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.
This is the second post of my series about understanding text datasets. Here we use the named entities to get some information about our data set.
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.
Once named entities have been identified in a text, we then want to extract the relations that exist between them. As indicated earlier, we will typically be looking for relations between specified types of named entity. I covered named entity… Continue Reading →
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.
In the last post, I introduced the U-Net model for segmenting salt depots in seismic images. This time, we will see how to improve the model by data augmentation and especially test time augmentation (TTA). You will learn how to… Continue Reading →
Today I’m going to write about a kaggle competition I started working on recently. I will show you how to approach the problem using the U-Net neural model architecture in keras. In the TGS Salt Identification Challenge, you are asked… Continue Reading →
This is the sixth post in my series about named entity recognition. This time I’m going to show you some cutting edge stuff. We will use a residual LSTM network together with ELMo embeddings, developed at Allen NLP. You will learn how to wrap a tensorflow hub pre-trained model to work with keras. The resulting model with give you state-of-the-art performance on the named entity recognition task.