A non-parameterized sentence embedding method that first compresses word vectors with wavelets and then applies a cosine transform over the compressed coefficients, matching baseline performance at a fraction of the dimension.
Don’t count, predict! a systematic comparison of context-counting vs
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CL 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Combining Discrete Wavelet and Cosine Transforms for Efficient Sentence Embedding
A non-parameterized sentence embedding method that first compresses word vectors with wavelets and then applies a cosine transform over the compressed coefficients, matching baseline performance at a fraction of the dimension.