Google Research • Representation Learning for Information Extraction from Templatic Documents such as receipts, bills, insurance quotes. We propose a novel approach using representation learning for tackling the problem of extracting structured information from form-like document images.

Blogpost

https://ai.googleblog.com/2020/06/extracting-structured-data-from.html?m=1

Paper

https://research.google/pubs/pub49122/
We propose an extraction system that uses knowledge of the types of the target fields to generate extraction candidates, and a neural network architecture that learns a dense representation of each candidate based on neighboring words in the document. These learned representations are not only useful in solving the extraction task for unseen document templates from two different domains, but are also interpretable, as we show using loss cases. #machinelearning #deeplearning #datascience #dataengineer #nlp

Google Research • Representation Learning for Information Extraction from Templatic Documents such as receipts, bills, insurance quotes. We propose a novel approach using representation learning for tackling the problem of extracting structured information from form-like document images.

Blogpost

https://ai.googleblog.com/2020/06/extracting-structured-data-from.html?m=1

Paper

https://research.google/pubs/pub49122/
We propose an extraction system that uses knowledge of the types of the target fields to generate extraction candidates, and a neural network architecture that learns a dense representation of each candidate based on neighboring words in the document. These learned representations are not only useful in solving the extraction task for unseen document templates from two different domains, but are also interpretable, as we show using loss cases. #machinelearning #deeplearning #datascience #dataengineer #nlp

Lecture Notes in Deep Learning: Feedforward Networks — Part 3 | #DataScience #MachineLearning #ArtificialIntelligence #AI

https://bit.ly/2Z2GgQY

Learning to Combine Top-Down and Bottom-Up Signals in Recurrent Neural Networks with Attention over Modules Mittal et al.: #ArtificialIntelligence #DeepLearning #MachineLearning

https://arxiv.org/abs/2006.16981

In future #AI hiring other AI be like: Job Profile: *human baby sitter*
- Experience : trained on 100 years of past data.
- Test Accuracy : 99.9999
- Precision: blah
- recall : blah
- AUC : blah blah
- Inference time: A.C
- Trained on : Latest "alien" TPUs and GPUs
- Bias : blah Note: AI trained on old TPUs will not be considered. And then AI will gossip with each other about bias and discrimination they have to go through compared to others like:
- "Wouldn't I be considered if I am trained on X country's data?"
- "Why was she considered even though she has outliers in the data?"
- "I am trained on old TPUs, I won't be considered? What!" LOL #artificialintelligence #machinelearning

Stanford CS224w’s lectures Machine Learning with Graphs, Leskovec et al.: https://lnkd.in/d4Cnahj #DeepLearning #Graphs #MachineLearning