Apart from conventional sequence models such as HMMs, significant advancement has been made in the field of Neural Networks (or deep learning) based sequence models. Specifically, Recurrent Neural Networks (RNNs) have empirically proven to outperform many conventional sequence models for tasks such as POS tagging, entity recognition, dependency parsing etc.
Though you’ll learn RNNs in detail later in the Neural Network course, this segment will give you a brief overview of how you can build POS taggers using RNNs.
You will study RNNs in much more detail in the Neural Networks course.