AI engineering glossary · NLP embeddings
What is HMM (Hidden Markov model)?
Hidden Markov model (also called HMM): A probabilistic model of a sequence in which hidden states, such as part-of-speech tags, follow a Markov chain and each state emits an observed item, such as a word. It is fitted from counts and decoded with the Viterbi algorithm.
Hidden Markov model: an example
In a POS tagger, hidden states are tags, and P(noun to verb) and P(word | tag) are the model's probabilities.
Related terms
- Viterbi algorithm
- Part-of-speech tagging
- Markov assumption
More NLP embeddings terms
- Hierarchical softmax
- In-batch negatives
- InfoNCE loss
- Intent classification
- Inverse document frequency
- Kneser-Ney smoothing
- Massive Text Embedding Benchmark
- Matryoshka representation learning
Where you learn it
Hidden Markov model is part of the AI Engineering Program, which teaches it with notes, a hands-on lab and an exam. The first lesson is free.