Photo by Sam Power on Unsplash The Apex project from NVIDIA is touted as a PyTorch extension that let developers do mixed precision and distributed training “with 4 or fewer line changes to the existing code”. It’s been out for a while (circa June 2018) and seems to be well received (huggingface/pytorch-pretrained-BERT uses Apex to do 16-bit training). So I decided to give it a try. This post documents what I’ve learned. ...
Photo by Steven Wei on Unsplash Introduction Previously I’ve demonstrated how to use pretrained BERT model to create a similarity measure between two documents in this post: News Topic Similarity Measure using Pretrained BERT Model. However, to find similar entries to* N* documents in corpus A of size M, we need to run NM* feed-forwards. A more efficient and widely used method is to use neural networks to generate sentence/document embeddings, and calculate cosine similarity scores between these embeddings. ...
credit In this post we establish a topic similarity measure among the news articles collected from the New York Times RSS feeds. The main purpose is to familiarized ourselves with the (PyTorch) BERT implementation and pretrained model(s). What is BERT? BERT stands for Bidirectional Encoder Representations from Transformers. It comes from a paper published by Google AI Language in 2018[1]. It is based on the idea that fine-tuning a pretrained language model can help the model achieve better results in the downstream tasks[2][3]. ...
Photo Credit Tables can be an effective way of communicating data. Though not as powerful in telling stories as charts, by cramming a lot of numbers into a limited space, tables can provide readers with accurate and potentially useful information which readers can interpret in their own ways. I’ve come across this new R package gt (Easily generate information-rich, publication-quality tables from R) and decided to give it a try. ...
Photo Credit R is awesome. In my opinion it’s the best (free) tool for telling great stories with data. My first post on Medium was about R. Although what I wrote here mostly involves Python, I still try to get back to R from time to time. I briefly mentioned my preferred R setup in this previous post “Analyzing Tweets with R” (in “R tips” section), which includes _Microsoft R Open _(MRO) and the checkpoint package. Unfortunately, checkpoint doesn’t work well with RStudio, and some weird issues with MRO become more and more annoying to me. Therefore I decided to find a new setup that can work more smoothly and reliably. After some trial and error, here is a configuration that I ended up most satisfied with: ...