This page introduces you to neural network (NN) classification methods for NLP. We start this section by recapping the logistic regression and then introduce a more powerful neural classification method (convolutional neural networks, CNN). We study what CNNs capture in their features, and their limitations.
The page contains slides, a quiz, and required reading.
Recommended Reading and Slides
Watch the recorded lecture for animations, they are not visible in pdf
Recommended reading: Jurafsky and Martin, 3rd edition (online), chapter 7. Note though that the CNNs are not covered in J & M
Optionally: study word embeddings and text classification sections in Lena Voita's NLP course:
Quiz 23: NN Text Classifiers
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.