Unverified50% confidenceFactExact time
WordPiece 是 BERT 使用的分词方案，与 BPE 类似但在合并策略上使用似然概率而非频率
1
Sources
50%
Confidence
Long-term
Relevance
8/7/2026
First Seen
Sources
Related Claims
VerifiedBPE的核心思路是从字符级别出发，反复合并出现频率最高的相邻字符对，直到词汇表达到预设大小73% similarVerifiedThe byte pair encoding (BPE) or WordPiece algorithms widely used in modern large models are essentially data-driven morphological segmentation methods.69% similarVerifiedModern LLMs generally use BPE (Byte Pair Encoding) or WordPiece algorithms for tokenization.69% similarUnverifiedBPE builds a shared vocabulary covering common roots and affixes by statistically counting the co-occurrence frequency of adjacent characters and iteratively merging high-frequency subword units.69% similarUnverifiedBPE 的核心思想是将高频共现的字符对反复合并为新的子词单元，能处理未登录词（OOV）同时保持词表规模可控68% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/705612API
curl https://kongchang.com/api/v1/knowledge/claims/705612MCP
get_claim(id=705612)