Frequency-aware Dimension Selection for Static Word Embedding by Mixed Product Distance.

Lingfeng Shen Haiyun Jiang Lemao Liu Ying Chen

Published in: CoRR (2023)

Keyphrases

life cycle
keywords
distance function
intrinsic dimension
euclidean distance
string edit distance
related words
n gram
high frequency
selection algorithm
low frequency
geodesic distance
vector space
pairwise distances
product quality
product design
data sets
similarity search
distance measure
text mining
search engine