In this 90-minute intermediate-level tutorial at PyData NYC we will introduce the concept of language modeling. In the first half we will explain language models, how they are used and why they are important in the domain of Natural Language Processing. In the second half we will be taking the attendees through a hands-on workshop where they will develop a language model based on a sample dataset and talk through some of the results and gotchas of working with language models.

To be able to run the Jupyter Notebook, please setup a Python environment with the dependencies specified in requirements.txt. Below we've included instructions on how to do so via conda.

conda create -n PyDataLM

source activate PyDataLM

conda install --file requirements.txt