Jun 24, 2022Member-onlyThe Fastest, Easiest Way to Access GDrive from Google ColabI’ve been a fan of Google Colab for quite some time. It’s super convenient, there’s no installation involved, plus you get free access to GPUs/TPUs, and it’s all backed up in the cloud. What more can you ask for. Did I mention it’s free? (Confession: I occasionally use Colab Pro…Google Colab2 min readGoogle Colab2 min read
Nov 8, 2021Member-onlyHow to Solve the New York Times Spelling Bee in an EmergencyThe New York Times Spelling Bee is a a deceptively simple game, but as millions of players have found out, this highly-addictive daily word puzzle is worse than cocaine. It’s so addictive, in fact, that some East Coast Spelling Bee junkies make sure to wake up every day at 3…Spelling Bee3 min readSpelling Bee3 min read
Published in Towards Data Science·Feb 8, 2021Member-onlyNLP Metrics Made Simple: The BLEU ScoreNatural language processing (NLP) has become a super-hot topic. One of the most successful applications of NLP is Machine Translation (MT) — the ability to automatically translate text from one language to another. …Bleu6 min readBleu6 min read
Nov 5, 2020Member-onlyHow to Enable Google Meet’s Background Blur on the Surface Pro XIn the escalating battle between online video-communication services, Google Meet recently introduced a beautiful Background Blur function to compete with Zoom’s backgrounds. Google Meet’s Blur function works great when you have the right hardware and software. So, I recently tried to use Background Blur on a Surface Pro X, Microsoft’s…Surface Pro2 min readSurface Pro2 min read
Published in Towards Data Science·Sep 29, 2020Member-onlyThe Magic of Reactive SupervisionHigh Quality NLP Data Labeling Using Social Media Interactions — This story is based on the paper “Reactive Supervision: A New Method for Collecting Sarcasm Data” by Shmueli et al., EMNLP 2020. Machine learning models are as good as the quality of their training data. Noisy, inaccurate labels can lead to disastrous predictions. But getting sufficient data with high quality…NLP8 min readNLP8 min read
Published in Code Like A Girl·May 26, 2020Member-onlyThe Google Doodle Paradox: Be Careful What You MeasureThose nifty little Google Doodles that you often see on Google’s home page may seem like nothing but harmless fun, right? I decided to dig a little deeper, and found a captivating tale that combines art and data with gender and change. …Gender Equality9 min readGender Equality9 min read
Published in The Startup·May 7, 2020Member-onlyThis Secret Feature in Google Drive Lets You Add a File to Multiple FoldersThis is a very short post about a rather hidden Google Drive feature that is very handy: adding a file to more than one folder. I use it regularly to organize my files on Google Drive, and found it to be very useful. I admit: calling this feature a “secret”…Google Drive3 min readGoogle Drive3 min read
Published in Towards Data Science·May 1, 2020Member-onlyDouble Your Google Colab RAM in 10 Seconds Using a Tiny Line of CodeGoogle Colab is an incredible tool. It can be described in three words: Python in the Cloud. OK, four words. But the important thing is, you don’t need to worry about the Python version (Colab has both Python 2 and Python 3), or about downloading modules (the most popular ones…Colab4 min readColab4 min read
Published in Towards Data Science·Dec 18, 2019Member-onlyMulti-Class Metrics Made Simple, Part III: the Kappa Score (aka Cohen’s Kappa Coefficient)Measure The Agreement Between Predicted and True Values — In my previous Multi-Class Metrics Made Simple posts, I wrote about Precision and Recall, as well as the F1-score. I received encouraging feedback from many readers. So first, thank you! In this post, I write about another popular measure: the kappa score. …Machine Learning6 min readMachine Learning6 min read
Published in Towards Data Science·Nov 22, 2019Member-onlyMatthews Correlation Coefficient is The Best Classification Metric You’ve Never Heard OfCongratulations! You’ve built a binary classifier —a fancy-schmancy neural network using 128 GPUs with their dedicated power station, or perhaps a robust logistic regression model that runs on your good old ThinkPad. …Machine Learning7 min readMachine Learning7 min read
