Extracting parallel fragments from comparable documents using a generative model.
Somayeh BakhshaeiReza SafabakhshShahram KhadiviPublished in: Comput. Speech Lang. (2019)
Keyphrases
- generative model
- probabilistic model
- information retrieval
- bayesian framework
- topic models
- document collections
- em algorithm
- prior knowledge
- text documents
- latent dirichlet allocation
- semi supervised
- posterior probability
- topic modeling
- discriminative models
- information retrieval systems
- document retrieval
- web documents
- document classification
- latent topics
- generative process
- discriminative learning
- document clustering
- retrieval systems
- user queries
- expectation maximization
- xml documents
- learned models
- vector space model
- text categorization
- markov chain monte carlo
- multiscale
- data sets