|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
Concept
Link: new way to calculate sentence
|
|
|
|
|
|
|
|
similarity;
|
|
|
n |
no chunker/parser
involved
|
|
|
n |
concept differs
from NPs in Lexical Chain
|
|
|
Considering
sentence similarity/relatedness via
|
|
|
|
|
Concept Link:
|
|
|
n |
Alleviate the
influence of expression variations; (but
|
|
|
might involve
inaccurate sense guess)
|
|
|
n |
Outperforms Word
co-occurrence approach
|
|
|
Minimizing
Redundancy via Modified MMR;
|
|
|
|
|
|
|
|
No
extra heuristics involved.
|
|
|
|
|
|
|