Track 4 · Path · 5 explainers
NLP II: Language Models
Classification, seq2seq, NER, and language modeling with BERT
- 1
Text Classification & Sentiment
Teach a model to assign labels to text — from spam detection to sentiment analysis
- 2
Seq2Seq & Beam Search
Encode an input sequence and decode an output — the architecture behind translation
- 3
Named Entity Recognition
Identify and classify named entities — people, places, organizations — in running text
- 4
Language Modeling
Predict the next token — the objective that powers GPT, BERT, and modern NLP
- 5
BERT & Masked Language Modeling
Mask a word, predict it from both sides — how BERT learns deep bidirectional representations