Tải bản đầy đủ (.doc) (34 trang)

BÀI TẬP LỚN MÔN XỬ LÝ NGÔN NGỮ TỰ NHIÊN Tìm hiểu về bài toán phân loại văn bản và thu thập thông tin

Bạn đang xem bản rút gọn của tài liệu. Xem và tải ngay bản đầy đủ của tài liệu tại đây (348.43 KB, 34 trang )





!"#$%

 &'()(*+,-

 
 
 
!" #
$%& #

 ! "









2
0
1
1
2
Bài tập lớn môn Xử lý ngôn ngữ tự nhiên
Mục lục


   1
Mục lục 2
./01
'()*+,-./,"0123+4
'5)6'++78+6+09
'5:;+<=.00,>0?+0@<<#

,#

'(:;+<=.2AB+&,CD2>&E,00+FAGHG
'5)I?&(++JKGDE,++JLMD<E
'5)I?&,NFN89(++JLM
'()6'<=.OI?&
POQR) >2









2
0
1
1
2
Bài tập lớn môn Xử lý ngôn ngữ tự nhiên


H0ST.BFA4U+&T+O*+8V6+=+30@WU*F
X5&VYZ+6+H00+6+4[0F+&B,WJF\A2]
3+F+620ST.BFA5^_O8++&=H0ST.BFA4U0P
B<N0+3,60!2+&`+&F0SJR6A+6+5aO6'
RST.BFA2A.b5R 4"WC++aB_OH00c./06
A+6+4U+d0Sd<3,A0F+&B.BFA+&T+F+&B+6++6
200060/2]F\,WJF\0ST.BFA5H0F+&B,WJF\
+6+0POe+TVf8O`5g<C+0cO*++h0c0H,N<C+ViO*+O6'
2O60%4"0PB0,"F+&B,V+0+6+5
AO+6+T41<;O0]+6+,"*+I0@+h0c0,+6+,"
O6+&X,+h0c0I+4*5
00O6'.BFA8++&=TOc04*0H00+6+F+&B
.N.I.BFA88j4.IHX+7&0k&C+"+&+c0
0k+"O9+&.BFAO00Oc081+-0+&N04PV68+A&5\.
0@,C4"F0081+-0+&N04P0YONNO/04-00/+=0@0
X5R0O/04-0F0l4,0081+-0+.0X
4&+&0]0/+=500+6+8]O6+&X+4h+'
0XV67&4=4"0Y0081+-0,4&0081+-0ON5
R0+&+c04P0P+=FNV.H00.d<++&XH0%0P+=F
Ol2AB00+&X*..BFA555O0XV6'.
&4[0V+3O6'00A+l5$'+3HZ0c,"+
A+&+c0+&0ST.BFADmF>.>GS0,>&G+<S>E&4X,N<
+8.BFADG+)EFO+&+1OZ0c5R0++TZ
0c,00+7++,"&-+A1+I,A0Z4U4[08./,+
4[0BV3+2]&C+2+&`(0123+4HOI?&555
)*+Sl<+2+&`+&8.BFA,_<]4[0Wn+43
  F  00  <  +  o>W+  RFSSp0+qH  o>W+  ^O&r+qH  ,   o>W+
R+>&r+q5
&Z+3N4U0P&C+"+06+&4"+81FN8,_<]00
Z0c0@Us )H+&008k+-AOT)sT00,A

Z0c0@00+&X4I`0T)tH8H7+ ]HR.5ZH00
+064P0@3+78+&,,C4"Z0c,"00,_<]+3KH
+385B6BF006B+4l+7F[VWJF\5
AH00PO*+060/4[00FA2]+&Fu,d0V
8,_<]+3$A+5"R6A+6+0@N0+4[08++&=3+
Sc0OIOv5G0*78H08++&=V+3H,_HwU*
0+_H00+6+4[0WJF\+62,_<]4A+JH2m><H2
>OF8++&=,N+l04*0POe+5a4PH0Z0c,W1.d00
060/8.BFA,_<]+3$A+44[03+Sc00+&`5&<
+'O=PO>OW+&'<00,C4"4U+'O=,",C4" 
$%&',%&'(
POQR) >3









2
0
1
1
2
Bài tập lớn môn Xử lý ngôn ngữ tự nhiên
23 4-56(78
0j+4U<3+H3+00+6+4[0+&4hAxO.N
.I+FA,_<]5R0+6+4P0P+=F00<<H00+FAV.H

00+6+V+3H00<Z0cV`05G!8./RST.BFA,
+&I+4*0@+h0c0F&C+8h<3,4>OFI"F[-0VF+&B,
WJF\H+V6+=2Z4[0&x0k&C+".I+6+V04[0
F+&B.N.I,_<]57O0-0]+&00+6+4[0F+&00
0ST.BFA+'8FN+&Sl0j0%4[0+h0c0.N.I,_<]5
AH00+h0c04U8./06A+6+,2]F\A+l06
,_C+XH,-./00A+lSJ./+S.>5Z4P0Y+d0SdF
002]F\F;.BFA,_<]H00C800060/V0cH0k.BFA,y
+d0SdxO.N.I,_<]5Rj+00P00]+7+81FIH+'OV3O
+FAH00060/+&-0F`0+6+xOO/04-0+lVZH8+A+&+c0H
&23+4+&d0+38+&Z00;.BFAV=5
$N+d0+34PH,C4"4e+&FFO+30j+0P+=V+04[0
B+6+B-0+a00;+FA,_<]P05R0;.BFA
8]4[0WJF\+34=X.!0P+=0PB060/+d4*
+&[j8+&,A08+A+&+c0,V+0+6+5Mz&H0j+
8]=&z<]0C+0@.BFA,_<]H=&z004e0+&0@00.BFAFI
4=0P+=0P4[0B888F70+3+5
$A0V+0+6++a00;.BFA,_<]+&00+h0c0$A+
O0f00f8].d,BV3+2]Z0c,",_<]P0H,"
.BFA,_<],00Vt+7+WJF\4U4[08++&=+&Z+3N5ZH
B,_<]+3$A+FI0PB4e0+&&Z0@P50P+=7+C
4[0SdV0<A+,"Oe+V-88H0j88,B88+3$A++&00
,_<]S,N006B8h<3+&Z+3N+3KH+385$7
+'B4e0+&]T+34300Vt+7+V8.BFA,_
<]H+08]0PBV\+7+ON4=0P+=+7./4[0B+3
0@+3$A+0%]23+4[0B8c0+I8+&+3$A+5
93:;<=>-*?@A-
932*B+(+,CDE-+(+()
 !"#$%&'(
$A0SJ./0ST.BFA,I+4*0@O*++h0c04U4[08++&=

+&,k_O+&TFI415$N.BFA4[0++78+&Sl+2+&'I+
4*0@O*++h0c0HO*+04[04e+&F+'OV3O,V+0+&+c0+a
B.BFA4P5:P0-FWC+8+4=O0@<++A+&+c0+a0
ST.BFA5X+7+C&x0P&C+"+&+c0O0j+V6FX
POQR) >4









2
0
1
1
2
Bài tập lớn môn Xử lý ngôn ngữ tự nhiên
+&N040k+"O9+&.BFAHAO,/0@0j+F8+AHVO8
00+&+c04PH8/0,/0B0SJ./+6+0H,-./
+&00A0ZA{+&[23+45
8.BFAF4I0@30@2+&'+A+&+c0+a0ST
.BFA5|+&'V8+&+c04[0+d0AS002+&'++78,
+F`0.BFAH0PuF0Y+'O00Oy+&+c0D8++>&E0P\u+&Z+78.B
FA0P,`0cV68]F+&Z+<*R^G00888+l
VZ+&N0415
$',7V8.BFA<;O,A0-*F-GCCH*G(*I*J*KI5L+MN=+,?
,-GCO+ACPBPCQ?*G(*-R+-*SP-TMN=+,?-*D&CH*G(*7U5)e0.!Oy'

0P+=+'O4[0+a<C+V'O*+R^G0YBOy8![8,NO/0
4-0+'OV3OON4[0`F+&+c05Sv0PBOSl4=400+Z
0-OyCL+VPU=K+V7B()7WKPEDCEX-3
:*ON0@Oy'8/+*0,V8IO,203H0P+=4l,N
A+le04l,NX.!5$-./,N.BFA0@O*+06+H2+&'
8.BFA+'O&4[0O*+F7+[+c0+4[0]O,O!+T
,!8- f0H4l,NA+l+'&C+ONH+&N0V0"0P<C+0cO*+
0<*F78V3I00%7&4[04"200<0+0-5
-B./0@Oy0P+=44[02SdFZ243O/04-0+'O
V3O5$NO*+0<*8/+&0<]+&'O+-T06++'F7++&ZV60P
+&HOe0.!FON4l,N+5
RP+=2064IV8+&+c00P&C+"Oy4[0FC&
V68]Oy0%0P+&H0P+=FONHB-0FI+O+XH
4e0<A+FV8./00Vt+7+.d+&Z+lVZ5G4PF68]0P00+Z
0-,00O400Oy4W>OWn+HV6+O+X5
POFIH8.BFA+d0&0P+=0FO*+2+&'W04Oy+a
00G+m&>S>HSJ./00Vt+7+S}0P`0OH7.IH+lVZH
81I555,00Vt+7+4[08++&=<TZ0c+&-+A1+I
)I?&1+ID>+&F>+m&VEH00+7++.+&"D>>&0
F&+OEH2I8F7+&F>&>.0+E555
0P+=Wn+43O*+Sl<+0-4l,NZ0c,"8.B
FA
? )*D0FSSp0+E('OO*+WID81FIE+aO*+Oy
.BFA,O*++&00FN80+&N05
? )+,-D&>&>SSE('OO*+WI;2+aO*+Oy.BFA
,O*+<3.d40P+&+d0
POQR) >5










2
0
1
1
2
Bài tập lớn môn Xử lý ngôn ngữ tự nhiên
? ).D0FS+>&E(,A0O6+]04=+'O&00+78W0
4BI00PO00FI4=O6+].BFA5
? )/01DSOO&r+E(,A04+'OV3OO*+O6+]0
+PO+f+0O*++780.BFA5
 !"#$)*%+,-'(
8.BFA,_<]8+A+&+c0+a000ST.BFA,_<]
D+>W+F.+<S>SE4"07843+3+&'+&-0F`000Oy'+6+D8++>&E
+&+c0DVmF>.>E42+1Oe00P+&D?+&,FE+a00+FA
,_<]80C+&j05|+&'0P+=4[00F,A0OT&*Vt+7+
8.BFA+&"+lH,'0j+4U+CD4U4[04"078T+&ZEVt+7+
8.BFA+&"+lDG+)EN+N,A08+A+&+c0+a00
0ST.BFA0P0C+&j05
6+4[0F+&B.N.IZSC+0-F,_<]57O0-
+0P+=+C&x.BFA+;+I.N.I,_<]0k0PVlF[FN&C+
"S,N00.BFA0P0C+&j0V05d0+3HBZ0c414U
0+C&x0P43#~+6+0@O*++h0c0xO.N.I,_<]5:P0P
+=F0006,_C+XH00<=Oy4"+&H00834e+H00Z0
V3IH]23+2"F[H00++-4A+JD>OFEH00+6++&Z00

m><S+>+OI55500Z0c,"0ST.BFA&4X,B_O
HX++T&x0P+=FO`FI+6+.N.I.BFA0P0C+&j05
+&Z+d0+3S_O8++&=HX+,y.!00A+lF
+&BT.I,_<],+7O+&-0k0PWN.!+XWZ5a4P
X+0P+=+&x00S]89O8.BFA,_<]0P+=0P+&
+OI0&C+"FS,N00S]89O8.BFA+&"
+lV05Z+0%0P+=+C&x00Vt+7+8.BFA
,_<]8c0+I8"S,N00Vt+7+8.BFA+&"+l<T,'
8]+d0A+&Z.BFA,_<],l4UT.I80C+&j0,0P+-OX
DprrE5
)*+,-./0<+V8.BFA,_<]HV81+-000<<
Z0cV`0H+0P00+6+S(
? oS+&>SSFO*+<AFZ24344q
? oS+&>SSWC+A0P+=.+3)Z+&Oq
? oRW0P+=_0]O*+Sl0c44q
? o)ZFO*+Z+l4"0W+dZ+&Oq
^V81+-000+6+2+&`HA+l08]4&00
SF10/+=O+-00OI(
? o3/+)Z0P+=1&O*+Sl<A44q
Mz&T410PSd81+-0SF7TOc04*05:=4I+4[0V_
,708]0PB06+&'Z0c,"+&-+A1+I+Z+35
POQR) >6










2
0
1
1
2
Bài tập lớn môn Xử lý ngôn ngữ tự nhiên
+8.BFA,_<]FO*+<+Z0c4Fu,d0H<
;O&C+"Vt+7+0%00NZ0cV0(++78+6
+Dp&O+&>+&>,FEH81+-0,_<]D+>W+FSSEH03+WC++6+
Dp&O+>W+&0+EHF784ID0FS+>&EH81FI,_<]D0+>&r+EH
=++&d02D,SFr+EH06A0ST.BFAH`0ODO0>
F>&E,<]+100Vt+7+8.BFA5
$NO*+A+l8,_<]+X<;O<<N00-(
? N0+"WJF\(g<N0HA+lSv0=,_<]+a.I
80C+&j0,".I0P0C+&j05$-./H,N,_<]/232-
4A+lSv0lf81+-0+/2325-554(R0+a
4[0F&Z&vO*+000P0C+&j04=+A0,A0WJF\5
? I<•00+6+V60+3+5g<N0H<*81+-0+'O
00FI<•00+6+,6-0+a,_<]5 N08/+*0&C+
",6B44[081+-0,Vt+7+Sv4[0.!
4=81+-0•<N0+38+>5$-./H3Vt+7+81+-0,_<]
0Y.d,W0WC+WC+A+aVHV4P+0P+=FI<•00
+a8/(1HH16H6-€
? 8.BFA4U4[0]F[0,N00Vt+7+V8.BFA
D.+OE+&"+l5
RP&C+"Vt+7+,888+l+4[0SJ./0>W+)4=+'O&
00V3+&j0ONH00OyONH,00FZV3+ON5R0<N0+"WJF\F00Vt
+7+&C+8c0+I8xO81+-0O*+81FN84e0<A++00+*0+-4e0
<A+HS4P+38./00888V8.BFAV4=+c0F

81+-0+lVZ,81+-000FZV3+5R0<N00kFISvV80],_
<]44@+a+7800,_<]H,-./81FN8,_<]5
)/0+Z0l0!0@>W+)+XF4XFlA2]H+AH,
4e0+&4=+&'.,+'OV3O00+78[8&*FN0@00,_<]5G4PH
00Vt+7+0-0@>W+)0P+=4[08181&+00AO,/
O0j+d0AVWJF\V8,_<](FI+6+O0j0P+=+&-0
&,FI81+-04[0+d0A<T0j5
R0FI+6+4[0+&-0&0P+=F(
? BP(*Y(Z•]SJH4[0FZV3+,NO{,_<]F+7800U00
++0V8+&+c04[0+d0A+&Z00U0@O{,_
<]5P0H0P+=]SJ&x00U+c,N00+a
VHO{O*++aV0P2A,NO*+0@4"0/+=4P5
? BP-TZg41]SJ&xO*+,_<]4[0U,N+a+a
WC+A+&,_<]4P5
? BP-*?[-()NZg41,NO{,_<]+'O+C000{+aH0{
+a4P+*0,"O*+Fu,d04P,.4P,A0+'OV8,_
<]4[0+d0A+&Z00VAO4[0U0O{,_
POQR) >7









2
0
1

1
2
Bài tập lớn môn Xử lý ngôn ngữ tự nhiên
<]5‚4=O0@888F00+7+B4[0+0&-+
,0PWN+78+&,00+6+2+&`0@,_<]
888+&N0415
R0FIV3+[8(
? A-*KI-*H()-*W\()Z)*+Sl+7+++&N041]SJ&x.B
FAZOy4[0+IF780j.14=+&[j8000Vt+7+
WJF\6B+dZ5R00C+&j00P0j.y+&Z+d0+30P+=
4[0SJ./O*+0ST0,A0WJF\V8+&+c05
? BPI*](P6I-*?[-()NZ g41O{,_<]4[04-,N00
+7+BFC&+aO*+810C800+7+B5^4PHO*+A+l
Sv81+-0Sd81<l*.0@00+7+B7.A0@+a
+7+BFA243007.AV0.0081<lFZV3+,
008n84V0xOV+0002AONB0j5I
FZV3+0P+=0%4[0SJ./4=F`0,+h[80@4"0@
00++c05
? *^+I*B5_(`a(7b@7cZ 6lFIFZV3++6
+X+d0A++0O!2+&Z000j.y0@,_<]HVt
+7+SJ./F[+30@*./ZOy0@00,_<]5
t+7+4[0`Fo+&-0,_<]ZOyq5
939'+-&B(I*](=&d+5_(`a(eDE-P^-D)&R+f^-+&(g
! .#/0)*
1FI,_<]D>W+0+>&r+EFWJF\PO00+FA+00
FN8V00081POD0+>&>SE5:1FO*++0,/81FN8FZ
243,A0&23+4WJF\5$NO{WJF\81POHV4&O*++
FAHO*+23+44[04&P0P+*0O*+FN8V653P+*0
O*+81FN84P+'8]0Y&81FN8OP+*0,5$-./H4&O*+
0@4","+=+H08]4&23+4&x0@4"4P+*00081FN827

8,9:29;<C+0cO*+O6+=+V05R0A
+l81FI,_<]+XFO,A0,NO*+ <=2 DF>&
F&+OE57++4P4[000C8O*++78Oy4=8/0,/0,A0.I`05
78Oy<;OO*++7800+d0+=0PU4[081FN8+&N00P
.IDWHET4PWF+d0+=4[081FN8HFUD81FN8E4[00
P5$N00C0ST,7HVO*++d0+=4[000C80A+lHPSv
0lfS&O*+O+`0+a+784+IOy,WI+d0+=ON4P,
O*+81FN851FN8,_<]F<+,40PB<N08++&=
3+Sc02+&`OZ10@3.Sd8++&=OIOv410@
00+6+Z+&d0+35
1! 2 !  .#/0)*
345678 .9 :7
)*+888+lVZ81FN8,_<]4[04"V=<TO*++a4=
0@4"0P810C84[04"WC+588SJ./O*++a4=,NO*+
0C+&j04]5a4=0P+=.I4[0..+&ZO*++78[8+FA
POQR) >8









2
0
1
1
2

Bài tập lớn môn Xử lý ngôn ngữ tự nhiên
4[081FN8<x+,0P+=.04[0+d4*S"6BV0
5
Rj+W>OWn+AO,/81FI,_<]<T0@4"0@+FA(,-./H
O*+Sl+FA,"B4*,7+H,O*+SlV0P,",C4"06A85
Rj+]SJ&x.S00@4"FFN0l45•]+7+0@0j+
V6+4[0B0@4"+a+10@+FA+,4PHPFZA+
FA,NO*++&B0@4"4[0FA+VZ+&+a4=A+l53+2]F
8n84D,"8+&_OESd+c0@+FA,NO{+a0@4"0PS}5
RPO*+,C,"WC+AF4*+lH4*[8F\H4*0+3+081FI
,75$-./HV81FI++c0+&Z+>&>+,NO*+X4`0o<'+XqH
B81FI00F4*,7+e006A8+'V8![8H
+&V81FN8000@4","4*,7+`0lO*+0l+a4=,7
Sv4&O*+01+&]FX00&x+C+0]000@4"4P4"P,"4*,7+5
P00V0H,NO*+X4`0++c0+&Z+>&>+<'+XH+7+V6
+-0[8.!4=81FIB+FA,NB0@4"0+3+B
4*,7+0P,jH4*,7+0PWSlH4*,7++1A+5
&<Z0cH0j+Sv<F7,"0C+&j00@+a4=0@
4"H000`Fd,00SJ./00+&`Sl0@00j+&ZFƒ+&810C8H
,O*+SlV-+d0+3,",A0<ZSI4=0@4"5
( ( ((>*2?2@A
&<Z0c0@00+0]•rO,K&>S,_O,
#H64"WC+,A0SJ./O*++a4=0P810C84=W04B4"
+0-0@O*++FA„…5$"Oe+Vt+7+H+a4=<;O8(00PO
+aVP4I.A0000@4"&Z<A+H,O*+<=.810C80@000@
4"5
)*+PO+aVPFO*+.S000+ae000<=+c0FZ243
+'+&I+O03<T+Z0@0@4"5$-./H0@4"+6FA+VZ00+a
+XH++H3HV+H0AHXH€Rj\&x
B+aV64[0FZV3+,N4O/0+6FZV3+,N<T

<C+Vi2ABu+Z09V=0H8H€
R10@4"4[0+h0c0+O*+810C8HP0F+h0c0+
O*+OIDV4PO*+Sl0@4"0P+=+*0O*+,j+0@01810C8E5
•]+7++'OV3O0@4"+&Z+a4=0%;O0P8(+'OV3O0@
4"4D0@4"FE,Sd+&"F+&`Sl0@0@4"+&Z015d0+3HP+&]FXH
001•S(+NOc04*+'+FASv8!,N0@4"4U0†)*+01
•,74[0+&]FX0O{0@4"&Z<A+5&+&X[84]C+H
+&`Sl0@O*+0@4"FSlD+SC+E00+a+cH+&.S0+aH4[0
+'O+C+&+FA„…5
+c0@]+7+0P+&0AOF+&"00+SC++'O+C
+&Z01„…5$N8]+7+H0j+0P+=0Y&&xO*++FA4"078
430@,"B4*,7+0P,jHB4*,7++1O"OHB4*,7+8
S+Tj+FH8![8,N0@4","B4*,7+H00S,7+Sl,+dZ
V6Tj+F5
POQR) >9









2
0
1
1
2
Bài tập lớn môn Xử lý ngôn ngữ tự nhiên

( ( (( B<C:D<'2@822E=DF
,'00.S0+a4]HO*+Sl+&`Sl0P+=4[0SJ./<T
]+7+4=4uDE8n844F[Sd8![80@00+a,N000@
4",DE4Oc02+&`0@00j+0@+*001810C8„…5
I+&`Sl4+ZH0j+`F00+&`SlSd8![8H0PFZA,N
00FZV3+B00+a,000@4",00FZV3+B00j++&Z015$-./H
3+FA4"07843+ao21G80H+'P4P,"6+65OS8!
[8+a21G80He00B0@4","6+6H4*OI
+&002A+3†$"+&d00H4PP80@+a21G80H
,0@4"6+6FNSd4PP80@+a‡,7HOlFZV3+B
o,0@4"6+64[0O*++&`Sl•5
RP+=+C&xH+&`Sl

V
m
0@O*+FZV3+,7DBO*++aV,O*+
0@4"ˆHBO*+0@4"V,0@4"0ˆ0@P+&Z01E0P+=4[04
u4*8![8+&<'00@4"0@B+FA4[04&0c+a
(




=
#
0

#
0


I

I
0

E
J
„…5g418n8+-+h4[0+d0A+C+0]00+FA0P
S}GH
I

E
F8n84Sd8![80@+FA,N0@4"ˆH,
0


FSlFWC+A
0@+a0@4"V+&+FA5
6OH0j+V6++I<C+0c]+7+4+074=
+'O&8n844*8![8
I

E
0@00+FA000Fu,d0O*+004*0F785
,4PHO*+8n84,74[04<x+<T0ZH,S
4PA+l4[0CFA+&Z[800+FA5R00Z0P+=8]
+XWZB+&`Sl+-0[8<x+000+FA5
R]00+3807Z0&x4[0FO<_+5:=+&4"4PH
,NO*+8n8+4jH,NB4"+4@‰8H0P+=]+3+&xB
,_<]+&Z,"0@4"V6<XWC+A+&B,_<]

+6+X5 4P <= +c00@00+&`Sl0P +=4[0 4] P(


=
#
0

I
0

J

„…5
ŠZ00-0FI+c0@00+&`Sl?Sd81<A+00+&`Sl?F
V]_81<A+B0j(O*+0@4"08]+c+NO*++780
D4V=EB+FA5)e+V0HB0@4"O+c,N+C+0]
00+FA+&0ST.BFA+'0jF,6-0,'0jV608n84&
<C+ViV3+F78![8,N00+FA+c5
,7H+&`Sl
I
J
0@O*+j+ˆ+&Z010P+=4[044*<3
4h0@4*8![8J
I
0@4"2B+FA+&0ST.BFA5)*+004
]  4=  +-  +  O*+  V]  _  81  <A+  F  4  P  O*+  00  &X  &I0(


−=
#

I

I
KEJ

ED
HT4P


=
#
I

#EK ‹
F+&+&<'0@
I

E
20ST.B
POQR) >10









2

0
1
1
2
Bài tập lớn môn Xử lý ngôn ngữ tự nhiên
FAA+XGH,
I

E
4[0W04<T]+7+OV6+-43+&J
I
5
&O*+Z00-W0HF\+3++6+0P+=4[08./08n8
+-00+&`Sl5g410j+V6<F7,"\+T5
$N00+3807H,NO*+0ST.BFAS,7+H+&`Sl0@000@4"
004*,7+H00S,7+SlH+ZZSv+C8,'+C+0]00+FA4"078
<x,"000@4"5)e+V0H.0PSd8+&*+&00+X<+&`Sl
0@0jSv0H."+FA+&4PV6+c+NB0@4"H
,yP884"0784V=43000@4"5
;2 ! .<=$<>7?%&,@/A,,(
8881FN8,_<] 1.<=$<>7? D.>0S+&>>?GE4[0
)+0>FF4&,_O„…5&Z01;O00j++&4[0U<T
00+7+BH00010cj+4[0U<x00+&`Sl0@+7+
B+c4l,N+FAOyH,00F014[0fU<T0081FN85
)*+A+l81FN8,7Sv81FIO*++FA%
I
<T8n8+J4A200
+&`SlO00+7+B4[0U000j++&,N,>0?+

I

%
043
V,N+NO*+j+F54PHU0@j+4[00%
I
5:Sl008N
8881FI,7SJ./<=.,_<]T.I81H,,700
010%4[0<=..N.I815)*+,-./,"0123+44[0
OI+&'5
)*+888V]+.!4=CFAO*+0123+481FI2

xOT03F[028EL„…5R3F[0SvV=O+&W>OFA+C+0]00
POQR) >11
lúa mì lúa mì
nông trại nông trại giạ giạ
thương nghiệp
thương nghiệp xuất khẩu
xuất khẩu
nông nghiệp
tấn tấn
nông nghiệp
lúa mìlúa mì
lúa mì
lúa mì
lúa mì
lúa mì lúa mì
lúa mì
Hình 1: Một ví dụ về cây quyết định










2
0
1
1
2
Bài tập lớn môn Xử lý ngôn ngữ tự nhiên
VAOCFA0P0!U,NPDe0

2
e0


2
E‡3V6HFd0`
O*+VAO
0
H81001+00FN8+FA0P0!+&
0
,0Œ,
O{FN8,7O*+010&Z<A+5|+&'4A2Fe8FI+&Z00010
043VO{F0@018+S0c00VAOCFZ00!
8IO+&!2

HV4PP4[00`FU0@F4P5 N023+4F,A0

0`+7+B
0
T4PSvW]&++028HO*+888Fd0`F0`
+>F[-0+6+>+&85ZHO*+01•2FNFZ•0P+=<S78H
3000124e0<A+,N.BFACFA5
:Sl008N88.I0123+4,7<;OO*+8
88+ZO01,O*+888Wn<N+014=FI<•B24e0
<A+„…5
93h'+-&B(-*?-*[I-*H()-+(e(i&RC^-+&(RD-R+D5^=jg
B!$C D
+78+6+Dsp&O+M>+&>,FEFO*++&B<+V
8.BFA,_<]5 +0@3+78+&,,A0+'O&00+FA
+&O*++78[800+FA0PS}+>O*+4"VA4P5R04"VA
0P+=FO*++&,CO*+,_<]5
4"VA4,FO*++&,CH<+Sv4&00SF74=+'O
&4e0+&0@01+&,C4PHS4PSS,N004e0+&0@00+FA
0PS}4=+'O&00+FA8![8C+,N01+&,C4P5&<+H
O6'0@<+,N<+^>&0b>5ZH<+++78
+6+F<+4[08++&=TOc04*05:l,N<+^>&0
b>H01+&,C4,F+78[800AO5,N<+++78
+6+H01+&,C4,0P+=FO*+01,_0PBu5A+lSv+'O
0081+-0Bu0@01+&,C4=+'O&4e0+&0@P5
POQR) >12










2
0
1
1
2
Bài tập lớn môn Xử lý ngôn ngữ tự nhiên
++78.BFAH0j++X0lf+'OV3O00.BFA0-W05
&00+&X[8V0H0j+V=O+&4=W>OO*++6+0P+&O*+
+A8+V65++78+6+HV3+2]0-W0+X4[02+1OH
+6+X0j+Ol+'OV3OO*+00+4l0-W0,NO*+
+6+4e0<A+4[04,5^4P0j+Sv+d0`+6+8![8C+
+a00V3+2]0@8n8WJF\+&N04P530j+SSP,N00V=A
+lV0H0j+Sv+C&x+&*.00+&,C0ST.BFAH
O*+8n8+'OV3O+d00C+F4=FO+]OUO*++&,CHF01•4=+'O&
01+&]FXD4[0<3+43,NVAO+&-0WC++6+E4e0<A+F,NO*+01
•4e0<A+5&++78+6+HO*+8n8+'OV3OxO+'O&O*++FA
OX.!405R0A+l++78+6+DsMSS+>OSE4[0SJ
./4=++7800+FAFZ24300Z0&z&5$C4",N++78
+6+F,A0WJF\00,_<]0P*.FZ2*+I4300,_<]
4[0SJ./+&N04P5'4&O*+O6'++0++78+6+
095=ZH,A0++78+6+F2+&'WJF\Fe8FIH,NWJF\4
,,4&<;O,kFe8+-+FIZ05
+00=4h+&,C+>O*+03F[00PS}xO+_+-
8![80@+FA4U74[05
POQR) >13
Thông n cần thiết
Truy vấn
Gửi cho Hệ thống

Nhận kết quả
Đánh giá kết quả
Tốt ?
Dừng lại
Đúng
Công thức hoá lại
Sai
Hình 2. Mô hình thu thập thông @n chuẩn









2
0
1
1
2
Bài tập lớn môn Xử lý ngôn ngữ tự nhiên
$A0++78+6+0P+=4[04u0<C+0cO*+FI+6+
,-./V=,_<]H']H1O+555ZHT410j+0Y4"
07843,A0++78,_<]<T,_<]FO*+FI+6+O8+c0
+d0A,Vt+7+WJF\4]5RP+=COI&x00Vt+7+
0%0P+=4[08./0++78+6+48+A5
R0Vt+7+++78+6+0P+=4[00&+FI(
? R0Vt+7+09

? R0Vt+7+0P8./+&-+A1+I5
PO4+Z<;O00Vt+7+.d+&Z008+c0+7++,
+`0+&"+l5PO+c0lf++78+&+c0<x00Vt+7+8
./+&-+A1+I4=4[000V3+2]+l+5
B1! 2 ! $C D
H00+6+44[08++&=OIOv,"SlF[,0@
3F+as+>&>+5s+>&>+4U+&T+F+&BH2]F\,4e0<A+F+
7+6+0P,+AF[5[-0+&+1OF00+6++7
4[08![8,N0X.!5:PFF\.0@00Z0c0ZS1
+&  00  Fu ,d0   V  8  .B FA  DG+)EH  +&-0  WC+  +6 +
Dsp&O+bW+&0+EH++78+6+Dsp&O+M>+&>,FE5
MC+"00888++78+6+4[08++&=,V3+2]O
0j4>OFIV+l+5&4P0P&C+"888+;+IT.I095
R0888+X.d+>00888+`00h4=5)*+Sl
888V04[08++&=+>N.d+&-+A1+I5^41H0j
+Sv+'O=S1,"00888++78+6+5
B1! 2 ! $E
FN00Vt+7+094[08++&=+aB_O43B
_OH,8FN+&Sl0j.d+&Z00+7++,06+c0+
`0+&"+l5&<Z0c0Y4"0784300O6'
)M8N)M8%MOH08M2P;NM2ED82M%MO5
(Q( ((K)M8
F>FO6'Z0c03F[H4]C+H,4[0+=A
4=4&\+T0<]00003F[W„…53+4;\&x+C+0]
0003F[0Z0c.d+&Z,A0SSB01+&,C,00+FA
4[0F+&B5)6' F>Z0c03F[0++7800+FA4[0
+&EMc,N+&,C4P5•]SJ+FA.
ˆ
4[0<=.++7800
+7+B

{ }
0I
% H555HH

=
HT4P+

FO*++7+BWC+A+&+FA%
I
5)*+
+&,C4[0<=.<xO*+<=+c0F00@00+7+B<;O00
++JKGHLMH,L5
$-./,N+&,C(
RSNTU#NUVOOVWB
POQR) >14









2
0
1
1
2
Bài tập lớn môn Xử lý ngôn ngữ tự nhiên

g418n8+'OV3O F>Sv74[0+C+0]00+FA0PFZV3+,N
V6FZV3+,Ne000+FA0PFZV3+,N5
R/+=H,NO*+01+&,C(
RSNF+,-'GTU#NNFHI/A/J,A,#GOTU#NUV
F1,/AK/GOO
A+lSv0lf+'O&+C+0]00+FA+*00@4"MXKHO
0/+=F00888++78+6+0cV68]F008
8881FN8,_<]5
(Q( (((Y2DD
ZV3+B+&,C,+FA0P+=4[0=+>uO*+OS
S5R0O+X&C+4]5)*++&3F[04[0SJ./`F21
6:2A;ZDD(
R3F[04[0SJ./+&<*<34h0@8n8+'OV3O F>HT
4P0Y0P00++JF0KG5Ž+T0-0@03F[04[04&V
W>OWn+SlF[0@00+7+B0+&01+&,C,+&+FA5^l
4[0`FOc04;Sf8W38,0P+=4[0SJ./O*+OSS5
$-./H00+aVHH4[0FZV3+,N00+FAGHGHGHG
+>00S(
FZV3+,NGHGHGHG
FZV3+,GHG
FZV3+,NGHG
,|•KGKG
$N+&,C|H0j+Sv0P00Oc04;Sf8W38S(
G
GHG
G
(Q( (( 019<
t+1++'OV3O++dF0ST0@O6' F>5Z
P&C++XWZ4[0SJ./Oe0.!PV07O5,N<C+0c00
HP0+C00O00OSS4[0SJ./„…5

:&O*++7800+FA,O*++&,C
{ }
U
### H555HH

,O*++&,C
|H0j+4+-+&0@OSSKNR#

O5:=74[000+FA
FZ2H0j+0Sf8W3800+FA]O.0@OSS,<•4+C+0]
00+FAc,NOSS•O*+6[240+&N05•
0P+=4[04uO*++&OSSKe0FO*+-+&SS,N
O*+,_<]4P50+c0FNC+0@Vt+7+F+'O4[0000`
+&•0f+8![85
:=+d0AO6'+'OV3O F>H0j+0P+=SJ./O*+SlVt
+7+A2]5ZH00+7++4PV64[04"078+&<Z
0c5
POQR) >15









2
0
1

1
2
Bài tập lớn môn Xử lý ngôn ngữ tự nhiên
(Q( ((Q<2'
){O*++FA04[040YO/0D.>WE<TO*+Sl+7+BHO{
+7+BOZ+]*.0@+FZ5R0+7+B+X4[0`F
00+7+B4Uf0YO/000+aV5:=,A0++784[0+d0A
0PH0j+ZSf8W3800+a5R0+aV4[0F+&B+&'
2\]2H,,NO{+aV+*0<*+a,dSv0P.S000+FA0c
+aV5:=+]OUO*++&,CH0j+Sv+d0A+'OV3O+&ZpF>0Y
O/05
t+7+4[0SJ./<T"A+l+OI,N004*+l
V00@+A8+0YO/0+'OV3OD,-./ ?+&>>SE5
R0[04=O0@Vt+7+F(
? +&B2"D0P+=0V6F+&BFZ43~S,N
V-0+N0<4E
? •+0787+,+h0c0FI0YO/00
? •+[800.S0+FA030j2.
ZH0j0%0P004=O&Z(
? d0A..
? l04*
? G.{+&[00+a4;u
(Q( (( K08M2P;N^M2ED82M%MP^BKO
)6'V6,>0?+4[0OT&*+aO6' F>+&,A0
+=A00+7+B0@+FA„…5•lO6' F>H0j+
U00+FA<T+7800+7+B5+&Z+d0+3H4=OV04[0
9+&,A0<=.+FZ5FAG4[0<=.<TO*+ M2P;P
2,N00+6Slc,NO{0"F+&`Slc,N+a+7+B0/
+=5&+&X[8HOF+hS6+7+B4[04u4=W04
*.0@+FA5&`Sl4[0+-<TW0SC+WC+A,4*2+&`

0@+aV5
#SNJ

J

(((J
U
O
$-./HV81+-0+FA#

,#

F<Z0cHFZ2
43<A414H+0P,>0?+4[0I+&Z4;+?0"S(
POQR) >16









2
0
1
1
2
Bài tập lớn môn Xử lý ngôn ngữ tự nhiên

R0+&`Sl+&ZO{,>0?+<=.W0SC+WC+A0@00+7+B
+&O{<<5FA#

H+7+B_8A9HK8`WC+A,NW0SC+
FF[+F5H55FA#

H+7+B_8A9HK8`WC+A,NW0
SC+FF[+F5H55
&O6'HO*++&,C4[04lWJO*++FA„…DW>O'
E5P00V0H0j+Sv<=01+&,C<TO*+,>0?++&`Sl0@
00+7+B5^V+d0A,A081+-001+&,C+Sv+4[0O*+,>0?
+5$A0+d0A01+&,C+d00C+F,A0SS0,>0?+0@01+&,C
,N00,>0?+4I.A000+FA+>O*++Z094P53+2]+Sv+
4[0O*+.S000+FA0P2Ao9,N01+&,C4U4&5C+
ZH00+FA4PSv4[0Sf8W38+>+&'+d]O.,Sv<0f+TO*+
6[4P5
:=+-,>0?+<=.O*++FAH00+a&Z<A++&+FA4[0+h
[8FI5&Z+d0+3H,A0+d0A4[0+d0A+>00S(
? R0+a8/4[0WP4
? 1<A+00+a<TV]+&f
POQR) >17
Magê
Đau đầu
1.0
1.0
D
1
(0.25, 0.75)
D
2

(0.6, 0.2)
Hình 3. Đồ thị biểu diễn các vec-tơ của bài báo D
1
và D
2
1.
0
1.
0
Magê
Đau đầu
D1
D2
query
Hình 4: Đồ thị biểu diễn quan hệ giữa truy vấn (query) và các tài liệu
D1, D2









2
0
1
1
2

Bài tập lớn môn Xử lý ngôn ngữ tự nhiên
:l,NKBe08BHO{+a4[0+0<A+<T00V]+&f5
6B+3$A+FI]S,C4"+a4,+an85:10%FO*+
,C4"VPV_V81+0+a+&+3$A+5$-./H,N+a28-+&
+3KHc,NPF+a2-+&+3$A+5G,C4","+an8Z
"=O+&+3$A+5R0,C4"4P`FSdO78OX+&+3$A+5
$-./H,N01 2AL8H+0P+=0P0081+0 2AL85,
25AL85
,7H4l,N+3$A+H0j+00P00888+0+a4e0<A+
5
(Q( (( (126;32abc#a
&`Sl0@O*++7+B0P+=4[0W04+>"005R0+38
070FSJ./8+c0db%dHT4P+&`Sl4[0+h[8<T3
+l(
? w0SC++7+BD+>&Op&>2>0?+pE?4e0+&0W0SC+WC+
A+7+B+&+FA
? 04]W0SC+0@+FAD,>&S>.0O>+p&>2>0?.pE?
4e0+&0W0SC+0@+7+B+&+<*+78[800+FA5
P00V0HO*++7+B3OVWC+A+&00+FA
+'%dSv0H0k3PWC+A+XWZ+&00+FA+'
%dSv+C85
$-./(06+c0.N414[04"WC+0P+=4[0.!4=+-00+&
4UPT+&Z„…(
I
d

d
d

OW

55 +=
„…

WF>,+00F>+

F=

%d

T4Pd

FW0SC+WC+A+7+BX

+&+FA51Sl+&%d4[0
+-+<x888]+-0,NV]_WC+AX

+&+FA5
(Q( (( ( _6;A+ND8E-O
00+&`Sl00+7+B4[0W04H0j+0O*+OSf8W38
4=44*+4;B00,>0?++&,C,+FA5)*+Sl8n844*
+4;4[0+=A.N415g4P|,GFF[+F00+78+7+B+&
+&,C,+&,_<](
#R ∩
06+c04]C+
%R
#R
+


ASl0@G0>

POQR) >18









2
0
1
1
2
Bài tập lớn môn Xử lý ngôn ngữ tự nhiên
#R
#R


ASl‘00&.
‹‹
#R
#R
+

ASl0S
EHOD #R
#R ∩
ASlI80;

)*+44*+4;+6+XH4[0<3+4340S
„…HW04P0B,>0?++FA,,>0?++&,C<T8n8+-+O*+
V3+2]*+I5:e0<A+H4+X4[0+-,N4*.0@,>0?+5:*
+4;4[0W04+>06+c0.N41„…(
∑ ∑

= =
=
==








J
J
R#
R#
R#D
 


5
5
EHD
•]SJ0]+&,C,+FA4[009<T4*.0@0jH06+c0
Sv+&TZ4](


=
==



JR#R#D

5EHD
^V+C+0]00+FA4[0SS,N+&,CH0jSv4[0Sf8W38
]O.+>4*+4;HV3+2]FO*+.S04U4[0Sf8W380@00+
FA5GS00P+=4[0WJF\<x00SJ./00Vt+7+V05
(Q( (( (Q<2'
)6'V6,>0?+&C++l06V+d0AH.4P+&+d0+3O*+
Sl8n8WC8WY4]4[0SJ./5=ZF<=A0@00,>0?+0Y
+;+IVAOB5&+d0+3H00,>0?+3OV4[0F+&B44@.
.+-+0@0j5$-./H0P+C+0]+7+BH+FAG0Y4"07843
+7+BH,7V60+3+8]F+&B+C+0]00+6Slc,N,>0?+
+c,N+FA5
)*+08M2P;A9-A@0P+=4[0SJ./[8FA4=FO
]O4*8c0+I80@+7++„…5Ž+T0@O6'FF+&B,>0?++&
O*++A8+4U4[00=4h5A8++&],"O*+.S000+FA,N
00+aV4e0<A+0!,N+6+,"W0SC+5 Z0I,A0+&WC++>0Y
O/0H+A8+0=4h0%0]+A004e0+-+X0@,A0SS00
,>0?+5t+7+0&O*+8n8+-+0C874[0,NB+&,C
+4l•H0k,NB+&,CFNH8n8+-81Sl09Sv0d0V'
+lVnO5[04=O+c0@Vt+7+F0+-+000081Sl
09SV0PSd+4h0@%d5:"4P&C+0P+=W]&+&+d0+3H,-./
V++ZOe0W4O*++FA+&+h[85
POQR) >19










2
0
1
1
2
Bài tập lớn môn Xử lý ngôn ngữ tự nhiên
:=N0F[A2]0@8n809H0j+SJ./<'8Sl
F[00+7+B+&O*++FA81Sl095$N00+&X[8
+FAf+'8n8+-WC8WYV64[00-W0H+ZVt+7+0%
0PO*+Sl4=OS(
? ’T0@V-0+N0+FA+&TZV60P\u,N<C+0c
FI095
? :*8c0+I8+-+•&C+"S,N00Vt+7++&N041
? RP+=+-++&N0
,7H4*+4;0P+=4[0+d0A<T06+c0S(
G+&>OVS
EHD


=
=




J
R#D
B1! 2 ! AL$.0/%MHN*@,,/(
R0888+&-+A1+I+X.d+&-+A1+I+78+&,
00]+7+CFAO`05P&zH08]0PO*+2+&'C
FA0O`081FI,_<]+&N0VSJ./P5|+&'CFA
&C+2+&`5300e?-'[8F\H01,+4[0Sv0P0C+
F[&C++l+5[0FIH32+&'CFAV6[8F\+'0P+=
.y43S/84h+<*A+l5
R0888+X8]4lOe+,NO*+Sl,C4"S(
? •]+7+SF7
? 88F+&B+6+[8F\
? &SdS/84hSO*++X.I+4*
3+00]+7+.d+&-+A1+I+Xf0]2+&'+d`0
+&VSJ./5Š3+l23+4A0@A+l5S
O*++X.I+46H0P+=A+lSvF1O,+'+&IS/84h.EH'
+-0Ft2"H2+&'+d`0<H+6+F+&B2"5C+0]00
F\.+&Z4"FO]OI+4*0@A+l5G4PH008880
0PSd+d4"0Y+&I+4*5 Z0I]+7++-0FtEH'0%00P
]+7+XZE32,f5
^410j+SvZ0c0/+=,"00888<5
(Q( ( (ghU;PENUME8MJE0O
RP+=P+4lOI&xH00Z0c41,"sMV+
06+&00Vt+7+4[04"WC+4=*.0@+FA,+&,CH
P00V0F+d0A4[00081+-0Bu5$NO/0+ZHA
+l0P+=8./00Fu,d0+&+c0000WJF\4=+'OV3O,++78
+6+5060P4[0+>u4I+4[0V]_`0,V]_

+h2+0@OI?&D>&F>+m&VE5
POQR) >20









2
0
1
1
2
Bài tập lớn môn Xử lý ngôn ngữ tự nhiên
$N,A0SJ./OI?&H0j+0P+=<=.O*+8+[
+&+&+c0+&Fu,d00@<+H,0P+=4[0SJ./+06+&
A+l++78+6+5
(Q( ( ((/,8;PE
:=0P+==FO+3OI?&0P+=8./0WJF\++78
+6+H0j+Sv4uO*+SlVAO4[0SJ./+&F\+Z+
OI?&5
w1.d00Vl0@O6'+-+0OI?&+004,
`FiNME%MOO&C+"004e0+-0@&?&S`0„…H
P4jF00j+OI4[0O68•+>00?&0@4*,7+5
g00j+OIT'+=A008n8+F0KG5:&0@j+
OISvD3004,4"D5P4[0+d0A<T8n8SS,N
+&•NOOO`4&4"0P5=ZF,A0+d0A8n8F0

LMSv0P+&•]O0k5DW>O'5<E5R0+&+&e04[0
`F00+&`SlH4u4*OI0@FZV3+5&O6'+-+0@
OI?&H+&`Sl+X4[04uF+&xO+&V]„?H…5
&+&X[88c0+I8H,-./V+d0A8n8+LMH0j+
0"O*+4,H004,4P`F4,j5
)6'+-+OI?&4[0<=.<T00+7+B,"V3+l
0@PD00OyV3+lE,+&00+7+B,"00O0j4[04+I
D00F7+SJ00+&`SlE5
POQR) >21
(1)
(1)
T=
(1)
(1)
T=
Hình 5. Mạng nơ-ron: toán tử AND (a) và toán tử OR (b)
(a)
(b)









2
0
1

1
2
Bài tập lớn môn Xử lý ngôn ngữ tự nhiên
(Q( ( (( KE-6:28*
)6'4[04"WC+FO*+O6'<FN8(
? N800+7+B+&,CD00j+OI4,EQ|F>&
? N800+FAD00j+OI4&EQGF>&
? N8000YO/0D00j+9EQF>&
&'H0j+0P00V\AS(
?
+

?0YO/0+7+B
?
G

?+FA
?
|

?+7+B+&,C0@X.!
?
8
ˆ
?+&`SlV3+lB_0@OI+7+B,O*+_0@
OI+FA
?
2

?+&`SlFZV3+B+7+B0@+&,C,+7+B+


?
m
ˆ
?+&FZV3+B+7+B+

,+
ˆ
?
.
ˆ
?+&`SlFZV3+B+FAG

,+FAG
ˆ
POQR) >22
0.5
1.5
1 1-2
1 1
Hình 6. Mạng nơ-ron với lớp ẩn: toán tử NOR
input










2
0
1
1
2
Bài tập lớn môn Xử lý ngôn ngữ tự nhiên
N8+7+B+&,C<=.00Z0X.!5){O*+j+FO*+
+7+B+&+&,C5N8+FA<=.+7800+FA5){j+203
43O*++FA5R0j++&FN80P00FZV3+0"0P+&`SlH+=A
Sd+4;B00+FA5•+&+4;4[0+-+<T+&`Sl
Bu0@00+7+B+&O{+FA5N800+7+BFFN84*5){
j+<=.O*++7+B4[040YO/05R0FZV3+0P+&B00j+
F00V3+FlB00+7+B+&8+&,C5
R0FZV3+0P+&`SlB00_+*0FN8+7+B0P0Y.y,00
_+*0FN8+7+B
I
<=.V]_\u0@+7+B

+&
+FA#
I
5ZV3+0P+&`Sl,

4u4*2+&`0@+7+B

+&
+<*+h[800+FA5R0+&VT40@00+&`Sl0P+=4[0
+&`yZe0,N<C+0c00W0453+&yZ4[0SJ
./H0P+=+Sv8]4lOe+,N00,C4"S(

? X`0.
? P4I+4[0Sd*+/
:=+'O&+&`SlJ
I
DFZV3+B+

,+
ˆ
EH0j+]SJ&x4*FZV3+
B+7+B+_V4;WC+A+&O*++FAH,+&0Y]O
V0PO*+FWC+A+&O*++FA5
ZV3+B+FA4[0<=.<T06+c0S(
∑ ∑

−+
=
I 0
0I00I0
0
0I0
kkkk
kk
WN##IO

5ED
5
(Q( ( ((QY322@8
Rc0_OI;O8(
POQR) >23
Hình 7: Mô hình biểu diễn mạng nơ-ron










2
0
1
1
2
Bài tập lớn môn Xử lý ngôn ngữ tự nhiên
? ++78+6+
? `0
++78+6+<f+4VX.!J0A+lO*+Z0
D+X4[0,3+.N.I6B+dZE5ŠZ04[081+-0,
+cFN8|Sv4[0W1.d5){_+&FN8|4[0FZV3+,NO*+
_+&FN8,N0!+7+B5ZV3+Sv<f+44[0V-0I+.`0
+>00OlFZV3+,

5){_0@FN87O*++-A+aFN8|Sv+-+
&x4*V-0I+,S4P+&"P+NOI5
&+&X[84P0PV]_0P+=W]&(
? &"F+-A+N_V0+aD+d4*+-+FIZ0E
? &"FP+N_4P+aG
&+&X[8+cHO{_0@FN8GSv+-O*++&V-0I+
8]WI4*+4;BZ0,+FA5R0+FA++784[0Sf8W38

+>+&V-0I+0@0j5
4PHX.!0PB0*4=F+&"FSdV-0I+0@+FA
+NB_V0+*0FN8Ge01&O*+SdF+&"8];0@00
_+*0FN8G+N00_+*0FN85:"4P0PuFSdF+&"+FA
8![843FN8Sv1&2+&'SdV-0I++&"F+&FN8,FN8
G5+&+d0+3H2+&'V6O<C+Vi+FAONH
.!S4BP0P+=]O<N+Sl+FAT4&5
|+&'`0<;O(
? 4h00FZV3+B00_+*0FN8G,FN8
? 4hFZV3++&O*+FN8
&N03+H8./F7+b 4=SJ4h00+&`SlV3+l
I
5Ž+T
Sv+_00+&+&`Sl0@V3+lB00+FA<x00W>OWn+4*
8![8,4*V-0I+0@00+7+BH,]O+&`Sl300+FA4[0
Wn++CV68![85R0I+4*]T43\u0@00+7+
B4[0SS,N+FA+>Sd8![80@+FA5
c43HSJ4h00FZV3+B
I
5•]+7+SJ./+&4IC
FA8FN4[0.d+&Z00Z0c0@>5POFIH8
88.d0+&Z4*8![80@00+FA74[0SO*++&,C5
g4I4+ZH0PSd+_+&0@00V3+l+d00C+FV-0I+
00_,N00+FA8![8,,A0]O+&300V3+B00_,N
+FAFV68![85g4I+cH2+&'CFA+I&V3+l
B00+7+B,V-0I+00_,N00+FA8![85
•]+7+4[0SJ./0O/04-0PO00+7+B4[0FZV3+
+N+FA+&Z0!0@4"5
R0CFA0PV]_N,A0OT&*004lWJ0@00
OI?&H4e0<A++&Fu,d0++78+6+5

POQR) >24









2
0
1
1
2
Bài tập lớn môn Xử lý ngôn ngữ tự nhiên
h3BP)+a+I*BIBIMk()P*&+D-(^CD;DDE-+(+()
h324P-RW()Pc^5_(`a(-+A()+,-
3$A+FO*+&A;„…H4e04=O<2++<*4e0
+&+3$A+,"Oe+B1OHBu,B885G4PH0j+8]+3
Z0c4e04=O0@+3$A+4=0P+=0P4[0BN
Z0c0/+=,",_<]+3$A+5
B1!72?:>O
B+>7P78:>
&+3$A+H0%+&00,_<]+3$A+H+0P+=+C1
FO*++8V2+&`5&V-88HO{+34c4*0F78H,+0P
+=8+A4[0001+&0]+3P0%+&,_<]„…5
Q((((1EL&
B1O0-FOe+1O0@6B5IS+FI8]Z0cV-
0I0@6B+3$A+5:PF,'+&Z+d0+3H00c./FZ243

+3$A+.0+7+HF+&BX+,yFI1O+.I,_<]HS
4PON+300++0WJF\5){+30-FO*+1O+3+,4[0FI
+O*+0/O+&,_<]5
Q(((( 1EL&l8
3Wn+,"Oe+Bu+'1A;Lm?2.2.l8„…5
d0&+0P+=+C&x4,B1O+C8C+F1O,+'+V60P
uD,-./000B04c&Z&vE5Z0%0PB+30P
uD,-./3E5
>„…H+0P+=81<A+00+3S(
? R0+3+dP0PuD,-./2H0HHiE0P+=4[0
.!4=`+ZSd,7+HA+[H0P+=4[0.!O*++a5
? R0+30PuV6.!4=`+ZSd,7+HA+[D,-
./nH<2EO0Y4[0.!,N+00F<*874=0C
+Z+a0PuT<7005V6+=P<2O0Y
0P+=PH0PB+a<2j(
? R0+3<]+1V6"0PuO0Y.!4=V3+[8+I
+u04,+&d0+380H4PF+a5$-./00+3
oAo+dPV60Pu0P+=+I++a0PuF
oAo5
Q((((Q1EL&
-0IB88<;OB2+f00C+I+aH0C+I015$+0P
+=+C&x+3FA;L&%CA2?$„…5
$",A0.!+34=0C+I+aH+0P+&X[8S(
POQR) >25

×