- What is a "word"?
- Morphology and morphological analysis
- Unsupervised subword segmentation
- Required Reading: Words and Transducers Jurafsky and Martin v2, Chapter 3, through section 3.9
- Required Reading: Text Normalization Jurafsky and Martin v3, Section 2.4
- Reference: SentencePiece (Kudo and Richardson 2018)
- Reference: Subword Reglarization ("unigram") (Kudo 2018)