Structured prediction

Structured prediction is an umbrella term for tasks that involve predicting structured outputs, rather than individual values. This unit covers two such tasks: sequence labelling, the task of mapping an input sequence to an output sequence, and dependency parsing, the task of mapping a sentence to a representation of its syntactic structure in the form of a dependency tree. The lectures introduce several technical approaches and concrete algorithms for these tasks.

Video lectures

Section	Title
4.01	Introduction to sequence labelling
4.02	Approaches to sequence labelling
4.03	The Viterbi algorithm
4.04	Introduction to dependency parsing
4.05	The arc-standard algorithm
4.06	Neural architectures for dependency parsing

Reading

• Eisenstein (2019), chapters 7–8, sections 2.3.1–2.3.2
• Eisenstein (2019), chapter 11