This time we have a look into the magnitude library, a feature-packed Python package for utilizing vector embeddings in machine learning models in a fast, efficient, and simple manner. We want to utilize the embeddings magnitude provides and use them in keras.
One of the latest milestones in pre-training and fine-tuning in natural language processing is the release of BERT. This is a new post in my NER series. I will show you how you can fine-tune the Bert model to do state-of-the art named entity recognition in pytorch.
This is the first post of my series about understanding text data sets. In practice, you often want and need to know, what is going on in your data. In this post we will focus on applying a Latent Dirichlet allocation (LDA) topic model to the “Quora Insincere Questions Classification” data set on kaggle.
An important part of every machine learning project is the proper evaluation of the performance of the system. In this post I will show you how evaluate sequence models with token-based labels. This way you can get a proper understanding of you sequence model performance.
Often in text classification, we use so called black-box classifiers. By black-box classifiers I mean a classification system where the internal workings are completly hidden from you. A famous example are deep neural nets, in text classification oftern recurrent or… Continue Reading →
In this post we will introduce multivariate adaptive regression splines model (MARS) using python. This is a regression model that can be seen as a non-parametric extension of the standard linear model.