EmBoost: Embedding Boosting to Learn Multilevel Abstract Text Representation for Document Retrieval.
Tolgahan CakalogluXiaowei XuRoshith RaghavanPublished in: ICAART (3) (2022)
Keyphrases
- document retrieval
- text representation
- text retrieval
- document collections
- language model
- retrieval model
- information retrieval
- vector space model
- document representation
- index terms
- information filtering
- document clustering
- concept learning
- vector space
- text documents
- bag of words
- text mining
- relevance feedback
- keywords
- relevant documents
- inverted index
- learning algorithm
- word sense disambiguation
- topic models
- digital libraries
- machine learning
- query terms
- training data
- text categorization