Words and Word Usage: Newspaper Text versus the Web.
Vinci LiuJames R. CurranPublished in: ALTA (2005)
Keyphrases
- english words
- related words
- word pairs
- text corpus
- word co occurrence
- linguistic information
- keywords
- syntactic categories
- web documents
- multiword
- lexical features
- punctuation marks
- printed text
- chinese text
- unknown words
- web pages
- noun phrases
- co occurrence
- n gram
- lexical information
- stop words
- word level
- textual features
- natural language text
- word recognition
- printed documents
- word frequency
- syntactic analysis
- word sense disambiguation
- text documents
- syntactic information
- handwritten words
- word segmentation
- word meanings
- semantic relatedness between words
- text corpora
- text segments
- word meaning
- training corpus
- historical documents
- semantically related
- word similarity
- word sense
- word spotting
- lexical semantics
- semantic relations
- world knowledge
- language specific
- wordnet
- handwritten documents
- text mining
- document analysis
- historical manuscripts
- page layout
- lexico syntactic
- text lines
- news articles
- concept space
- compound words
- document images
- web images
- information extraction
- semantic information
- compressed text
- sentence level
- text queries
- spoken document retrieval