Introduction Sentence embedding models like Sentence-BERT [1] have become indispensable tools in working with sentence-level data in multiple areas like semantic search, summarization, question answering, and many more. The strength of these models lies in their ability to assign semantically meaningful representations to sentences directly, because of the way they were…

How can we make AI more accessible and interesting for non-experts? Whenever developers want to hash passwords in a database they just use a hashing library designed for this task which abstracts all the hashing math away from them. When a programmer wants to perform some kind of I/O operation…

In this third part of the blog we will be looking at the actual LSTM model and see the results! In the previous part we prepared our card texts for modelling: we created three-dimensional NumPy arrays with (batch_size, length_of_sequence, number_features) shape. In this part, we will first create the model…

In this second part of the blog we will be looking at how to pre-process the textual data for modelling . Next part will focus on the actual deep learning stuff! In part 1 we “spoke” to the Hearthstone API to get card information. What we got was a bunch…

In this first part of the blog I will give a small introduction to the idea and will show how to get the data to start with this project. Next parts will focus on data pre-processing and modelling. A while ago I attended a little talk about “I, Robot”, the…