Hey, is there an award for #1 MOST SUBSCRIBED IRANIAN YOUTUBER?!
Well I'm also Canadian, but I won't win in that category...
Also YouTube is blocked in Iran so a lot of talents don't get to show, which is unfair!
BUT HAY I'M #1 ANYWAY... at least for now... @YouTube
Our new-ish, neural, pure Python stanfordnlp package provides grammatical analyses of sentences in over 50 human languages! https://t.co/p6MhHyHLC2 Version 0.2.0 brought sensibly small model sizes and an improved lemmatizer. Try it out: pip install stanfordnlp
Nice blog post titled "The Quiet Semi-Supervised Revolution" by Vincent Vanhoucke. It discusses two related works by the Google Brain team: Unsupervised Data Augmentation and MixMatch.
https://t.co/7nEFUgX8a1
I expected the Transformer-based BERT models to be bad on syntax-sensitive dependencies, compared to LSTM-based models.
So I run a few experiments. I was mistaken, they actually perform *very well*.
More details in this tech report: https://t.co/6hV9YoOvN8
Text books are great, but for the latest research you have to read research papers. Be aware that conclusions are based only on one person's view and may never make it into a text book. Reading a research paper requires a critical dialogue. Here is how: https://t.co/GEIXjROTSI