Utility of Neural Embeddings in Semantic Similarity of Text Data.
Manik HendrePrasenjit MukherjeeManish GodsePublished in: FICTA (1) (2020)
Keyphrases
- semantic similarity
- text data
- high dimensional data
- text classification
- text mining
- high dimensional
- co occurrence
- similarity measure
- wordnet
- structured data
- low dimensional
- vector space model
- semantic information
- text documents
- document collections
- semantic similarity computation
- dimensionality reduction
- neural network
- data sets
- semantically similar
- vector space
- knowledge discovery
- web pages
- artificial intelligence
- nearest neighbor
- semi supervised
- learning algorithm
- information retrieval
- document representation