Different word representations and their combination for proper name retrieval from diachronic documents.
Irina IllinaDominique FohrPublished in: ASRU (2015)
Keyphrases
- information retrieval
- spoken documents
- index terms
- document retrieval
- text queries
- information retrieval systems
- retrieval systems
- stop words
- sparck jones
- term frequency
- word frequency
- term weighting
- structured documents
- document space
- word clouds
- document collections
- handwritten documents
- related documents
- multimedia documents
- word spotting
- document level
- spoken document retrieval
- document content
- query words
- document image retrieval
- document analysis
- retrieval process
- word frequencies
- semantic content
- query terms
- text retrieval
- text documents
- vector space model
- expert finding
- retrieval model
- query expansion
- latent topics
- relevance feedback
- retrieval engine
- tf idf
- relevant documents
- text corpus
- keywords
- arabic documents
- natural language text
- xml documents
- co occurrence
- text categorization
- test collection
- search engine
- metadata
- web documents
- indian languages
- word pairs
- average precision
- retrieval strategies
- word recognition
- printed documents
- text classification
- sentence level
- multiword
- document representation
- semantic similarity
- document clustering
- cross language information retrieval
- n gram
- relevance model
- text mining
- information extraction