Document representation and classification with Twitter-based document embedding, adversarial domain-adaptation, and query expansion.
Minh-Triet TranLap Q. TrieuHuy Q. TranPublished in: J. Heuristics (2022)
Keyphrases
- document representation
- query expansion
- language model
- information retrieval systems
- document classification
- document collections
- relevant documents
- information retrieval
- vector space model
- bag of words
- vector space
- language modeling
- text documents
- retrieval model
- document clustering
- text classification
- web documents
- image classification
- document retrieval
- relevance feedback
- text data
- data fusion
- semantic information
- test collection
- machine learning
- labeled data
- feature selection
- decision trees
- feature space
- document level
- data sets
- tf idf
- keywords
- training set
- probabilistic model
- text mining
- unlabeled data
- n gram
- action recognition
- natural language
- feature extraction
- semi supervised
- search engine
- user queries