Ksuravar writeup of Frietag et. al.

This is review of Frietag_2000_Maximum_Entropy_Markov_Models_for_Information_Extraction_and_Segmentation by user:ksuravar.

Summary:

1. The paper presents new markovian model MEMM
2. The paper uses conditional probabilities of states given observation sequences (and previous state) as apposed to probability of a state given the previous state and probability of the observation given the state independently.
3. The observations themselves can be dependent

Comments:

1. Though the paper mentions in the introduction that "GIS (used for the parameter estimation in this case) is similar in form and computational cost to expectation-maximization alogorithm" I think providing the running time or some measure where we can compare the complexity the new model whoud be great. THe reason is I believe new model is computationally more expense then old and before appreciating the results we should also think about the computational time it takes for giving those results.
2. One think I liked about the paper is that they not only gave the new markovian model but also considered the "three classical problems" of markovian model and gave the variant of 'forward-backward' procedure.