Paper reading as a Cargo Cult

I have come across various people (including my past self) who meet up regularly to study papers and discuss them. This helps people bond over their common believes and interests, which I think is good, but in no way is this ever going to lead anyone to make scientific progress. In this post I’ll reason why this doesn’t help, and what I think we should do instead.

Research Skills

How can I become a better researcher? I grouped my thoughts on this into the four themes: Robustness, Sense of Direction, Execution, and Collaboration.

Why Rasa uses Sparse Layers in Transformers

Feed forward neural network layers are typically fully connected, or dense. But do we actually need to connect every input with every output? And if not, which inputs should we connect to which outputs? It turns out that in some of Rasa’s machine learning models we can randomly drop as much as 80% of all connections in feed forward layers throughout training and see their performance unaffected! Here we explore this in more detail.

Semantic Map Embeddings – Part II

In Part I we introduced semantic map embeddings and their properties. Now it’s time to see how we create those embeddings in an unsupervised way and how they might improve your NLU pipeline.

Semantic Map Embeddings – Part I

How do you convey the “meaning” of a word to a computer? Nowadays, the default answer to this question is “use a word embedding”. A typical word embedding, such as GloVe or Word2Vec, represents a given word as a real vector of a few hundred dimensions. But vectors are not the only form of representation. Here we explore semantic map embeddings as an alternative that has some interesting properties. Semantic map embeddings are easy to visualize, allow you to semantically compare single words with entire documents, and they are sparse and therefore might yield some performance boost.