Text comparison using word vector representations and dimensionality reduction.
Hendrik HeuerPublished in: CoRR (2016)
Keyphrases
- dimensionality reduction
- keywords
- sentence level
- english text
- text retrieval
- text input
- linguistic information
- high dimensional
- text corpus
- natural language text
- data representation
- word pairs
- english words
- chinese text
- principal component analysis
- word level
- n gram
- vector representation
- structure preserving
- lexical features
- semantic representations
- syntactic analysis
- handwritten words
- string matching
- low dimensional
- text mining
- syntactic categories
- related words
- syntactic information
- co occurrence
- pattern recognition
- text segments
- multiword
- printed text
- word counts
- concept space
- feature selection
- word recognition
- document analysis
- word sense
- noun phrases
- high dimensionality
- vector space
- feature extraction