Unverified50% confidenceFactExact time
BPE 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
1
Sources
50%
Confidence
Long-term
Relevance
7/6/2026
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83% 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.74% similarVerifiedThe BPE algorithm originates from the field of data compression and builds a vocabulary by iteratively merging high-frequency character pairs.73% similarVerifiedModern LLMs generally use BPE (Byte Pair Encoding) or WordPiece algorithms for tokenization.72% similarVerifiedBPE（Byte Pair Encoding）是大语言模型使用的Token化算法，通过统计训练语料中字符对的共现频率迭代合并最常见的字符组合72% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/113295API
curl https://kongchang.com/api/v1/knowledge/claims/113295MCP
get_claim(id=113295)