Like the data-centric sibling of your favorite programming environment. It provides an easy-to-use interface for weak supervision as well as extensive data management, neural search and monitoring to ensure that the quality of your training data is as good as possible.
This won’t rid you of the need to manually label, but it’ll save you time in the process!
This is the first time I’ve heard of a reverse dictionary, but now that I have… so cool!
Opposite to a regular (forward) dictionary that provides definitions for query words, a reverse dictionary returns words semantically matching the query descriptions.
Ever had a word on the tip of your tongue and you Just. Can’t. Think of it?! Reverse dictionary!
That’s a big addition. Here’s what Hillary Juma (Common Voice’s community mgr) had to say about it:
Internet access is increasingly mediated through speech: Voice assistants and smart speakers give us directions, search for information, connect us to friends, used in assistive technology and much more. Yet this technology doesn’t work for millions of people. For example, neither Amazon’s Alexa, Apple’s Siri, nor Google Home support a single native African language.
By giving individuals the ability to share their speech, we can help ensure all communities have access to voice technology and the opportunity it unlocks.
What a great initiative! (I first heard about Common Voice on Practical AI.)
Texthero is a python package to work with text data efficiently. It empowers NLP developers with a tool to quickly understand any text-based dataset and it provides a solid pipeline to clean and represent text data, from zero to hero.
geared towards building search systems for any kind of data, including text, images, audio, video and many more. With the modular design & multi-layer abstraction, you can leverage the efficient patterns to build the system by parts, or chaining them into a Flow for an end-to-end experience.
Use OpenAI’s CLIP neural network to search inside YouTube videos. You can try it by running the notebook on Google Colab.
The README has a bunch of examples of things you might search for and the results you’d get back. (“The Transamerica Pyramid”, anyone?)
The author also has another related project where you can search Unsplash in like manner.
You may recall spaCy from this episode of Practical AI with its creators. If not, now’s a great time to introduce yourself to the project. 3.0 looks like a fantastic new release of the wildly popular NLP library. The list of new and improved things is too long for me to reproduce here, so go check it out for yourself.
There’s also three YouTube videos accompanying the release. That’s evidence of just how much effort and polish went in to this.
A formalization and continuation of this old Quora question about the most important research papers which all NLP students “should definitely read”.
If you say… “Hey, computer, play me some music” and then it starts playing you some music, there’s a number of things that have to have happened for that to come true.
Congrats to Clément and the Hugging Face team on this milestone!
The company first built a mobile app that let you chat with an artificial BFF, a sort of chatbot for bored teenagers. More recently, the startup released an open-source library for natural language processing applications. And that library has been massively successful.
The library mentioned is called Transformers, which is dubbed as ‘state-of-the-art Natural Language Processing for TensorFlow 2.0 and PyTorch.’
If any of these things ring a bell to you, it may be because Practical AI co-host Daniel Whitenack has been a huge supporter of Hugging Face for a long time and mentions them often on the show. We even had Clément on the show back in March of this year.
The goal of this repository is to build a comprehensive set of tools and examples that leverage recent advances in NLP algorithms, neural architectures, and distributed machine learning systems. The content is based on our past and potential future engagements with customers as well as collaboration with partners, researchers, and the open source community.
Kick Olivia’s tires (mixed metaphor alert!) by chatting with her online or start with the docs if you’d like to set up and host your own instance.
A little ingenuity paired with changes to ReCaptcha’s audio challenge allowed this hacker to create a Python ‘robot’ that defeats the ‘not a robot’ test with 90% accuracy. The approach is brilliant:
The code is small enough to grok in 5-10 minutes. Love it!
Flair allows you to apply our state-of-the-art natural language processing (NLP) models to your text, such as named entity recognition (NER), part-of-speech tagging (PoS), sense disambiguation and classification.
Multilingual and built on PyTorch.
Tobias Macey, on why this particular episode of Podcast.__init__ is worth a listen:
Tools for natural language processing are often limited in the number of human languages that they support. This was an interesting discussion on some of the work being done to make it easier to analyse text in multiple languages.
CV Compiler is an online resume analysis tool designed exclusively for software engineers.
The review technology scans for keywords from the world of programming and how they are used in the resume, relative to the best practices in the industry.
CV Compiler was built using Python with libraries NLTK and spaCy for tokenization, lemmatization, and POS-tagging.
The internal analysis engine for large datasets (resumes, job descriptions) was built upon a Seq2Seq model in TensorFlow.
