Lexical Comparison Between Wikipedia and Twitter Corpora by Using Word Embeddings.
Luchen TanHaotian ZhangCharles L. A. ClarkeMark D. SmuckerPublished in: ACL (2) (2015)
Keyphrases
- text corpus
- natural language processing
- wordnet
- natural language text
- word frequency
- computing semantic relatedness
- word sense disambiguation
- semantic relations
- linguistic information
- text corpora
- lexical information
- keywords
- lexical features
- word similarity
- named entities
- semantic information
- word meaning
- dimensionality reduction
- word pairs
- information extraction
- social media
- social networks
- semantic network
- co occurrence
- related words
- noun phrases
- syntactic categories
- lexical resources
- statistical machine translation
- vector space
- text documents
- domain specific
- syntactic information
- world knowledge
- multiword
- social networking
- n gram
- knowledge base