Word-Based Statistical Compressors as Natural Language Compression Boosters.
Antonio FariñaGonzalo NavarroJosé R. ParamáPublished in: DCC (2008)
Keyphrases
- natural language
- data compression
- natural language processing
- natural language text
- linguistic knowledge
- language processing
- probabilistic context free grammars
- compression algorithm
- statistical information
- image compression
- machine learning
- knowledge representation
- random access
- natural language generation
- word pairs
- natural language interface
- text compression
- compression scheme
- statistical methods
- statistical models
- n gram
- statistical analysis
- co occurrence
- multiresolution
- artificial intelligence
- information retrieval
- statistical tests
- confidence intervals
- information theoretic
- lossless compression
- question answering
- natural language sentences