Hey there, you just received the monthly depends-on-the-definition newsletter for April 2020. I hope you are safe and sound in these difficult times. Maybe this issue can give you some new inputs for your work.
The paper "Context-Aware Document Term Weighting for Ad-Hoc Search" proposes a context-aware document term weighting framework for document indexing and retrieval. It first estimates the semantic importance of a term in the context of each passage by leveraging BERT. These fine-grained term weights are then aggregated into a document-level BOW representation.
Tips & Tricks
A library that tries help you to understand. "What lies in word embeddings?"
In recent years, there has been an increasing interest in open-ended language generation thanks to the rise of large transformer-based language models trained on millions of webpages. This blog post gives a brief overview of different decoding strategies and more importantly shows how you can implement them with very little effort using the popular transformers library!