Towards Proactive Information Retrieval in Noisy Text with Wikipedia Concepts.
Tabish AhmedSahan BulathwelaPublished in: CoRR (2022)
Keyphrases
- information retrieval
- explicit semantic analysis
- world knowledge
- document collections
- semantic relatedness
- text mining
- bag of words
- wikipedia articles
- concept space
- text retrieval
- information retrieval systems
- text processing
- document corpus
- probabilistic topic models
- key concepts
- computational linguistics
- semantic network
- external knowledge
- natural language text
- semantic features
- linguistic analysis
- semantic information
- genre classification
- information extraction
- text data
- text collections
- named entity disambiguation
- latent dirichlet allocation
- short texts
- test collection
- named entities
- text classification
- query expansion
- wordnet
- relevance feedback
- web documents
- background knowledge
- retrieval systems
- relevant documents
- natural language processing systems
- wikipedia pages
- knowledge base
- conceptual retrieval
- vector space model
- document structure
- keywords
- knowledge repositories
- search engine
- related documents
- text corpus
- text documents
- noun phrases
- structured documents
- document retrieval
- retrieval model
- semantic similarity
- semantic relations