In the last lecture we discussed probabilistic context free grammars. In this folder, we start by discussing how syntactic parsers can be evaluated. We see that the 'vanilla' PCFGs yield relatively weak statistical parsers. We discuss sources of these weaknesses, and introduce you to different ways how these parsers can be improved. Interestingly, we are still able to use the algorithm we discussed last time (CKY).
- lecture recordings and slides
- some required reading from Jurafsky and Martin
- a quiz that tests your understanding of the material presented here.
Lecture slides and reading
Readings: J&M Edition 2, sections 14.7, 14.4, 14.5.
Quiz 16: Beyond vanilla PCFGs
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.