The Dependence on Frequency of Word Embedding Similarity Measures.
Francisco ValentiniDiego Fernández SlezakEdgar AltszylerPublished in: CoRR (2022)
Keyphrases
- similarity measure
- co occurrence
- semantic similarity
- word sense disambiguation
- low frequency
- pointwise mutual information
- mutual information
- frequency counts
- similarity metrics
- n gram
- high frequency
- keywords
- feature vectors
- probabilistic model
- euclidean distance
- similarity function
- data hiding
- word pairs
- document frequency
- similarity assessment
- watermarking algorithm
- word similarity
- data embedding
- nonlinear dimensionality reduction
- search engine
- similarity search
- wordnet