TweetNorm: a benchmark for lexical normalization of Spanish tweets.
Iñaki AlegriaNora AranberriPere R. ComasVíctor FresnoPablo GamalloLluís PadróIñaki San VicenteJordi TurmoArkaitz ZubiagaPublished in: Lang. Resour. Evaluation (2015)
Keyphrases
- social media
- natural language processing
- domain specific
- wordnet
- named entities
- normalization method
- semantic relations
- semantic network
- context sensitive
- word sense disambiguation
- context specific
- benchmark suite
- lexical information
- micro blogging
- comparative analysis
- preprocessing
- linguistic information
- language identification
- short text
- co occurrence
- keywords
- neural network