Named Entity Recognition with Pytorch Transformers

What if I told you that you can develop a state-of-the-art Natural Language Processing (NLP) system to do Language Generation, Question Answering or Named Entity Recognition with only few line […]

Querying text annotations at scale with SPARK

Whether you are analyzing textual data or building features from text, you will likely use text annotations. While many software libraries and material exist to annotate documents, querying these annotations […]

AI or not AI? Classifying ArXiv articles with BERT

Things are evolving faster and faster in the NLP world. We can’t go 6 months without someone releasing a new language representation model that breaks records on major downstream benchmarks. […]

Node2vec and arXiv data

Since its publication in 2016 by Aditya Grover and Jure Leskovec, Node2vec has become the go-to algorithm to easily compute embeddings for nodes in a graph/network. Working with embeddings has […]

Knowledge Graph Features and Explanation

Although latent feature models such as TransE are demonstrating state-of-the-art performance in the task of link prediction in knowledge graphs, they act as a black box. Latent feature models rely […]

Translating Embeddings (TransE)

In this post I present Translating Embeddings (TransE), a method for the prediction of missing relationships in knowledge graphs. Rather than digging into the mathematics, I focus on presenting the […]