Over the last two years, the Natural Language Processing community has witnessed an acceleration in progress on a wide range of different tasks and applications. 🚀 This progress was enabled by a shift of paradigm in the way we classically build an NLP system: for a long time, we used pre-trained word embeddings such as word2vec or GloVe to initialize the first layer of a neural network, followed by a task-specific architecture that is trained in a supervised way using a single dataset.
Recently, several works demonstrated that we can learn hierarchical contextualized representations on web-scale datasets 📖 leveraging unsupervised (or self-supervised) signals such as language modeling and transfer this pre-training to downstream tasks (Transfer Learning).Excitingly, this shift led to significant advances on a wide range of downstream applications ranging from Question Answering, to Natural Language Inference through Syntactic Parsing…
“Which papers can I read to catch up with the latest trends in modern NLP?”
Read More
Monthly Archives: June 2019
How DevOps Drives Analytics Operationalization and Monetization
I recently wrote a blog “Interweaving Design Thinking and Data Science to Unleash Economic V…” that discussed the power of interweaving Design Thinking and Data Science to make our analytic efforts more effective. Our approach was validated by a recentMcKinsey article titled “Fusing data and design to supercharge innovation” that stated:
“While many organizations are investing in data and design capabilities, only those that tightly weave these disciplines together will unlock their full benefits.”
I even developed some Data Science playing cards that one could use to help guide this Design Thinking-Data Science interweaving process. Read More
On YouTube’s Digital Playground, an Open Gate for Pedophiles
Christiane C. didn’t think anything of it when her 10-year-old daughter and a friend uploaded a video of themselves playing in a backyard pool.
“The video is innocent, it’s not a big deal,” said Christiane, who lives in a Rio de Janeiro suburb.
XA few days later, her daughter shared exciting news: The video had thousands of views. Before long, it had ticked up to 400,000 — a staggering number for a video of a child in a two-piece bathing suit with her friend.
“I saw the video again and I got scared by the number of views,” Christiane said.
She had reason to be. Read More
Twitter acquires Fabula AI, a machine learning startup that helps spot fake news
Twitter has acquired Fabula AI, a London-based startup that uses machine learning (ML) to help detect the spread of misinformation online.
Terms of the deal were not disclosed, but the acquisition will underpin a research group at Twitter led by Sandeep Pandey that will work toward finding new ways to leverage machine learning across natural language processing (NLP), recommendations systems, reinforcement learning, and graph deep learning. The group will also address ML ethics. Read More
DIY Facial Recognition for Porn Is a Dystopian Disaster
Someone posting on Chinese social network Weibo claims to have used facial recognition to cross-reference women’s photos on social media with faces pulled from videos on adult platforms like Pornhub.
In a Monday post on Weibo, the user, who says he’s based in Germany, claimed to have “successfully identified more than 100,000 young ladies” in the adult industry “on a global scale.”
To be clear, the user has posted no proof that he’s actually been able to do this, and hasn’t published any code, databases, or anything else besides an empty GitLab page to verify this is real. When Motherboard contacted the user over Weibo chat, he said they will release “database schema” and “technical details” next week, and did not comment further. Read More
The Collapsing Crime Rates of the ’90s Might Have Been Driven by Cellphones
It’s practically an American pastime to blame cellphones for all sorts of societal problems, from distracted parents to faltering democracies. But the devices might have also delivered a social silver lining: a de-escalation of the gang turf wars that tore up cities in the 1980s.
The intriguing new theory suggests that the arrival of mobile phones made holding territory less important, which reduced intergang conflict and lowered profits from drug sales. Read More
Imagining Life as a Stack of Mental States
Contrary to what your intuition may believe, looking forward to playing a tennis match on Sunday afternoon isn’t really about the tennis match at all.
What makes your nightly ritual of blanket-slippers-tea-kindle special hasn’t got much to do with the activity of reading of all.
An overnight mountain climbing trip on the weekend offers something more than an arduous trek up unforgiving soil.
Your obsession with that local Thai joint is thanks to something more fundamentally true than how good their green curry sauce is.
Layered imperceptibly beneath all the above activities is a cardinal fact. A necessary truth, one ubiquitous to all human beings and applicable to every possible (un)pleasurable activity. A truth that shapes decision-making and the design of one’s lifestyle.
Every action, activity, hobby, or ritual is nothing more than the pursuit of a certain mental state. Read More
Fake videos of real people — and how to spot them
Deepfakes are getting better, but they're still easy to spot
LAST WEEK, MONA Lisa smiled. A big, wide smile, followed by what appeared to be a laugh and the silent mouthing of words that could only be an answer to the mystery that had beguiled her viewers for centuries.
A great many people were unnerved.
Mona’s “living portrait,” along with likenesses of Marilyn Monroe, Salvador Dali, and others, demonstrated the latest technology in deepfakes—seemingly realistic media generated using machine learning. Developed by researchers at Samsung’s AI lab in Moscow, the portraits display a new method to create credible videos from a single image. With just a few photographs of real faces, the results improve dramatically, producing what the authors describe as “photorealistic talking heads.” The researchers (creepily) call the result “puppeteering,” a reference to how invisible strings seem to manipulate the targeted face. And yes, it could, in theory, be used to animate your Facebook profile photo. But don’t freak out about having strings maliciously pulling your visage yet. Read More
AI-Assisted Fake Porn Is Here and We’re All F***ed
There’s a video of Gal Gadot having sex with her stepbrother on the internet. But it’s not really Gadot’s body, and it’s barely her own face. It’s an approximation, face-swapped to look like she’s performing in an existing incest-themed porn video.
The video was created with a machine learning algorithm, using easily accessible materials and open-source code that anyone with a working knowledge of deep learning algorithms could put together. Read More
Rick's Cafe AI 