Exploiting syntactic, semantic and lexical regularities in language modeling via directed Markov random fields.
Shaojun WangShaomin WangRussell GreinerDale SchuurmansLi ChengPublished in: ICML (2005)
Keyphrases
- markov random field
- language modeling
- syntactic semantic
- language model
- retrieval model
- information retrieval
- query expansion
- dependency parsing
- random fields
- maximum a posteriori
- graph cuts
- energy function
- belief propagation
- n gram
- higher order
- probabilistic model
- pairwise
- mrf model
- parameter estimation
- cross lingual
- conditional random fields
- image segmentation
- potential functions
- knowledge base
- markov networks
- semantic relations
- wordnet
- mixture model
- text classification
- information retrieval systems
- keywords
- em algorithm
- natural language processing
- bayesian networks
- translation model
- computer vision