Unsupervised Text Normalization Using Distributed Representations of Words and Phrases.
Vivek Kumar Rangarajan SridharPublished in: VS@HLT-NAACL (2015)
Keyphrases
- distributed representations
- keywords
- syntactic categories
- multiword
- word pairs
- noun phrases
- text documents
- proper names
- word frequency
- semantic constraints
- real valued
- neural network
- information retrieval
- semantic similarity
- database
- semantic relations
- retrieve documents
- part of speech
- natural language text
- language model
- artificial intelligence
- natural language
- text mining
- word sense disambiguation
- web documents
- semantic information
- topic models
- knowledge base
- semantic network
- web pages
- named entities