
Abstract: Understanding the questions posed by instructors and students alike plays an important role in the development of educational technology applications. In this intermediate level workshop, you will learn to apply NLP to one piece of this real-world problem by building a model to predict the type of answer (e.g. entity, description, number, etc.) a question elicits. Specifically, you will learn to:
1. Perform preprocessing, normalization, and exploratory analysis on a question dataset,
2. Identify salient linguistic features of natural language questions, and
3. Experiment with different feature sets and models to predict the answer type.
The concepts will be taught using popular NLP and ML packages like SpaCy, Scikit Learn, and Tensorflow.
The workshop will be structured as “reverse classroom” based laboratory exercises that have proven to be engaging and effective learning devices. Knowledgeable facilitators will help students learn the material and extrapolate to custom real world situations. Our team of machine learning engineers and data scientists will be your guides.
This workshop assumes familiarity with Jupyter notebooks and the basics of scientific packages like numPy and sciPy. We also assume some basic knowledge of machine learning and deep learning techniques like CNNs, LSTMs, etc. Reference materials will be provided to gain a better understanding of these techniques for interested attendees.
Bio: Coming Soon!

Curtis Giddings
Title
Senior Machine Learning Engineer | Course Hero
Category
beginner-w19 | intermediate-w19 | machine-learning-w19 | open-source-w19 | trainings-w19
