Multiple choices questions in NLP, Natural Language Processing solved MCQ, Maximum entropy markov model VS Hidden markov model, advantage of memm over hmm, which among hmm and memm uses features?
Natural Language Processing MCQ - Advantages of MEMM over HMM
1. The advantages of Maximum Entropy Markov Model (MEMM) over Hidden Markov Model (HMM) in sequential labeling problems include
a) Incorporate arbitrary features;
b) More reasonable independence assumptions;
c) Guarantee better performance;
d) Wider application scenarios.
|
Answer: (a) Incorporate arbitrary features MEMM is a graphical model for sequence labeling that uses the features of both HMM and Maximum Entropy models.MEMM is a discriminative model.MEMMs offer increased freedom in choosing features to represent observations. In sequence tagging situations, it is useful to use domain knowledge to design special-purpose features.
Hidden Markov Model VS Maximum Entropy Markov ModelHMM is only limited to the dependence between observations and states, MEMM introduces a custom feature function, which can not only express the dependence between observations, but also express the complex dependence between the current observation and multiple states before and after.
Advantages of MEMMIn a MEMM, we can build a feature vector with many features. For example, we can encode part-of-speech information of the n previous words, morphological features of the prior & next words, the existence of non-alphanumeric characters within the current word, and so on. Another advantage is that we can easily deal with unknown words through the use of general features (ex. word shape features). For example, we can encode whether the given word contains a digit, uppercase letter, special characters, and so on.
|