BERT (2018): bidirectional pretraining that unified NLP
Devlin et al. released BERT, popularizing language-model fine-tuning via masked LM and next sentence prediction.
4 articles
NLP
Index of editorial tags and filtered coverage.
Word2Vec (2013): the algebra of words
Tomas Mikolov and Google colleagues released Word2Vec, popularizing dense embeddings and king–man+woman≈queen analogies.
Statistical NLP at IBM: translation leaves pure rules behind
IBM’s statistical machine-translation models based on alignments marked NLP’s data-driven turn.
SHRDLU (1970): natural language in a blocks world
Terry Winograd’s SHRDLU combined parsing, planning, and a micro-world to converse about manipulable blocks.