手法を比較

	GloVe埋め込み	BERT埋め込み
分野	テキストマイニング	テキストマイニング
系統	Process / pipeline	Process / pipeline
提唱年	2014	2019
提唱者	Pennington, Socher & Manning	Devlin, Chang, Lee & Toutanova (Google AI)
種類	Static word-embedding model	Contextual transformer text-representation method
原典	Pennington, J., Socher, R. & Manning, C. D. (2014). GloVe: Global Vectors for Word Representation. EMNLP.	Devlin, J., Chang, M.-W., Lee, K. & Toutanova, K. (2019). BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding. NAACL-HLT, 4171-4186.
別名	GloVe, global vectors, GloVe Kelime Gömülmeleri	contextual embeddings, transformer embeddings, BERT Tabanlı Metin Gömülmeleri
関連	3	4
概要	GloVe (Global Vectors for Word Representation) is a static word-embedding model introduced by Pennington, Socher and Manning (2014) that learns word vectors directly from global word-word co-occurrence statistics gathered across an entire corpus. The resulting vectors place semantically related words close together and perform strongly on semantic analogy tasks.	BERT-based text embeddings, introduced by Devlin and colleagues at Google AI in 2019, turn text into context-sensitive dense vectors using a bidirectional Transformer encoder. Because the meaning of a word shifts with its context, BERT produces richer representations than static methods such as Word2Vec or topic models like LDA.