Abstract Part-of-speech (POS) induction is one of the most popular tasks in research on
unsupervised NLP. Many different methods have been proposed, yet comparisons are …

Informative computational modeling can be an invaluable tool for understanding syntactic
acquisition. In this chapter, I describe how modeling can be used to both formalize specific …

Learning is often accompanied by a subjective sense of confidence in one's knowledge, a
feeling of knowing what you know and how well you know it. Subjective confidence has …

Human language acquisition has been studied for centuries, but using computational
modeling for such studies is a relatively recent trend. However, computational approaches to …

Traditionally, it has generally been assumed that adult speakers are in possession of
syntactic categories such as NOUN (eg, boy, girl) and VERB (eg, see, dance). This chapter …

We define the crouching Dirichlet, hidden Markov model (CDHMM), an HMM for partof-
speech tagging which draws state prior distributions for each local document context. This …

Children learn a robust representation of lexical categories at a young age. We propose an
incremental model of this process which efficiently groups words into lexical categories …

Because language acquisition happens in stages, early language acquisition strategies
probably don't yield adult knowledge directly. Instead, they're more likely to provide …

Clustering is a central technique in NLP. Consequently, clustering evaluation is of great
importance. Many clustering algorithms are evaluated by their success in tagging corpus …

This thesis concentrates on two fields in natural language processing. The main contribution
of the thesis is in the field of morphology learning. Morphology is the study of how words are …