How does Apple find dates, times and addresses in emails?

by

They likely use Information Extraction techniques for this.

Here is a demo of Stanford’s SUTime tool:

http://nlp.stanford.edu:8080/sutime/process

You would extract attributes about n-grams (consecutive words) in a document:

  • numberOfLetters
  • numberOfSymbols
  • length
  • previousWord
  • nextWord
  • nextWordNumberOfSymbols
    …

And then use a classification algorithm, and feed it positive and negative examples:

Observation  nLetters  nSymbols  length  prevWord  nextWord isPartOfDate  
"Feb."       3         1         4       "Wed"     "29th"   TRUE  
"DEC"        3         0         3       "company" "went"   FALSE  
...

You might get away with 50 examples of each, but the more the merrier. Then, the algorithm learns based on those examples, and can apply to future examples that it hasn’t seen before.

It might learn rules such as

  • if previous word is only characters and maybe periods…
  • and current word is in “february”, “mar.”, “the” …
  • and next word is in “twelfth”, any_number …
  • then is date

Here is a decent video by a Google engineer on the subject

More Related Contents:

  1. Machine understand natural language – nlp [closed]
  2. Speeker Identification (Machine Learning)
  3. Keras Text Preprocessing – Saving Tokenizer object to file for scoring
  4. Extract email id from text file by showing path
  5. Which algorithms involves in deep learning? [closed]
  6. Machine Learning Two class classification [closed]
  7. Artificial Neural Network Toplogy
  8. Whats the difference between a test set and a train set?
  9. What function defines accuracy in Keras when the loss is mean squared error (MSE)?
  10. What is the role of the bias in neural networks? [closed]
  11. Loss & accuracy – Are these reasonable learning curves?
  12. Clarification on a Neural Net that plays Snake
  13. Why do we have to normalize the input for an artificial neural network? [closed]
  14. Many to one and many to many LSTM examples in Keras
  15. How to interpret caffe log with debug_info?
  16. Logo recognition in images [closed]
  17. Caffe | solver.prototxt values setting strategy
  18. Cost function training target versus accuracy desired goal
  19. What is the difference between loss function and metric in Keras? [duplicate]
  20. ResNet: 100% accuracy during training, but 33% prediction accuracy with the same data
  21. Is deep learning bad at fitting simple non linear functions outside training scope (extrapolating)?
  22. How to interpret loss and accuracy for a machine learning model [closed]
  23. How to put more weight on certain features in machine learning?
  24. What is the difference between linear regression and logistic regression? [closed]
  25. TimeDistributed(Dense) vs Dense in Keras – Same number of parameters
  26. Keras: model.evaluate vs model.predict accuracy difference in multi-class NLP task
  27. How to create caffe.deploy from train.prototxt
  28. What is the difference between Keras model.evaluate() and model.predict()?
  29. Scikits-Learn RandomForrest trained on 64bit python wont open on 32bit python
  30. How should I teach machine learning algorithm using data with big disproportion of classes? (SVM)

Leave a Comment