Towards Proactive Information Retrieval in Noisy Text with Wikipedia Concepts.
Tabish AhmedSahan BulathwelaPublished in: CIKM Workshops (2022)
Keyphrases
- information retrieval
- world knowledge
- explicit semantic analysis
- semantic relatedness
- document collections
- text mining
- text retrieval
- document corpus
- probabilistic topic models
- concept space
- information retrieval systems
- text data
- wikipedia articles
- named entity disambiguation
- computational linguistics
- computing semantic relatedness
- semantic network
- external knowledge
- linguistic analysis
- knowledge sources
- genre classification
- wordnet
- text collections
- text processing
- document retrieval
- semantic information
- short texts
- semantic features
- natural language text
- wikipedia pages
- key concepts
- latent semantic analysis
- query expansion
- bag of words
- named entities
- text clustering
- search engine
- conceptual retrieval
- information extraction
- natural language processing systems
- web documents
- retrieval systems
- information access
- background knowledge
- topic models
- question answering
- latent dirichlet allocation
- key topics
- document clustering
- structured documents
- semantic similarity
- semantic relations
- knowledge base
- video search