Prior-Knowledge-Embedded LDA with Word2vec - for Detecting Specific Topics in Documents.
Hiroshi UeharaAkihiro ItoYutaka SaitoKenichi YoshidaPublished in: PKAW (2019)
Keyphrases
- latent topics
- topic models
- latent dirichlet allocation
- topic modeling
- statistical topic models
- prior knowledge
- latent variables
- topic discovery
- text documents
- generative model
- lda model
- probabilistic topic models
- co occurrence
- bag of words
- keywords
- information retrieval
- latent topic models
- news articles
- latent semantic analysis
- probabilistic model
- face recognition
- document clustering
- word pairs
- stop words
- latent dirichlet
- text corpora
- document retrieval
- information retrieval systems
- word spotting
- xml documents
- topic hierarchy
- word counts
- training data