…r randomly in a given interval of time. It is a limiting form of the binomial distribution in which n becomes very large and p is very very small (meaning the number of trials is very large while the probability of occurrences of outcome under observation is small.
… we glossed over some things that are required to make this work with real-world data. For example, there’s additional work you have to do to deal with different lengths of input and output sentences (see bucketing and padding). There’s also issues with translating rare words correctly.