The model, a culmination of various automated and machine learning techniques, is being open-sourced to the research community.
Facebook is open-sourcing a new AI language model called M2M-100 that can translate between any pair among 100 languages. Of the 4,450 possible language combinations, it translates 1,100 of them directly. This is in contrast to previous multilingual models, which heavily rely on English as an intermediate. A Chinese to French translation, for example, typically passes from Chinese to English and then English to French, which increases the chance of introducing errors. Read More
Daily Archives: October 20, 2020
How can Startups Make Machine Learning Models Production-Ready?
Today, every technology startup needs to embrace AI and machine learning models to stay relevant in their business. Machine learning (ML), if implemented well, can have a direct impact on a company’s ability to succeed and raise the next round of funding. However, the path to implementing ML solutions comes with some specific hurdles for start-ups.
Let’s discuss the top considerations for getting ML models production-ready and the best approaches for a startup. Read More
The Globe and Mail’s Sophi Wins Best Digital News Start-Up
The Globe and Mail’s automation and predictive paywall engine, Sophi.io, won WAN-IFRA’s North American Digital Media Award in the category of Best Digital News Start-Up.
… Sophi Automation autonomously places 99% of the content on all of The Globe and Mail’s digital pages, including its homepage and section pages. This lets the newsroom focus on producing the finest journalism possible and has been so successful that it is now being used for print laydown as well. Read More
Detecting Deep-Fake Videos from Phoneme-Viseme Mismatches
Recent advances in machine learning and computer graphics have made it easier to convincingly manipulate video and audio. These so-called deep-fake videos range from complete full-face synthesis and replacement (face-swap), to complete mouth and audio synthesis and replacement (lip-sync), and partial word-based audio and mouth synthesis and replacement. Detection of deep fakes with only a small spatial and temporal manipulation is particularly challenging. We describe a technique to detect such manipulated videos by exploiting the fact that the dynamics of the mouth shape – visemes – are occasionally inconsistent with a spoken phoneme. We focus on the visemes associated with words having the sound M(mama), B(baba), or P(papa) in which the mouth must completely close in order to pronounce these phonemes. We observe that this is not the case in many deep-fake videos. Such phoneme-viseme mismatches can, therefore, be used to detect even spatially small and temporally localized manipulations. We demonstrate the efficacy and robustness of this approach to detect different types of deep-fake videos, including in-the-wild deep fakes. Read More
Facebook’s open source M2M-100 model can translate between 100 different languages
Facebook today open-sourced M2M-100, an algorithm it claims is the first capable of translating between any pair of 100 languages without relying on English data. The machine learning model, which was trained on 2,200 language pairs, ostensibly outperforms English-centric systems on a metric commonly used to evaluate machine translation performance. Read More
Rick's Cafe AI 