手法を比較

	BERT埋め込み	テキスト含意
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	2019	—
提唱者	Devlin, Chang, Lee & Toutanova (Google AI)	—
種類	Contextual transformer text-representation method	NLP sentence-pair classification task
原典	Devlin, J., Chang, M.-W., Lee, K. & Toutanova, K. (2019). BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding. NAACL-HLT, 4171-4186.	Dagan, I., Glickman, O. & Magnini, B. (2006). The PASCAL Recognising Textual Entailment Challenge.
別名	contextual embeddings, transformer embeddings, BERT Tabanlı Metin Gömülmeleri	natural language inference, NLI, recognising textual entailment, RTE
関連	4	4
概要	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.	Textual entailment, also known as natural language inference (NLI), is the natural-language-processing task of deciding whether one piece of text (the premise) entails a second piece of text (the hypothesis), contradicts it, or is neutral with respect to it. Formalised by the PASCAL Recognising Textual Entailment Challenge (Dagan, Glickman & Magnini, 2006) and broadened by the MultiNLI corpus (Williams, Nangia & Bowman, 2018), it underpins question answering and fact-verification pipelines.