Documente Academic
Documente Profesional
Documente Cultură
ABSTRACT
The Hindi/Urdu Treebank (HUTB) (Bhatt et al 2009) has been under development since 2008.
It is an innovative resource for research on natural language processing (NLP) for Hindi and
Urdu: like all treebanks, it contains levels of morphological and syntactic annotations. However,
unlike other treebanks, it is being annotated simultaneously for lexical predicate-argument
structure (PB, in the PropBank style), and the syntactic annotations are available in both a
dependency representation (DS) and a phrase structure representation (PS). All three levels
of representation are independently motivated and independently described. The treebank
comprises 400,000 words of Hindi and 150,000 words of Urdu.
The goal of this tutorial is to give an in-depth introduction to the HUTB and to enable
participants to start using it productively. Because of the novelty of the structure of the
treebank, researchers in Hindi and Urdu NLP are encouraged to fully understand the contents
of this treebank, rather than to just consider it as raw data for machine learning approaches.
=>68%/),7?>%
00-*1%0?@A,7")1%B6>%C?(D%0":41%E*F1%(),7?>9<<@';<?@A,7");65A%
%
F'+>"8"%G)"54)%
-"8HA"'$<'1%E8"I6('":4%?J%0?@?()5?1%K?A@56(1%E*F1%F'+>"8";G)"54)9<?@?()5?;65A%
%
!6<%L1%MNOM%
0=-2BP%MNOM%
%
=I6(I"6>%
!
!
!
!
!
!
!
28:(?5A<$?8%:?%:+6%8):A(6%?J%'48:)<$<%(6#(6'68:)$?8';%%Q/),7?>1%OR%,"8A:6'S%
28:(?5A<$?8%:?%:+6%,?(#+?@?H41%'48:)T1%)85%@6T"<)@%'6,)8$<'%?J%3"85"%)85%E(5A;%%
Q*+)(,)1%UN%,"8A:6'S%
.+6%,?(#+?@?H"<)@%(6#(6'68:)$?8%J?(%3"85"%)85%E(5A1%"8<@A5"8H%68<?5"8H%"''A6'1%
:?D68"V)$?81%#)(:W?JW'#66<+%:)H'1%)85%,?(#+?@?H"<)@%(6#(6'68:)$?8;%%Q*+)(,)%)85%
/),7?>1%MN%,"8A:6'S%
.+6%56#68568<4%(6#(6'68:)$?8%Q!*S%J?(%3"85"%)85%E(5A%'48:)TX%#("8<"#@6'1%
(6#(6'68:)$?81%)85%6T),#@6';%%Q*+)(,)1%MR%,"8A:6'S%
.+6%@6T"<)@%'6,)8$<%(6#(6'68:)$?8%QYKS%J?(%3"85"%)85%E(5AX%#("8<"#@6'1%
(6#(6'68:)$?81%)85%6T),#@6';%%QG)"54)1%MR%,"8A:6'S%
.+6%#+()'6%':(A<:A(6%(6#(6'68:)$?8%QY*S%J?(%3"85"%)85%E(5A%'48:)TX%#("8<"#@6'1%
(6#(6'68:)$?81%)85%6T),#@6';%%Q/),7?>1%MR%,"8A:6'S%
*),#@6%"8"$)@%6T#6(",68:'%"8%3"85"%)85%E(5A%B-Y%A'"8H%:+6%3E.K;%%Q*+)(,)%)85%
/),7?>1%OR%,"8A:6'S;%
=I6(I"6>%
!
!
!
!
!
!
!
28:(?5A<$?8%:?%:+6%8):A(6%?J%'48:)<$<%(6#(6'68:)$?8';%%Q/),7?>1%OR%,"8A:6'S%
28:(?5A<$?8%:?%:+6%,?(#+?@?H41%'48:)T1%)85%@6T"<)@%'6,)8$<'%?J%3"85"%)85%E(5A;%%
Q*+)(,)1%UN%,"8A:6'S%
.+6%,?(#+?@?H"<)@%(6#(6'68:)$?8%J?(%3"85"%)85%E(5A1%"8<@A5"8H%68<?5"8H%"''A6'1%
:?D68"V)$?81%#)(:W?JW'#66<+%:)H'1%)85%,?(#+?@?H"<)@%(6#(6'68:)$?8;%%Q*+)(,)%)85%
/),7?>1%MN%,"8A:6'S%
.+6%56#68568<4%(6#(6'68:)$?8%Q!*S%J?(%3"85"%)85%E(5A%'48:)TX%#("8<"#@6'1%
(6#(6'68:)$?81%)85%6T),#@6';%%Q*+)(,)1%MR%,"8A:6'S%
.+6%@6T"<)@%'6,)8$<%(6#(6'68:)$?8%QYKS%J?(%3"85"%)85%E(5AX%#("8<"#@6'1%
(6#(6'68:)$?81%)85%6T),#@6';%%QG)"54)1%MR%,"8A:6'S%
.+6%#+()'6%':(A<:A(6%(6#(6'68:)$?8%QY*S%J?(%3"85"%)85%E(5A%'48:)TX%#("8<"#@6'1%
(6#(6'68:)$?81%)85%6T),#@6';%%Q/),7?>1%MR%,"8A:6'S%
*),#@6%"8"$)@%6T#6(",68:'%"8%3"85"%)85%E(5A%B-Y%A'"8H%:+6%3E.K;%%Q*+)(,)%)85%
/),7?>1%OR%,"8A:6'S;%
.+6%3"85"%.(667)8D%
! Z%/6#(6'68:)$?8'%
! !*X%!6#68568<4%*:(A<:A(6%
! YKX%Y(?#K)8D%Q@6T"<)@%#(65"<):6W)(HA,68:%
':(A<:A(6S%
! Y*X%Y+()'6%*:(A<:A(6%
! [+4%+)I6%:+(66%@6I6@'%?J%(6#(6'68:)$?8\%%
[+):%5?6'%]@6I6@%?J%(6#(6'68:)$?8^%,6)81%"8%
J)<:\%
[+):%"'%)%*48:)<$<%/6#(6'68:)$?8\%
O;! *48:)<$<%#+68?,68)%Q]>+):^S1%6;H;X%
! *A7_6<:%?J%)%I6(7%
! /6@)$I6%<@)A'6%
! *,)@@%<@)A'6%
-"8HA"':'%:685%:?%)H(66%?8%>+):%#+68?,68)%6T"':%
M;! &):+6,)$<)@%(6#(6'68:)$?8%:4#6%Q]7)'"<%+?>^S1%6;H;X%
! Y+()'6%':(A<:A(6%:(66%
! !6#68568<4%:(66%
! =(%'?,6:+"8H%,?(6%<?,#@"<):65X%H()#+1%-`P1%.FP1%a%
Z;! `?(,)@%'48:)<$<%56'<("#$?8%Q]56:)"@65%+?>^SX%
);!
7;!
<;!
5;!
&)##"8H%J(?,%#+68?,68)%:?%(6#(6'68:)$?8'%Q"8%#)($<A@)(%:4#6S%
0+?'68%(6#(6'68:)$?8%J?(%)%'#6<"b<%#+68?,68?8%)@'?%<)@@65%
!"!#$%&%'
Y+68?,68)%6T:()<:65%"8%(6#(6'68:)$?8%)(6%:+6%&"()*+*)(!,-"'
`?(,)@%56'<("#$?8%"'%)%%$"(!.,.'(/)-*$'"J%":%,)D6'%#(65"<$?8'%
/6#(6'68:)$?8%.4#6'X%
!6#68568<4%)85%Y+()'6%*:(A<:A(6%
! !6#68568<4%.(66%Q!*SX%
! =86%@)76@%)@#+)76:1%>?(5'%%Qc%>?(5'%"8%)%'68:68<6S%
! F@@%8?56'%@)76@65%>":+%>?(5'%?(%6,#:4%':("8H'%
! Y+()'6%*:(A<:A(6%.(66%QY*SX%
! .>?%5"'_?"8:%@)76@%)@#+)76:'1%:6(,"8)@'%Qc%>?(5'%"8%
'68:68<6S%)85%8?8:6(,"8)@'%
! F@@%)85%?8@4%"8:6("?(%8?56'%)(6%@)76@65%>":+%
8?8:6(,"8)@'%
! -6)I6'%)(6%@)76@65%>":+%:6(,"8)@'%?(%6,#:4%':("8H'%
! B?:+"8H%6@'6%"'%#)(:%?J%:+6%56b8"$?8d%
eT),#@6X%*,)@@%0@)A'6'%
! 3"85"%
! !"#$%%&%'()"%*+%,-*.%%')/"%%
! F$J%86%%*66,)%D?%%%76>)DAAJ%'),_+))%%
! F$J%e(H%*66,)%F<<%':A#"5%<?8'"56(;YJI%%
! %fF$J%<?8'"56(65%*66,)%':A#"5;g%%
! e8H@"'+%
! F$J%<?8'"56(65%*66,)%':A#"5%
! F$J%<?8'"56(65%+6(%':A#"5%
[+):%"'%:+6%Y+68?,68?8\%
! *48:)<$<)@@4%)85%'6,)8$<)@@41%!"#$%&'(%:)D6'%)%
<@)A')@%<?,#@6,68:%
! F$J%<?8'"56(65%h<@)A'6%:+):%'+6%"'%':A#"5i%
! F$J%<?8'"56(65%h<@)A'6%+6(%':A#"5i%
! KA:%:>?%#(?7@6,'X%
! B?%I6(7%%
! )'(%"'%'6,)8$<)@@4%'A7_6<:%?J%$*+,%&%7A:%+)'%)<<A')$I6%
<)'61%>+"<+%"'%A8A'A)@%Q'A7_6<:'%)(6%A'A)@@4%
8?,"8)$I6S-
! *?X%
! F$J%<?8'"56(65%h',)@@%<@)A'6%+6(%':A#"5i%
[+):%"'%:+6%/6#(6'68:)$?8%.4#6\%
! `?(%:+"'%6T),#@61%>6%>"@@%'+?>%56#68568<4%
:(66'%)85%#+()'6%':(A<:A(6%:(66'%
B?:6%?8%!*%)85%Y*%
! .+6'6%)8)@4'6'%)(6%"8:A"$I6@4%I6(4%'","@)(%
! `?(,)@%8?$?8X%]<?8'"':68<4^%Q`6"%k")1%'66%
K+)l1%/),7?>%m%`6"%MNOOS%
! 28:A$?8X%I6(4%'",#@6%)85%H686()@%)@H?(":+,%<)8%
:()8'J?(,%<?8'"':68:%!*%:?%Y*%)85%.%!'-.'($/0%
*A,,)(4X%*48:)<$<%Y+68?,68)1%
/6#(6'68:)$?8%.4#6'1%F8)@4'6'%
! *48:)<$<%#+68?,68)%)(6%:+6%6,#"("<)@%5):)%
?J%'48:)T%)'%#)(:%?J%:+6%'<"68<6%?J%@)8HA)H6%
! 0)8%76%I6(4%'","@)(%)<(?''%@)8HA)H6'%
! .+6(6%<)8%76%'6I6()@%#?''"7@6%)8)@4'6'%
! *?,6%+)I6%@6''%"8J?(,)$?8%
! KA:%:+6(6%<)8%76%5"o6(68:%)8)@4'6'%:+):%(6#(6'68:%
:+6%'),6%"8J?(,)$?8%5"o6(68:@4%
! .+6%)8)@4'6'%<)8%76%'","@)(%"8%!*%)85%Y*%
! -?:'%?J%<+?"<6'%"8%:(667)8D%56'"H8d%
%
[+):%!?6'%.+"'%&6)8%J?(%B-Y\%
! .(667)8D'%)(6%8?:%8):A()@@4%?<<A(("8H%5):)%%
! .+6%HA"56@"86'%)(6%#)"8':)D"8H@4%#(?5A<65%74%@"8HA"':'%
)85%(6#(6'68:%)%J?(,)@%56'<("#$?8%?J%:+6%@)8HA)H6%
! F88?:):?('%A856(':)85%)%'68:68<61%56:6(,"86%>+):%
'48:)<$<%#+68?,68)%6T"':1%)85%A'6%:+6%HA"56@"86'%:?%
<+??'6%)8%)8)@4'"'%J?(%:+6%'68:68<6%Q)%':(A<:A(6S%
! E'6('%?J%:+6%:(667)8D%<)8%A'6%:+6%HA"56@"86'%:?%
"8:6(#(6:%:+6%':(A<:A(6'%)85%H6:%7)<D%:+6%'48:)<$<%
#+68?,68)%#(6'68:%
! .+6'6%#+68?,68)1%)85%8?:%:+6"(%(6#(6'68:)$?8%"8%:+6%
:(667)8D1%<)8%76%A'65%J?(%B-Y%"8%1)/*'.'((',('$'#*/2"#-!)"$'#-34-*)'-('$'/(!)'(d%
! .+6(6%"'%)@(6)54%@?:'%?J%@"8HA"'$<'%"8%?A(%(6'?A(<6'1%>6%
_A':%8665%:?%,)D6%A'6%?J%:+):%@"8HA"'$<%"8J?(,)$?8d%
.+6%3"85"%.(667)8D%
! !*X%56#68568<41%)88?:):65%74%+)85%
! YKX%)88?:):65%74%+)85%?8%:?#%?J%!*1%)55'%
"8J?(,)$?8%)7?A:%@6T"<)@%'6,)8$<'%
! !?6'%8?:%<+)8H6%:(66'%
! F55'%@)76@'%:?%)(<'%)85%J6):A(6'%:?%8?56'%
! Y*X%#+()'6%':(A<:A(61%56("I65%)A:?,)$<)@@4%
J(?,%!*pYK%
! 0?8:)"8'%@6''%"8J?(,)$?8%:+)8%!*pYK%
! !*%)85%Y*%<?8:)"8%5"o6(68:%"8J?(,)$?8%
0?,#)("'?8%?J%!*1%YK1%Y*%Q*),#@6S%
[+):\%
3?>\%
!% !%
Y+()'6%*:(A<:A(6%
!%
!"'$8HA"'+%A86(H)$I6qA8)<<A')$I6%
!"'$8HA"'+%:6,#?()@q@?<)$I6%)5_A8<:'%
!% !%
!% !%
!"'$8HA"'+%A8)<<A')$I6q:()8'"$I6%>":+%6,#:4%)H68:% !%
!%
=I6(I"6>%
!
!
!
!
!
!
!
28:(?5A<$?8%:?%:+6%8):A(6%?J%'48:)<$<%(6#(6'68:)$?8';%%Q/),7?>1%OR%,"8A:6'S%
28:(?5A<$?8%:?%:+6%,?(#+?@?H41%'48:)T1%)85%@6T"<)@%'6,)8$<'%?J%3"85"%)85%E(5A;%%
Q*+)(,)1%UN%,"8A:6'S%
.+6%,?(#+?@?H"<)@%(6#(6'68:)$?8%J?(%3"85"%)85%E(5A1%"8<@A5"8H%68<?5"8H%"''A6'1%
:?D68"V)$?81%#)(:W?JW'#66<+%:)H'1%)85%,?(#+?@?H"<)@%(6#(6'68:)$?8;%%Q*+)(,)%)85%
/),7?>1%MN%,"8A:6'S%
.+6%56#68568<4%(6#(6'68:)$?8%Q!*S%J?(%3"85"%)85%E(5A%'48:)TX%#("8<"#@6'1%
(6#(6'68:)$?81%)85%6T),#@6';%%Q*+)(,)1%MR%,"8A:6'S%
.+6%@6T"<)@%'6,)8$<%(6#(6'68:)$?8%QYKS%J?(%3"85"%)85%E(5AX%#("8<"#@6'1%
(6#(6'68:)$?81%)85%6T),#@6';%%QG)"54)1%MR%,"8A:6'S%
.+6%#+()'6%':(A<:A(6%(6#(6'68:)$?8%QY*S%J?(%3"85"%)85%E(5A%'48:)TX%#("8<"#@6'1%
(6#(6'68:)$?81%)85%6T),#@6';%%Q/),7?>1%MR%,"8A:6'S%
*),#@6%"8"$)@%6T#6(",68:'%"8%3"85"%)85%E(5A%B-Y%A'"8H%:+6%3E.K;%%Q*+)(,)%)85%
/),7?>1%OR%,"8A:6'S;%
COLING 2012
Outline
Introduction
!! Some facts about Hindi and Urdu
!! Linguistic properties
!! Morphology
!! Some basic Syntax
!! Lexical semantics
!!
Hindi:Some facts
A major language of Indo-Aryan family
!! Official language of 11 Indian states: Uttar Pradesh,
Uttarakhand, Bihar, Delhi, Jharkhand, Chhattisgarh, Himachal
Pradesh, Haryana, Rajasthan and Madhya Pradesh
!! Also spoken outside India in Fiji, Mauritius, Guyana etc
!! Number of speakers who returned Hindi as their mother
tongue (in India) : 422,048,642 (41.03%) (2001, Census of
India report)
!! A large population in India who speak Hindi as their second
language
!! Script : Devanagari a syllabic script
!!
Hindi-Urdu (Hindustani)
!!
!!
!!
!!
!!
!!
!!
!!
!!
!!
!!
!!
Morphology
Nouns
!!
Number
Case
The case roles in Hindi are normally marked by postpositions.
However, Hindi nouns reflect two cases morphologically,
Direct and Oblique
!!
Case
!!
!!
Pronouns
Morphologically, like nouns, the pronouns also inflect for number and case.
Sg - dir : yaha (this), vaha (that), jo (who/which) , kaun (who.interro), kyaa (what) and
kuch (some)
Sg Obl : isa (this), usa (that), jisa (which), kisa (which.interro), koii (someone), and
kisii (someone)
Pronouns (Contd)
!!
Before ne: maiM (I) and tuu (you.sg) dont change. For eaxmple,
maiMne (I.erg) and tuune (you.erg)
!!
Before other postpositions: maiM (I) and tuu (you.sg) change to the
oblique forms, mujh (me) and tujh (you.sg). Thus, mujhko (to me) and tujhko (to
you.sg)
!!
!!
Before all postpositions: ham (we), tum (you.sg/pl) and aap (you-hon) dont
change form.
hamne (we.erg), tumne (you.erg), aapne (you-hon.erg), humko (to us), tumko (to
you.sg/pl) aapko (to you-hon).
maiM (I), tuu (you), ham (we), and tum (you) dont attach to kaa (gen)
postposition. Instead they have irregular forms meraa (my), teraa (your),
hamaaraa (our), and tumhaaraa (your)
Adjectives
!! Morphologically, an adjective is inflected for gender, number, and case as it agrees
with the following noun.
!! Postpositions are attached only to the nouns. Adjectives preceding these nouns also
have oblique form. acche laRke ne good boys erg
!! The transformations that an adjective (eg acchaa 'good') undergoes with regard to
number, gender and case are given below
Case !
Ditect
Oblique
Number!G
ender "
Sg
Pl
Sg
Pl
Masc
acchaa
acche
acche
acche
Fem
acchii
acchii
acchii
acchii
Verbs
!!
!!
Verbs in Hindi/Urdu are inflected for tense, aspect, mood (TAM) and the
agreement features of gender, number and person.
Tense, aspect and mood are mostly expressed by auxiliaries in Hindi/Urdu.
Thus, only certain moods, aspects and tense are marked in the verb forms.
Given below are some examples of various verb forms from Hindi/Urdu:
Root
ro
cry
ronaa
to cry
Habitual
rotaa
cry.hab
Perfective
royaa
cried
Causative
rulaa
rulvaa
Infinitive
Auxiliaries
!!
(a) bacce
Children_d meal
eat prog be.pl.pres
'The children are having a meal'
(b) bacce
khaanaa
khaate
rah sakte
Children_d meal
eat_nf
prog ablit
'The children can continue to have their meal'
!!
haiM
be.pl.pres
Postpositions
!!
baccoM
khaanaa le liyaa
take refl.pst
Compound Post-positions
Compound postpositions are formed by connecting the postpositions ke, kii, and
se with other words as follows:
ke anusaar
ke alaavaa
ke kaaran
ke dvaaraa
ke saamne
ke liye
kii ora/taraf
kii tarah
kii jagah
se baahar
se pahle
according to
in addition to
because of
through
in front of
for
towards
like
in place of
out of
before
Prepositions in Urdu
'ezafe' in Urdu
qabl az_waqt
'before' 'from_this'
'before' 'from_time'
'before this'
'before time'
(c) az 'from,since,for'
az raahe hamdardi,
az
sare
nau,
khaarij az bahes
'beyond' 'from' 'discussion'
(d) ta 'to,until,till'
ta waqt
'until' 'time'
'ezafe' in Urdu
!! Urdu has what is referred
to as 'ezafe'.
!! Normally marks a
genitive but is not
restricted to genitive alone
EZ: N+Adj
nasl-e-insani
'race-of-humanity'
lamha-e-aakhar
'The last moment'
EZ: N+N
daur-e-hukumat
'period-of-rule
hukumat-e-hind
'government-of-India'
EZ: Adj+N
qabil-e-rahem
'quailified for sympathy'
EZ: Adj+Adj
qabil-e-qubul
'qualified-for-acceptance'
Reduplication: A morphological
processes
!!
!!
!!
!!
!!
Full Reduplication
!!
!!
!!
!!
!!
Hindi and Urdu are both relatively free word order SOV
languages
For case marking, Hindi primarily uses postpositions.
The verb agrees either with subject or with object
Adjective agrees with the noun it modifies
Simple Transitive
trans-1:
trans-2:
trans-3:
compel.f.pst
Intransitive: Unergative
Unerg-1: !"#$ %&'()
Atif soyegaa
Atif sleep.m.sg.fut
'Atif will sleep'
unerg-2:
*!"#$ * %&+)
*Atif ne soyaa
Atif erg sleep.m.sg.pst
'Atif slept'
unerg-3:
Intransitive: Unaccusative
unacc-1:
!"#$%$ &'()$
darvaazaa khulegaa
door.m.sg.d open.m.sg.fut
*!"#$%* + &',$
*darvaaze
ne khulaa
door.m.sg.obl erg open.pst
'The door opened'
unacc-3:
compel.fut
Existential
exist-1:
Dative Subject
unacc-4:
in
moon
see(unacc).pst
clouds
in
me.dat
moon
Ditransitive
see(unacc).pst
Complement Clause
late
part
Relative Clause
rel-cl-1:
rahii
sister
who Delhi
in
stay.hab.f.sg
kal
aa
hai
prog.f.sg be.sg.pres
come.f.sg.fut
Relative Clause
rel-cl-2: !" #$ %&'() *+ ',-" ./ 0/ 12 3/
maiMne vah kitaab jo tumne dii
I.erg
that
book.f
thii
paRh
lii
refl.f.sg.pst
that
book.f
read
jo tumne dii
thii
jo
which book.f
you.erg
I.erg
read
refl.f.sg.pst
Complex Predicate
compl-pred-1:
compl-pred-2:
do
prog.m.sg
kar rahaa
prog.m.sg
thaa
be.m.sg.pst
thaa
be.m.sg.pst
Causatives
Unerg-1:
!"#$ %&'()
Atif soyegaa
Atif
sleep.m.sg.fut
'Atif will sleep'
causative-1:
causative-2:
sulvaayaa
Lexical Semantics
Semantic properties of certain verb types seem to affect the case
selection for certain arguments. For example,
!! Experiencer verbs
!! The experiencer argument takes dative case
raam ko bukhaar hai, raam ko caand dikhaa, raam ko dukh hai
'Ram' 'dat' 'fever' 'be.pres',
!!
Participatory verbs
The second argument of the participatory verbs takes 'se'
postposition
!!
karega,
References
!!Agnihotri, Rama K. 2007. Hindi, An Essential Grammar. Routledge,
London and New York.
!!Kachru, Yamuna. 2006. Hindi. London Oriental and African
Language Libtary.
!!McGregor, R. S. 1995. Outline of Hindi Grammar. Oxford University
Press.
!!Dr. Sharma, A. 1975. A Basic Grammar of Modern Hindi. New Delhi.
!"#$"%#&'
!
!
!
!
!
!
!
()*$+,-./+)'*+'*0#')1*-$#'+2'34)*1./.'$#5$#3#)*1/+)36''7819:+&;'<='9%)-*#3>'
()*$+,-./+)'*+'*0#'9+$50+?+@4;'34)*1A;'1),'?#A%.1?'3#91)/.3'+2'B%),%'1),'C$,-6''
7D01$91;'EF'9%)-*#3>'
G0#'9+$50+?+@%.1?'$#5$#3#)*1/+)'2+$'B%),%'1),'C$,-;'%).?-,%)@'#).+,%)@'%33-#3;'
*+H#)%I1/+);'51$*J+2J35##.0'*1@3;'1),'9+$50+?+@%.1?'$#5$#3#)*1/+)6''7D01$91'1),'
819:+&;'KF'9%)-*#3>'
G0#',#5#),#).4'$#5$#3#)*1/+)'7LD>'2+$'B%),%'1),'C$,-'34)*1AM'5$%).%5?#3;'
$#5$#3#)*1/+);'1),'#A195?#36''7D01$91;'K='9%)-*#3>'
G0#'?#A%.1?'3#91)/.'$#5$#3#)*1/+)'7NO>'2+$'B%),%'1),'C$,-M'5$%).%5?#3;'$#5$#3#)*1/+);'
1),'#A195?#36''7P1%,41;'K='9%)-*#3>'
G0#'50$13#'3*$-.*-$#'$#5$#3#)*1/+)'7ND>'2+$'B%),%'1),'C$,-'34)*1AM'5$%).%5?#3;'
$#5$#3#)*1/+);'1),'#A195?#36''7819:+&;'K='9%)-*#3>'
D195?#'%)%/1?'#A5#$%9#)*3'%)'B%),%'1),'C$,-'QRN'-3%)@'*0#'BCGO6''7D01$91'1),'819:+&;'
<='9%)-*#3>6'
Representing
Tokens, Morph Analysis,
POS and Chunks in
The Hindi/Urdu Treebanks
!"#$%&'(
()*+'&%,-.*&(
!!(/*012*$*3%4-$(5'10'6'&#-.*&(
!!(7!8(#-33%&3(
!!(92"&+%&3(
!!(:&#'0;42"&+(<'1'&<'&4=(-&&*#-.*&(
!!(:�-;42"&+(<'1'&<'&4%'6((
!!
!"#$%&'()"%*
*+,-".()/*
!!*011,$1*
!!
2".3",%41*
!! 5,%/-,()"%1*
*
6"7*$8(.39$:*
!!
!"#$$%#&#'($$)($$$$$'(%##$$$$$$'*##+##$$$$,*##$
-;(-*****<"=********$7>******<(%(%(******$(-?3$7@***********3(1-*
*
*
Tokenization
Represented in SSF
ADDR TOKEN
1
2
3
4
5
6
7
usa
laDake
ne
kelA
khAyA
thA
.
!"#$%&'()"%*+,--.$-++
+/.%01.()"%-+
!!
233+4.%01.()"%-+1"+5$+1"#$%&'$6+
!!+7"84".%6-+
92,:5(;(%(+<5="1;$=:-&-1$=>?+523:@&AB23(B(+<C&=3:-0;""3>+
!! 7"84".%6-+&%1$=%(33B+0"%1(&%+(+4.%01.()"%+
!! 2=$+4="6.0)@$+
!! D"=4;"3"C&0(3+(%(3B-&-+"E+1;$+8$85$=-+"E+1;$+0"84".%6-+
!! !;$+&--.$?+F;$1;$=+1"+0=$(1$+(+-&%C3$+1"#$%++
!! G$0&-&"%+
!! 7=$(1$+1;=$$+1"#$%-+
!! D(=#+1;$+;B4;$%+(-+HIJ,KH+
+
!"#$%&'()*+,-,&)(.&-/,&01$#1,1(/)2"(&&
'af' defines the composite attribute consisting of root, category, gender, number,
person, case, tam (tense,aspect,modality)/vibhakti(case marker), suffix
ADDR_ TKN_
1
2
3
4
5
6
7
usa
laDake
ne
kelaa
khaayaa
thaa
.
OTHR
<fs af=vaha,pr,,,>
<fs af=laDakaa,n,m,sg,3,o,,>
<fs af=ne,psp,,,,,,>
<fs af=kelaa,n,m,sg,3,o,,,,,>
<fs af=khaa,v,m,sg,any,,yaa,>
<fs af=kelaa,v,e,,,>
<fs as='&STOP,punc,,,,,'>
!"#$%&''()'$$
!"#$%!&'(!%)*+,-+!)./0-,.!!
!!
!%/-)1!23!-)*+!
!!
ADDR TKN
1
2
3
4
5
6
7
usa
laDake
ne
kelA
khAyA
thA
.
OTHR
CAT
PRP
NN
PSP
NN
VM
VAUX
SYM
<fs af=vaha,pron>
<fs af=laDakA,noun>
<fs af=ne,psp>
<fs af=kelA,noun>
<fs af=KA,verb>
<fs af=kelA,verb>
<fs as='&STOP,punc,,,,,'>
!"#$%&$'((
Chunking is introduced to save the effort in manual tagging
!! Dependency relations are marked between the chunk heads
!! Chunking restructures the tree, i.e., the value of ADDR_ will change)
!!
ADDR_
1
1.1
1.2
1.3
2
2.1
3
3.1
3.2
4.
4.1
TKN_
((
usa
laDake
ne
))
((
kelA
))
((
khAyA
thA
((
.
))
CAT_
NP
PRP
NN
PSP
NP
NN
VG
VM
VAUX
BLK
SYM
OTHR
<fs af=vaha,pron>
<fs af=laDakA,noun>
!"#$%&''
<fs af=ne,psp>
<fs af=kelA,noun>
<fs af=KA,verb>
<fs af=kelA,verb>
<fs as='&STOP,punc,,,,,'>
!"#$"%#&'
!
!
!
!
!
!
!
()*$+,-./+)'*+'*0#')1*-$#'+2'34)*1./.'$#5$#3#)*1/+)36''7819:+&;'<='9%)-*#3>'
()*$+,-./+)'*+'*0#'9+$50+?+@4;'34)*1A;'1),'?#A%.1?'3#91)/.3'+2'B%),%'1),'C$,-6''
7D01$91;'EF'9%)-*#3>'
G0#'9+$50+?+@%.1?'$#5$#3#)*1/+)'2+$'B%),%'1),'C$,-;'%).?-,%)@'#).+,%)@'%33-#3;'
*+H#)%I1/+);'51$*J+2J35##.0'*1@3;'1),'9+$50+?+@%.1?'$#5$#3#)*1/+)6''7D01$91'1),'
819:+&;'KF'9%)-*#3>'
G0#',#5#),#).4'$#5$#3#)*1/+)'7LD>'2+$'B%),%'1),'C$,-'34)*1AM'5$%).%5?#3;'
$#5$#3#)*1/+);'1),'#A195?#36''7D01$91;'K='9%)-*#3>'
G0#'?#A%.1?'3#91)/.'$#5$#3#)*1/+)'7NO>'2+$'B%),%'1),'C$,-M'5$%).%5?#3;'
$#5$#3#)*1/+);'1),'#A195?#36''7P1%,41;'K='9%)-*#3>'
G0#'50$13#'3*$-.*-$#'$#5$#3#)*1/+)'7ND>'2+$'B%),%'1),'C$,-'34)*1AM'5$%).%5?#3;'
$#5$#3#)*1/+);'1),'#A195?#36''7819:+&;'K='9%)-*#3>'
D195?#'%)%/1?'#A5#$%9#)*3'%)'B%),%'1),'C$,-'QRN'-3%)@'*0#'BCGO6''7D01$91'1),'
819:+&;'<='9%)-*#3>6'
!"#$%&'(
!
!!!"#$%$%#$!&'#((#)*#+!,'#(-./'0!1!23-!
&'#((#)*#+!4/5-+!67-5!%$!83-!9%$5%:;'56!
8'--<#$07!
!!
=/(-!<#7%*!*/$*->87!
!=/(-!9%$5%!*/$78'6*)/$7!
!!
?#67#)@-7!
!! ?/A/'5%$#)/$!
!! ;$#**67#)@-7!
!! B-+#)@-!*+#67-7!
!!
!?/$*+67%/$7!
!!
!"#$%&'()%"*
!
!!!"#$$%&'(!)!*'$!+,!-.$!/+0-!1/2+#-&'-!
31'451067#$0+5#7$08!
!!!9631-:!1'!;+50!<=>!-&0(0!057.!&0!2'4?!
'&-5#&3!3&'45&4$!5'@$#0-&'@1'4!$-78!
!!!=1'451067!1',+#/&6+'!$'7+@$@!&-!@1A$#$'-!
3$;$30!057.!&0!/+#2.+3+417&3?!0:'-&767?!
0:'-&767+)0$/&'67!B@$2$'@$'7:C8!
!
!"#$"%&'('#$'#)*%+,''-.#/%
%
0%+1'%23,(45%
6'75%.,8)9'5%:;</%%
!! +34,"5=%.,8)9'5%>;?:</%
!! 23#@',5A.83#.9%$.A.%>;?></%
!!
%&'('#$'#)*%B,.==.,%C,.='73,/%D%E.#"#".#%
F,.==.8).9%=3$'9%
%
!!
!"#$%&'('(&'$)*&++&*$
,'-(&'$.&'/0&/12$
!!$3(4"$+5*6"5.5/#$
!!$31.&781.#$91:(;.1$<5*-$5*-1*$
=5*$1:&+6.1>$
!"#$!%%!!#&'!(!#)'!!*!!####'!+#
####$?4"(.-@$$$?A*0(B@$$$?1&BC"&;@$?6*12@$
$"#&'!(!#$!%%!!#)'!!*!!#'!+#
%"#&'!(!#)'!!*!!#'!+#$!%%!!#
,"#$!%%!!#)'!!*!!#'!+#&'!(!#
#
!"#$#$%&'()"**")'
'
!"#$%&!#'()*&!+,,!-./.!
!!!0%%12!$(!3'(45&%!#!6(738%$%9!7#:57#88;!6(*652%!
#*&!$<%('%=6#88;!6(*252$%*$!#*#8;252!(>!0#*21'5$!
?'#77#=6#8!2$')6$)'%!
!!!-#2%&!(*!23(1%*!>('7!
@A53#'21;9!BCCDE!
!
!!!F(6)2%2!(*!8#*?)#?%!#2!#!7%#*2!(>!
6(77)*56#=(*!
!
!!
!"#$#$%&'()"**")'+,#-.'
'
/)0"-&'"'&0#-0#+0'"&'"'&0)$0&',1'*,.$20)3*,.$20.'
)04"5,#&'
!!'670)8'&0#-0#+0'9"&'"':)$*")8'*,.$20.';<0#0)"448'
"'70)=>'
!!'?04"5,#&'=0-@00#'70)=&'"#.'-90$)':")5+$":"#-&'
+"440.'AB")"B"C'
!!'D-90)')04"5,#&'E'&F+9'"&')0"&,#G':)F:,&0G'
<0#$570'0-+'
!!'/90')04"5,#&'")0'0H:)0&&0.'-9),F<9'0H:4$+$-'
*")B0)&'+"440.'%7$=9"B5%'
'
!!
"#$%&#!'()&)*!+,)!-'./!
!
opened
!
!
k1
k2
!
!
Sabina
lock
!
the
!
!
K1 (Karta) : the doer! of the action (the locus of activity)
!
!
opened
k1
sabina
K3 (karaNa) : instrument
k2
k3
lock
key
the
this
opened
k7t
Yesterday
k1
Sabina
k2
k7p
k3
lock
key
home
the
this
my
opened
k7t
k1
yesterday lock
the
k3
key
this
!"#"$%&'(&)*+$,%-%&
L1 Semantic relations : karakas, eg
raama karta
raamaH (Sans)!
raama (Hindi)
raamudu (Telugu)!
!"#$%&'()$
!! %&#*+$,-,)./0/$
!! 1!2$3,440-4$
!! 5'(-67.$80-08,)$9&-/63"(-3/$:9+"-;/<
=,4/>$,-'$3+(0#$+(,'/$
!! $%,#;$3+($#(),6&-/$,9#&//$9+"-;/$:+(,'$
3&$+(,'$#(),6&->?$
!! @+"-;A0-3(#-,)$'(*(-'(-90(/$,#($)(B$
"-/*(90C('$
!! D+($3#((/$,#($7")).$(E*,-'('$
,"3&8,69,)).$$
!"#$%&'()*+$
!"#$$%&$'($$%&)$$**%&$)+,$%-)$.$%%
/)$$,$$%)$*%%
$
,-$
!"#$$0121%%&$'($$033%&)$$**044%%
&$)+,$056%-)$.$044%%/)$$,$$078%)$*079:;%%
%
<=%
>>!"#$$0121%%&$'($$033%!"##$$044??041%%
>>&$)+,$056%%"#,??041%%
>>'"##(##078%)$*079:;??07@%
%
!"#$%&'()*+,-...(
!!"#$%%&'('))*%+,%%&--)!"##$$&..//&.'))
!!*%012%&34)%"#&#&..//&.'))
!!'"##(##&56)0%7&589://&5;)
)
)))!2</))))))=0%%
) ) )!2>/)))))))=0%%)
)
)
)
)))*0%%77))))))?0%@%))))*0%%77)))))))))?0%@%)
)
)
))))))))))))))))))))))))"#$%%))*%+A%%))*%012%)
!"#"$"%&'(")*+,%
%-.#'/0%1"#)/.1"+0,%.+%"+%"/)*+2'3'+0%
!!
%45+0"/)/*6,'7"+)/%
%89'%$"#0"%"+:%$"#7"%*;%"%3'#<%"#'%:'0'#7.+':%<5%09'%3'#<=,%
,'7"+)/,%
!!%>'#<%:'+*0',%"+%"/)*+2'3'+0%
!!%?+5%"/)*+%.,%"%<@+:('%*;%,@<6"/)*+,%
!
!
"#$%&#!'()&)*!+,)!-'./!0%+,!+,)!/)1!
2,)!/)1!'()&)*!+,)!-'./!
2,)!-'./!'()&)*!
!
!!
!!
!"#$%&'()*+),-")."/0)
!! 1)."/0$2)/**,)3"%*,"(4)
5-")$'&.6,7)
"! 5-")/"(82,)
)
!"#$%&'())*'
"!
!! 9*'8()*+)$'&.6,7)4)!"#$"%
!! 9*'8()*+)/"(82,)))4)!"#&"%
%+,-.*/'
#"01&*'
!"#$"%&%!"#'"%
$!"#$%!
!!
!"#$%&'$&(#)#*$+"#$,&-.$
"!
"!
./$0$!"#$"%
.1$0$!"#'"%
./$
.1$
%
!!
&"'!
!"#$"(%!"#'"%2&3#43#2$
-&55#2(&)*$+&$67#)+8+"#3#$
"!
(")*!
9&+$6,:6'2$
$
)*+%,--#%%-.+/+,%
"! ;!"#$*&&5;$<2$.65+6$
"! !"#$2#)+#)-#$"62$)&$#=(,<-<+$.6536$
$
!"#$%&'()*+$+,-.)/)0+(1+2(&3+
+
,-.)/)0+(1+2(&3+
+
+
+
++++++++++4)*.5')0+%)6+++++3.7+-5.**/)0
+2%8&9++:(;/)0+
+++++8"5)/)0+%+3.7+++++%)6+8"5)/)0+++++++++++%)6+2(&3+(-.)/)0+
++++++<%&'()=>++++ +++89.+2.;.5+++++++++++++++<%&'()+?>+
++++++++++++++++++++++++++++++++++++++<%&'()+@>+
+
!"#$%&'()*+$+,-.)/)0+(1+2(&3+
++!"#$%
!"#$%
34+
35+
&!'%
(!)*%
34+
36+
*#'%
*#'%
35+
(!)*%
!"#$%
34+7+!"#$"%&'()#*+%
35+7+!"#,"%&"-).$)'*+%
36+7+!"#"/"%&0/1$#2,)/$*+%
34+
(!)*%
!"#$%&
&!"'&()*+,&+-&.+/',0,1.&,+23(445&2'6#02'$&(,&(1',*7'&/(2*)0/(,89&:+%&
!!
!
"#$%&#!'()&)*!+,)!-'./!
!
;+<'7'2%&
=&!"'&$/'(>'2&3(5&?')0?'&,+8&8+&'@/2'$$&8"'&2+4'&+-&8"'&(1',89&;',)'%&
!
0,)!/)1!'()&)*!+,)!-'./!
&
!!&!"'&.>(2(A(.&B0,$82#3',8C&0$&2(0$'?&8+&8"'&2+4'&+-&.>(28(.&B?+'2&D&>(2(A(D>(2820C&
!
0,)!-'./!'()&)*!
!
=&!"'&.>(23(.&&0$&2(0$'?&8+&8"'&2+4'&+-&.>(28(.&B?+'2&D&>(23(D>(2820C&
!"#$%&.>(28(.&+2&8"'&+8"'2&>(2(>(&2+4'$&)(,&.$"0E.&?'/',?0,1&+,&<"(8&8"'&$/'(>'2&
<(,8$&8+&'@/2'$$&B707(>$"(C&
!!&F"0)"&$#GD()*+,&8"'&$/'(>'2&<(,8$&8+&-+)#$&+,9&
&
!"#$%#&'()*+,#+-.+!"#$#%&'(%%)*!
!! /0#&1)(#+,#+2#)#2,()("#$%#&'()4+,#+-.+)
5$&-24"$+,()$&#)$((46+#7)0$&4.8()	$-.+()$22.&74+691)
"%)!+!!,-./.0!1(.!2,3&!4$1(!"#$%&'()+!
"5)!+6!%7!'89.!"#$%&'()!4$22!,-./!1(.!2,3&+!
!
"! :%#1')6#,()$((46+#7)&%91%!"$/!5):!&%9%/%!"$/!%)!;$(#7).+))
<=$,),=#)("#$%#&)<$+,(),.)#>"&#(()
"!
!! !1+,$>)#2,()#$#%&'(%!
!"#$"%#&'
!
!
!
!
!
!
!
()*$+,-./+)'*+'*0#')1*-$#'+2'34)*1./.'$#5$#3#)*1/+)36''7819:+&;'<='9%)-*#3>'
()*$+,-./+)'*+'*0#'9+$50+?+@4;'34)*1A;'1),'?#A%.1?'3#91)/.3'+2'B%),%'1),'C$,-6''
7D01$91;'EF'9%)-*#3>'
G0#'9+$50+?+@%.1?'$#5$#3#)*1/+)'2+$'B%),%'1),'C$,-;'%).?-,%)@'#).+,%)@'%33-#3;'
*+H#)%I1/+);'51$*J+2J35##.0'*1@3;'1),'9+$50+?+@%.1?'$#5$#3#)*1/+)6''7D01$91'1),'
819:+&;'KF'9%)-*#3>'
G0#',#5#),#).4'$#5$#3#)*1/+)'7LD>'2+$'B%),%'1),'C$,-'34)*1AM'5$%).%5?#3;'
$#5$#3#)*1/+);'1),'#A195?#36''7D01$91;'K='9%)-*#3>'
G0#'?#A%.1?'3#91)/.'$#5$#3#)*1/+)'7NO>'2+$'B%),%'1),'C$,-M'5$%).%5?#3;'$#5$#3#)*1/+);'
1),'#A195?#36''7P1%,41;'K='9%)-*#3>'
G0#'50$13#'3*$-.*-$#'$#5$#3#)*1/+)'7ND>'2+$'B%),%'1),'C$,-'34)*1AM'5$%).%5?#3;'
$#5$#3#)*1/+);'1),'#A195?#36''7819:+&;'K='9%)-*#3>'
D195?#'%)%/1?'#A5#$%9#)*3'%)'B%),%'1),'C$,-'QRN'-3%)@'*0#'BCGO6''7D01$91'1),'819:+&;'
<='9%)-*#3>6'
!"#$%&'()"*&+,%(-"./"0"+1&,2+(32/(
4$+5$(6(7/58(9(./$+%$.'"0:(
/"./"0"+1&,2+(&+5(&+&';0$0(
<0=>$+$(?&$5;&(
7+$@"/0$1;(23(A2'2/&52:(B28'5"/(
()!
.)!
:)!
?)!
A)!
!"#$%#$&'
'
*"+,-+"#'
/#$0"1234#5'60"78-#9'
;0-<%'=>%'1%=#4+"#'
@4#14'60"78-#9'
B4#524&+3'6C%#"<%#-'
!"#$%&$&'()*+,$%*-./()+.*$%(0./1)*12$
! 3()4%*'$)*$)51.()+,$65'&+.*$)*&7'/%*4$&#&1'($
! !".$,/')1'8$1"'$9/&1$':',+;'$0.<%.$;),,%*'2$
! =7.$0.&&%><'$,".%,'&?$
! @',1.*$A%,B%*&.*$,/')1'8$1"'$9/&1$8%&0.&)><'$&#/%*4'$
-./$5&'$7%1"$1"'$()&&$)8(%*%&1/)+.*$.-$1"'$9/&1$
':',+;'$0.<%.$;),,%*'$
! ="'$9/&1$':',+;'$0.<%.$;),,%*'$7)&$,/')1'8$%*$CDEF$>#$
G.*)&$H)<B$)1$1"'$I*%;'/&%1#$.-$J%K&>5/4"$
!"#$%&'()*+,%
! !*"%)#+'(+$%(*+%-#,(%+.+)/0+%1"23"%0'))34+5%
! 6+)("4%73)834,"4%)#+'(+$%(*+%-#,(%$3,1",'92+%,:#34;+%
<"#%=,+%>3(*%(*+%?',,%'$?343,(#'/"4%"<%(*+%-#,(%
+.+)/0+%1"23"%0'))34+%
! @*+%-#,(%+.+)/0+%1"23"%0'))34+%>',%)#+'(+$%34%ABCD%9:%
E"4',%F'28%'(%(*+%G430+#,3(:%"<%H3I,9=#;*%
!"#$%&'(
! )*+(,#-".-/(.*-(0#$.(-1-,23-(4+5%+(3",,%&-6(
! 78-,.+&(9%,:%&$+&;(,#-".-/(.*-(70#$.(/%$4+$"<5-(
$=#%&'-;(>+#(?$-(@%.*(.*-(A"$$("/A%&%$.#"2+&(+>(.*-(
0#$.(-1-,23-(4+5%+(3",,%&-(
! 7B*-(0#$.(-1-,23-(4+5%+(3",,%&-;(@"$(,#-".-/(%&(CDEF(
<=(7G+&"$(H"5:;(".(.*-(I&%3-#$%.=(+>(!%J$<?#'*(
!"#$%&'()*+"(+$,"++-%.(
! /0*('1"$2"3(20"(4152("6"'&7"(8*+-*(7$''-%"9(
! :;"'2*%(<-'=-%5*%$."%2>('1"$2"3(20"(:4152(3-58*5$,+"(
5?1-%."20"#">(@*1(A5"(B-20(20"(#$55($3#-%-521$&*%(*@(
20"(4152("6"'&7"(8*+-*(7$''-%"(
! :C0"(4152("6"'&7"(8*+-*(7$''-%"20"#">(B$5('1"$2"3(-%(
DEFG(,?(:H*%$5(!$+=$."%2>($2(20"(I%-7"15-2?(*@(J-K5,A1.0(
!"#$%&'()$*)$+,($-&%,+$./)0(-$
! 1($/((2$)(3./45$&/67-3.47/$+7$8-(6(-$+,($-&%,+$
./)0(-$
! 9,($+,(3($76$5-(.+($),7*:2$;($<+,($=-)+$(>(54'($
87:&7$'.55&/(?$
! 9,($+,(3($&/$+,($=-)+$)(/+(/5($0.)$<+,($=-)+$
2&)87).;:($)@-&/%(?$
! 1($5./$=:+(-$7*+$+,($0-7/%$./)0(-$
!"#$""%#&"'($)*#+$,-.'()-$#
#
! /-#0$%#-12#(3-12#"4"$2&#($%#25"+.#6(.)*+6($2&#
! /-#*(621."#&"'($)*#+$,-.'()-$#(*.-&&#&7$2(*)*#
4(.+()-$#
!"#$""%#&"'($)*#+$,-.'()-$#
#
! /-#0$%#-12#(3-12#"4"$2&#($%#25"+.#6(.)*+6($2&#
! /-#*(621."#&"'($)*#+$,-.'()-$#(*.-&&#&7$2(*)*#
4(.+()-$#
!"#$%&'()%*+,#$&+%(
! (!"#$%&'()%*+,#$&+%($-+./(0",-1($%2(
3$,&')3$%/1("43,"11"2(/5,+.65(1"#$%&'(,+7"1(
(
! 86"%/9(:43",)"%'",9(;5"#"9(<"1.7/("/'=(
(
! >+?"0",9(2)@'.7/(/+(5$0"($(1/$%2$,2(1"/(+*(
/5"#$&'(,+7"1(
!"#$#%&'#()*+(,)
! !"#$#%&'#()*+(,)-!"#$*+(,.)$"#/&01%)+)2+3)4#)
5+""3)#64)71(1"+8)$6"$#%1)91:+('5)"#81)8+;188&(7)
! <)!"#$*+(,)&%)+)8+"71)!""#$!$%&'5#"$6%)#=)
$"10&5+41>+"76:1(4)&(=#":+'#()
! <)%14)#=)%1:+('5)"#81%)&%)01?(10)=#")!"#$%/1";)
! <)%3(4+5'5+883)$+"%10)5#"$6%)&%)4@1()4+7710)2&4@)
/1";>%$15&?5)%1:+('5)"#81)&(=#":+'#()
!"#$%&'()*"&+,)-.,/)
! !"#$%&'()0,-',/)/,+&'12)"#.,/)#')&)3,"45465
3,"4)4&/7/)
! 897/)7/)0,-',0)7')&)3,"4).,:72#')2#'/7/1';)#<)!"#$%&
'(%)&
! =&29)$",072&>,))?7..)9&3,)&)/,>)#<)"#.,/)&//#27&>,0)
?7>9)&)07/1'2>)@/&;, ))
! A)$#.6/,+#@/)$",072&>,)2&')9&3,)/,3,"&.)"#.,/,>/)
?7>97')7>/)<"&+,)-.,)
!"#$%&'()$#
! *+,"#-."/0#1,$#2$))#
#
#
!"#$%&'(
)*+,(-./#0(.1(2,33(
!-/3#
4&50$-#+6#-."/."/#
!-/7#
8,."/#-5"/#
!-/9#
:."/#6+-#
!"#$%&'()$#
! *+,"#-."/0#1,$#2$))#
! 3&))#&0($"#1-$$0#-."/#1,$#)&4$#
#
#!"#$%&'( )*+,(-./#0(.1(2,33(
!-/5#
6&70$-#+8#-."/."/#
!-/9#
3,."/#-7"/#
!-/:#
;."/#8+-#
!"#$%&4(
5.(-/!!./#0(
!-/9#
<7--+7"=."/#$">1?#
!-/:#
<7--+7"=$=#$">1?#
!"#$"%&'()*+#,%
! -##(.+/#0%!"#$"%&'()*+#,%"#1(2134%.5'33%4.3)46%
! 7'3+/(#%(8%8'+93%:234%
! ;9).<%+'0=93#.%"#43'/(#%
! >39+#/?%'(23%2+@322"#0%
%%
!"#$%&'(%)&&*+"&,-./-&
! 01+&234%)&+*&*"#$%&'(%)5&
! !"#$%)&*+"&)-$4(%&6%"7)&89:;&*"#$%)<&=>9&4"%/-?#2%)&@&
! !"#$%)&*+"&.+$-.#()&-.&?+$4(%A&4"%/-?#2%)&8B:=;<&
BC>D&4"%/-?#2%)@&
&
!"#$%&'()*"+,$-&
! .(/#01,2&3,-+($-&4&$%#+-&/5&+"#$%&1()*"+,$-&
! #(/&67(/##+7&,*88&1()*"+,$-9&(+:/;+(1<8+&5(/"&73-:/*(-+&:/,$+=$&
! .>?6&+"#$%&-*<@+:$-&/5&,/,AB,3$+&:/"#8+"+,$&1,7&17@*,:$&:81*-+-&
! >!C.>?6&)1#-&3,(D:3#318&(+81D;+&:81*-+-&
! &E'.6&+837+7&1()*"+,$-&3,&:/A/(73,1$+7&:81*-+-&
! .>?&1,7&>!C.>?&1(+&3,-+($+7&1*$/"1D:188%&
! E'.&1,7&#(/&1(+&3,-+($+7&"1,*188%&
!"#$%&'()*&+,-.)
!"#$%&%'()&*"#%+,-(
!"#$%&%'()&*"#%+,-(./,0(1"+234+(,5*-(
/01/2)3&4,-")
/01/56782))9':;"-<.)<&4,-")
/01=2)/+-'.>)-?$-";-'<-")
/01=56782)9':4<-:)<&4,-")
/01@2)*A-B->)$&C-'.)
/01=51DE2)3&4,--)F;.A)&)G"-<;$;-'.H)"#I-)
/01J2)0-<;$;-'.)
/01J5/*02)/K";L4.-)
/01M2)9',."4B-'.)
/01J51DE2)1#&I)
/01J58DN2)8#4"<-)
/01J5ED32)E#<&C#')
/01J5O902)O;"-<C#')
!"#$%&'()*&+,-.)
!"#$%&'()'*+,&-./(
/0123*2!)4)*-5$#"&6)
/0123270)4)2&''-"))
/012389:))4)8#;&<#')
/0123!0!4)!="$#,-)
/0123:/>)4):&=,-)
/0123?@A)4)?B,;#=",-)
/0123/?C)4)/DE-"F)
/012327A)4)2-&',)
!"#$%"&'()*+,#-.,#/)
!
!
!
!
!
!
!
0".*1,)23/#&"'4,)
5#/((%&/'4,)/#6)5#,3$/'4,)
78"&2,#'/1)
9/'4,)&%:;,(2)
9"23/#&"'4,)
</%&/'4,&)
<-.*1,8)=3,6"(/2,&)
!"#$$%&#'()*+*!"),-#'()*
! ./&'"$'0"*1)23))"*/"2,#"&/'()*(),1&4***
! %"#$$%&#'()&*)5-5*6%7#*809)":;*<%2#*8)=970>):****
! !"),-#'()&*)5-5*?#@&#*87#%-?:;**
! A/"-7)*#,-%B)"2*0C*%"#$$%&#'()&*2#D)&*E,-F;*
%"),-#'()&*2#D)*E,-G*
! ./#-"0&'$*2)&2&*#,)*%&)>*20*>/&'"-%/&?*
%"#$$%&#'()&*C,0B*%"),-#'()&*
! H5-5*#"/B#$I*2)&2;*$0-"#2)*01J)$2*2)&2*#B0"-*02?),&*
!"#$%&'()*%+,&
(-"++./0& &!" #$% &$'"( ) *$+' ,'-$
&& &1"2&&&&&&&&&3"",&&&)""4"256&&7%86&+""64&&4819""&
&& &:%;,%34":&&-8<9,&&&+25(4;&&&&&&&&&&&&8-&&&&&&&&&755-&&&&&&&;%%=(-"++>?@;,&
&&
&AB%;,%34":&-8<9,C&,9%&755-&D";&;%%-&)%98-4&,9%&+25(4;A&
&
&
4",.;()*.E0 &!" #$% &$'"( ) ./0!1 *$+' ,'-$
&& &1"2&&&&&&&&&&&3"",&&&)""4"256&7%86&7(*915&+""64&4819""&
&& &:%;,%34":&&&-8<9,&&&&+25(4;&&&&&&&&&&&8-&&&&&&&&7%?4",&&&&&&755-&&&&;%%=(-"++>?@;,&
&&
&AB%;,%34":&-8<9,C&F&;"D&,9%&755-&)%98-4&,9%&+25(4;A&
!"#$"%&'$(
! )*+,*(-"$(./0(/"1$(02(2034*+5(.-'(6"#$"%&'7(
! 8,,(9""(
! (:$0(!($#;""<($;''=!(4">'($04'0+'($;''=(
! 8,,(9&""(
! (:$#;""(!($#;&""<(4">'($04'0+'($;''=(!(6"#$'($04'0+'(.0(2";;("$;''=(
! ?'(*+.30,#6'(.-'(;"@';(8AB8(.0("+";1C'(6"#$'3$(
! D#@.1='$(02(8ABE(:8ABEFBGHI(8ABEFJKD<(203(
6"#$''$(
! 8AB8FJKD(203(*+.'34',*".'(6"#$'3$(
!"#$"%&'$(
)*'+,-./( ( (!"#$ %&'()
(( ( ( (0%1((((($23',""(
(( ( ( (0%1((((((($4''5676$,61#8(
(( (
(90%1(:;44($4''59(
<"#$"%&'-./
(( (
!!!!!!!!!
(((((((((
(
!
(
(""3""(*'((0%1(((=2(((($#4""3""((
!
!7";>(('+,((0%1(("<<((($4''56<"#$65$8(
(
(?@A'(7";>(<"#$'>(8A'(<A;4>(82($4''5B(
(
<"#$"%&'-C/ (/)0 + !*) 1 !"#$ ,& %-.2)*)
(( ( ( (7""D(*'(((""3""($'((0%1((=2(((($#4&""3""((
!!!!!!!!!!!
!!!!!!!!!!!
(
!
!
!
!
!728A'+('+,(((7";>(((((E3((0%1(((("<<!!!$4''56<"#$65$8((
!?@A'(728A'+(7">'(8A'(7";>(82(<"#$'(8A'(<A;4>(82($4''56B(
!"#$"%#&'
!
!
!
!
!
!
!
()*$+,-./+)'*+'*0#')1*-$#'+2'34)*1./.'$#5$#3#)*1/+)36''7819:+&;'<='9%)-*#3>'
()*$+,-./+)'*+'*0#'9+$50+?+@4;'34)*1A;'1),'?#A%.1?'3#91)/.3'+2'B%),%'1),'C$,-6''
7D01$91;'EF'9%)-*#3>'
G0#'9+$50+?+@%.1?'$#5$#3#)*1/+)'2+$'B%),%'1),'C$,-;'%).?-,%)@'#).+,%)@'%33-#3;'
*+H#)%I1/+);'51$*J+2J35##.0'*1@3;'1),'9+$50+?+@%.1?'$#5$#3#)*1/+)6''7D01$91'1),'
819:+&;'KF'9%)-*#3>'
G0#',#5#),#).4'$#5$#3#)*1/+)'7LD>'2+$'B%),%'1),'C$,-'34)*1AM'5$%).%5?#3;'
$#5$#3#)*1/+);'1),'#A195?#36''7D01$91;'K='9%)-*#3>'
G0#'?#A%.1?'3#91)/.'$#5$#3#)*1/+)'7NO>'2+$'B%),%'1),'C$,-M'5$%).%5?#3;'$#5$#3#)*1/+);'
1),'#A195?#36''7P1%,41;'K='9%)-*#3>'
G0#'50$13#'3*$-.*-$#'$#5$#3#)*1/+)'7ND>'2+$'B%),%'1),'C$,-'34)*1AM'5$%).%5?#3;'
$#5$#3#)*1/+);'1),'#A195?#36''7819:+&;'K='9%)-*#3>'
D195?#'%)%/1?'#A5#$%9#)*3'%)'B%),%'1),'C$,-'QRN'-3%)@'*0#'BCGO6''7D01$91'1),'819:+&;'
<='9%)-*#3>6'
!"#$%&'()#*+)*#&',&-#&%&.)$/0.'
12&.',$3402'
556(7'508*349$':.9;&#%9)<'
#$3402=++8%>+08*349$>&?*'
!"#$%&'()#*+)*#&',!(-'.&/#&%&0)$120'30'
)"&'43053'$05'6#5*'7#&&8$09%'
! :&;3%&5'8<'.$=&%"'>"$?@'603;&#%3)<'2A'
B$%%$+"*%&?%@'CD"&#%)''
! C%%3%)&5'8<'C00$"3)$'E$#*53'$05'FG&0'.$D82G'
! :&;&H2/&5'30'+20=*0+120'G3)"':('$05'!>'
! I0%/3#&5'8<'J"2D%9<$0')#$53120'
!"#$%&'()*+,'&+-.+
! /0'12$3")+4&'%&"15+
! 6'78"9:*+;3+#<"=12+";'(9+<")%("%:+"#>(=2=7')+=)+
#0=<*&:)+
! ?:8:<'4+"+90:'&3+',+23)9"@+2(#0+90"9+23)9"@+',+"+
<")%("%:+#")+;:+:@4<"=):*+;3+
! A")%("%:B()=8:&2"<+4&=)#=4<:2+
! A")%("%:B24:#=C#+4"&"1:9:&2+
! -.+,'&+D=)*=+=)24=&:*+;3+/0'12$3")+4&'%&"1E+;(9+
)'9+,'<<'F=)%+")3+24:#=C#+/0'12$3")+"44&'"#0+
!"#$%&'($)%$*+,#&-.&'/&
! '/&(,*(,#,)0#&(,+"1-)&2,03,,)&!"#$%&!'
()"*$%&+",&)-./"0+'1+).%+.)"&4$)0,(."%,&0-&
+,5$%-)6&")7&1.)2&%"'34)*'4)*")'4$)0,(."%,&0-&
*8-)-+-9:&")7&#,;")1%#<&(-=98+:&#*,">$)96&
! ?8,#,&03-&+,@,+#&"(,&(,+"0,7&2:&7,($@"1-)#A&
! B-(7#&")7&%-)#10=,)0#&;-@,&")7&+,"@,&+)&%"1'
! ?(")#.-(;"1-)"+&9(";;"(&
! C-)-#0("0"+&(,*(,#,)0"1-)&
! D-0&=)+$>,&E)9+$#8&',))&?(,,2")>F&
&
!"#$%&$'())*+",-.)'/0-*1'
2#"3#)#.1/,-.'4/5#'06'7!'
! 783/)#')13*$1*3#'
! 9-,-.'-:';#<%$/;'8#/5)'=%18'"3->#$,-.)'?@A0/3'
18#-36B')-31'-:C'/.5'/))-$%/1#5':*.$,-./;'
"3->#$,-.)'
! 9-*.)'=%18'"-)1"-)%,-.)'
! D#30)'=%18'/*<%;%/3%#)'/.5'$-+";#+#.,E#3)'?!"C'
! F%./36'03/.$8%.G'
! H8#-3#,$/;'3#/)-.)'
! H-'0#'5%I#3#.1':3-+'J!'
!"#$"%&'()*+,
! !"#$%&'&()*+,*-*#$%'.#-(%#/(0,**1%#23#4(3#(5*#*,%6(
! -(./0*,!*(12,34/5,-(6#%42,(57,8/",9"(:,;"5&<"0=>,?*/5%6/5(2,@5($+0/02,(57,
-/)'/0/5A(=%50B,C57/'0A(57"5&,D%5E/'0"%5,#/A4//5,F'//#(5G0:,,H5,!"#$%%&'()*+#,+
-./01!+2344:,
! 34/5,-(6#%4:,IJKJ:,F*/,0"6)$/,A'<A*,(#%<A,7/)/57/5>+,(57,)*'(0/,
0A'<>A<'/,'/)'/0/5A(=%50:,H5,!"#$%%&'()*+#,+055/162343:,
! 8/",9"(,(57,L('A*(,?($6/':,IJJK:,D%5E/'=5&,M/)/57/5>+,NA'<>A<'/0,A%,?*'(0/,
NA'<>A<'/0:,H5,?'%>:,%O,A*/,P<6(5,;(5&<(&/,F/>*5%$%&+,D%5O/'/5>/,
QP;FRIJJKS,2,N(5,M"/&%2,D@:,
! 07*(83#/3(%#/(9,/:(0,**1%#2-(
! L('A*(,?($6/'2,-(./0*,!*(12,!*<E(5(,T('(0"6*(52,34/5,-(6#%42,M")=,
L"0'(,N*('6(2,(57,8/",9"(:,IJJU:,P"57",N+5A(VB,@55%A(=5&,M/)/57/5>+2,;/V">($,
?'/7">(A/R@'&<6/5A,NA'<>A<'/2,(57,?*'(0/,NA'<>A<'/:,H5,!"#$%%&'()*+#,+
-/70623389+:;<+-(;%"(=>#(=?+/#(,%"%($%+#(+0=;@"=?+1=()@=)%+!"#$%**'()2,
P+7/'(#(7:,
! 8/",9"(2,34/5,-(6#%42,-(./0*,!*(12,L('A*(,?($6/'2,(57,M")=,L"0'(,N*('6(:,
IJJU:,F%4('70,(,6<$='/)'/0/5A(=%5($,A'//#(5G:,H5,A<%+:;<+-(;%"(=>#(=?+
B#"C*<#D+#(+A"%%E=(C*+=(&+1'()@'*>$+A<%#"'%*+FA1A6:G+2,W'%5"5&/52,
T/A*/'$(570:,
!"#$"%&'()*+,
! !"#$%#&#'(#')*$+#&,#-#'./01'$
! -(.+(,!/&012,3(1(',405("62,7'06,8*9(:2,8");,<"5'(,3*('1(2,=(>5*1",!("2,(6?,
-(://@,3(6&($A,BCCDA,8/)/6?/6E+,(66%F(;%6,5E*/1/,G%',H6?"(6,$(6&0(&/5A,H6,
I'%E//?"6&5,%G,HJKL=I,2,4+?/'(#(?2,H6?"(A,
! !"#$2,134/'5$+#&,#-#'./01'$
! I(0$,M"6&5#0'+2,<('F*(,I($1/'2,(6?,<"FE*,<('E05ABCCBA,7??"6&,5/1(6;E,
(66%F(;%6,F%,F*/,I/66,N'//O!(6>A,H6,!"#$%%&'()*+#,+-./012212,3(6,8"/&%2,K7A$