Towards robust word embeddings for noisy texts.
Yerai DovalJesús VilaresCarlos Gómez-RodríguezPublished in: CoRR (2019)
Keyphrases
- data sets
- noisy environments
- co occurrence
- noisy data
- text segments
- text corpus
- vector space
- natural language text
- natural language generation
- word sense disambiguation
- computing semantic relatedness
- english words
- syntactic analysis
- word recognition
- distance measure
- dimensionality reduction
- natural language processing
- natural language
- keywords
- search engine