Table 3 Notations used in this paper.
From: An efficient learning based approach for automatic record deduplication with benchmark datasets
Notation | Description |
|---|---|
\({A}_{j}\) | Denotes jth attribute |
\({}_{VL}\) | Denotes word embedding of \({w}_{l}\) |
A | Denotes an attribute |
a, b | Indicate two scalar values |
D | Denotes dataset |
df(w) | Indicates count of tuples where token w is found among attributes |
idf(w) | Denotes inverse document frequency |
N | Represents pairs of tuples |
S | Denotes a vector |
T | Denotes a tuple |
x, y | Denote two k-dimensional vectors |
Y | Denotes a label vector |
α | Denotes smoothing hyperparameter |
