This page introduces you to statistical parsing. We build on what we described in the previous lecture. We extend Context-Free Grammars to the probabilistic setting (i.e. Probabilistic CFGs), discuss maximum-likelihood estimation of PCFGs and extend CKY to support PCFGs. We discuss ways of evaluating quality of syntactic parsers. The basic PCFGs parser is not an accurate parsing model, so we introduce several techniques (some of them very simple) which can greatly boost its performance.
Please do the required reading, and attempt the quiz. If there is anything you don't understand, then please ask questions in the lecture or on piazza.
Slides and required reading
Reading: Section 14.1 - 14.5, 14.7 in J&M, 2nd edition.
Quiz 15: statistical parsing
These questions are designed to test your understanding of the above course content; doing this quiz does not contribute to your overall grade. Some questions require a text answer. You can ask for formative feedback on these from your tutor or on piazza. Other questions are multiple choice or they require a numeric answer: you will get immediate feedback for these. Please don't attempt this quiz until you have acquainted yourself with this lecture and the required reading.
You must be logged onto Learn to do this quiz.