2.1. TEXTUAL FEATURES 11
2.1.3 NEURAL TEXTUAL FEATURES
CNN
w
i
k
w
i
2 R
k
n
w
1Wn
D w
1
˚ w
2
w
n
;
˚ h
h
Qw
i
D .W w
iWiCh1
/
./ W
Qw D ΠQw
1
; Qw
2
; ; Qw
nhC1
t
RNN
12 2. WHAT NEWS CONTENT TELLS
Word Embeddings
Fully Connected Layer
with Softmax Predictor
ConvNet Layer
Max-pooling
It
is
never
below
zero
......
!
h
it
D
!
GRU.w
it
/; t 2 f1; : : : ; M
i
g
h
it
D
GRU.w
it
/; t 2 f1; : : : ; M
i
g:
w
it
!
h
it
h
it
h
it
D Œ
!
h
it
;
h
it
w
i
v
i
2 R
2d1
v
i
D
M
i
X
tD1
˛
it
h
it
;
2.1. TEXTUAL FEATURES 13
Sentence EncoderWord Encoder
a
o
s
α
α
α
N
α
α
α
M
o
w
h
h
h
N
v
v
v
N
h
h
h
N
h
h
h
M
w
w
w
M
h
h
h
M
······
······
······
······
······
······
······
˛
it
t
th
s
i
˛
it
o
it
D tanh.W
w
h
it
C b
w
/
˛
it
D
exp.o
it
o
T
w
/
P
M
i
kD1
exp.o
ik
o
T
w
/
;
o
it
h
it
h
it
o
w
!
h
i
D
!
GRU.v
i
/; i 2 f1; : : : ; N g
h
i
D
GRU.v
i
/; i 2 fN; : : : ; 1g:
h
i
2 R
2d1
!
h
i
h
i
h
i
D Œ
!
h
i
;
h
i
..................Content has been hidden....................
You can't read the all page of ebook, please click here login for view all page.