hard
·
Qual 4.0