Unverified60% confidenceFactExact time
BERT was released by Google in 2018, employing bidirectional pre-training that randomly masks 15% of words via a masked language model and requires their restoration.
2
Sources
60%
Confidence
Long-term
Relevance
7/23/2026
First Seen
Sources
词向量到大语言模型：AI 2.0技术演进全解析
Related Claims
VerifiedBERT was introduced by Google in 2018, a pioneering work in pre-trained language models, and was the first to adopt a bidirectional encoder architecture, setting new records on 11 NLP benchmark tests.85% similarVerifiedBERT was proposed by Google in 2018 and is a pre-trained language model based on the Transformer architecture.76% similarUnverifiedGoogle launched the BERT pre-trained language model in 2018 and the PaLM model with 540 billion parameters in 2022.75% similarUnverifiedSentencePiece由Google于2018年推出，支持无监督训练，无需预先进行空格分词，Google的T5、LLaMA等模型均采用其Unigram语言模型算法73% similarUnverifiedGoogle于2022年发布SayCan，让语言模型仅负责生成可行动作序列，具体执行交由预训练底层技能策略完成72% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/600459API
curl https://kongchang.com/api/v1/knowledge/claims/600459MCP
get_claim(id=600459)