Word Embeddings from Large-Scale Greek Web Content.
Stamatis OutsiosKonstantinos SkianisPolykarpos MeladianosChristos XypolopoulosMichalis VazirgiannisPublished in: CoRR (2018)
Keyphrases
- web content
- website
- web pages
- web data
- web documents
- user generated
- web users
- n gram
- real world
- small scale
- low dimensional
- dimensionality reduction
- co occurrence
- word segmentation
- html documents
- web usage mining
- semantic browsing
- web resources
- user interests
- euclidean space
- manifold learning
- web information
- text categorization
- word recognition
- social media
- machine learning