NATURAL LANGUAGE PROCESSING (NLP) NEWSLETTER
The NLP Cypher | 08_22_21
Way back in February of 2020, someone Twitter posted they had FOIA’d the NSA aka National Security Agency. This actor, by the name ‘cupcake’ was able to retrieve a 400-page printout of their COMP 3321 training course (😂). It was OCR’d and uploaded to the cloud totaling 118MB of absolute FOIA madness of Python learning material courtesy of the Men in Black by the way of Fort Meade. Enjoy!
Don’t click on this 👇 and definitely don’t type “help” and press “enter”.
You can create your own commands within cmd.to platform. Also you can use them with custom domains. Easiest way to…
Windows 96 Bruh!
Want access your favorite OS of all time: Windows 96??
MIKESOFT WINDOWS 96
MIKESOFT presents you WINDOWS 96, the latest release of your favorite operating system!
A graph neural network paper list for real-world applications.
GitHub - chaitjo/awesome-efficient-gnn: Efficient Graph Neural Networks - a curated list of papers…
This is a curated list of must-read papers on efficient Graph Neural Networks and scalable Graph Representation…
How to Hack APIs in 2021
Best way to learn about securing the modern day API is to first learn how hackers crack them.
How to Hack APIs in 2021
Detectify Crowdsource is not your average bug bounty platform. It's an invite-only community of the best ethical…
Papers to Read 📚
This was the BIG paper released this week on what they term ‘Foundation Models’ 🥶
Bored Humans | 50 AI Demos to Play With
BoredHumans.com - Fun AI Programs You Can Use Online
We created 50 fun artificial intelligence (AI) pages you can use for free: Lyrics Generator - Our AI writes hit songs…
Build Your Own Transformer with JAX
Making a Transformer-VAE with JAX.
JAX allows writing simple code that runs efficiently on TPUs. These models can then operate on massive scales setting…
Few-Shot Question Answering with Splinter 😎
You can find it in HuggingFace’s Model Hub
Hackers Code in Morse Code
“Microsoft has disclosed details of an evasive year-long social engineering campaign wherein the operators kept changing their obfuscation and encryption mechanisms every 37 days on average, including relying on Morse code, in an attempt to cover their tracks and surreptitiously harvest user credentials.”
Hackers Spotted Using Morse Code in Phishing Attacks to Evade Detection
Hackers have been spotted using Morse Code in Phishing attacks to evade detection.
Repo Cypher 👨💻
A collection of recently released repos that caught our 👁
A multi-lingual benchmark dataset for mono-lingual retrieval in eleven typologically diverse languages, designed to evaluate ranking with learned dense representations.
GitHub - castorini/mr.tydi
Download | Baselines and Evaluation | Paper Mr. TyDi is a multi-lingual benchmark dataset built on TyDi, covering…
A system that leverages pretrained language model (PLM) to identify vulnerable software names and version in the public vulnerability reports.
GitHub - guanqun-yang/FewVulnerability: Detecting software vulnerability described public security…
This is the repository of the paper "Few-Sample Named Entity Recognition for Security Vulnerability Reports by…
Vision and Language Pretraining method via a structural knowledge masking (SKM) strategy.
GitHub - MILVLG/rosita: ROSITA: Enhancing Vision-and-Language Semantic Alignments via Cross- and…
Release the basic framework for ROSITA, including the pretrained base ROSITA model, as well as the scripts to run the…
Question Answering dataset for temporal reasoning. Examples below:
GitHub - wenhuchen/Time-Sensitive-QA: Code and Data for Paper "A Dataset for Answering…
The repo contains the dataset and code for paper Time-Sensitive Question Answering dataset. The dataset is collected by…
Every Sunday we do a weekly round-up of NLP news and code drops from researchers around the world.
For complete coverage, follow our Twitter: @Quantum_Stat