AI Blog
Two solutions to test for deep fake text
Synthetic content is probably going to be the gravest threat to the authority of media companies. Media newsrooms need to have a pro-active strategy to track, and flag deep fake text and video, which is now proliferating at an alarming rate. Reassuringly, so are the solutions being developed to detect deep fake. Here are two…
How contextualized are BERT, GPT-2 and ELMo word representations?
Until these major breakthroughs happened recently, NLP approaches were built around static representations of words (word2vec). Static embeddings of a word, say “mouse”, would fare poorly in accounting for variance in the various contextualized representations of the word (as rodent or gadget). BERT, GPT-2 and ELMo changed all that – and in a big way.…
Deep learning models to find causality?
The Holy Grail for machine learning models is whether a model can infer causality, instead of finding correlations in data. Well, it isn’t like this is a big focus area among researchers currently, but it is a fascinating challenge. A researcher at Facebook, Leon Bottou, presented an interesting framework that shows a path forward. His…
TextFooler fools BERT
It was a humbling moment for the state-of-the-art NLP models when an adversarial test compromised the output significantly. Yes, this included BERT as well, where its classification task prediction accuracy in a set of text analytics tasks reduced by 5 to 7 times! TextFooler is a baseline framework for synthetically creating adversarial samples, was created…
XGBoost learns better with monotonicity constraints for Cartoq
Cartoq, leading automobile site in India (43mn annual uniques), produces automated content [example of automated content here] related to best used car deals in the market.
Price prediction-based Automated Content generation
Here’s one interesting use-case for automated content related to deals advice for buyers. Suppose you want to identify best deals for used car buyers.