Approaches I
	• Unsupervised learning – lots of text as input (100M words or so) – wordform similarity and context similarities – stem classes or full decomposition – Promising performance on small subtasks • Yarowsky (2000) – Overall results (so far) are inadequate • Brent (1999), Goldsmith (2000) – 100M-word corpus is unrealistic for most languages where induction is needed
	2/5/01