Two-Stage Constraint Based Hindi Parser - PowerPoint PPT Presentation

About This Presentation
Title:

Two-Stage Constraint Based Hindi Parser

Description:

rAma Ora siwA kala Aye. Node 2 becomes potential parent (of 1) ... Note: kala' remains attached to its parent aaye' (does not show up in stage 2) rAma ... – PowerPoint PPT presentation

Number of Views:131
Avg rating:3.0/5.0
Slides: 50
Provided by: Lapt335
Category:
Tags: based | constraint | hindi | kala | kana | parser | stage | two

less

Transcript and Presenter's Notes

Title: Two-Stage Constraint Based Hindi Parser


1
Two-Stage Constraint Based Hindi Parser
LTRC, IIIT Hyderabad
2
Brief Recap
  • Broad coverage parser
  • Dependency
  • Paninian framework
  • vibhakti-karaka correspondence
  • karaka frames (basic transformation)
  • Source groups, demand groups
  • Constraints
  • Three basic constraints
  • Constraints as Integer programming equations

3
Parser
  • Two stage strategy
  • Appropriate constraints formed
  • Stage I (Intra-clausal relations)
  • Dependency relations marked
  • Relations such as k1, k2, k3, etc. for each verb
  • Stage II (Inter-clausal relations conjunct
    relations)
  • Conjuncts, relative clauses, kriya mula, etc
  • In certain cases, separates syntax from semantics
    (eg. kriya mula), in others, reduces the
    complexity.

4
Steps in Parsing
SENTENCE
Morph, POS tagging, Chunking
Identify Demand Groups
STAGE - II
Load Frames Transform
YES
Is Complex
NO
Find Candidates
Apply Constraints Solve
Final Parse
5
Stage I Types being handled
  • Simple Sentences (finite verbs)
  • Clausal arguments
  • Non-finite verbs
  • wA_huA
  • wA_hI
  • nA
  • kara
  • 0_rahe, etc.
  • Copula
  • Genitive

6
Stage - II
  • Handles
  • Conjuncts
  • Subordinating Coordinating
  • Relative clauses
  • Complex predicates
  • Basic constraints similar to Stage-I
  • Some additional constraints
  • New demand groups
  • New candidates

7
Steps (Stage II)
Identify New Demand Groups
Load Frames Transform
Output of STAGE - I
Find Candidates
Repair
Apply Constraints Solve
FINAL PARSE
8
Example Relative Clause
  • vaha puswaka jo rAma ne mohana ko
    xI hE prasixXa hE
  • that book which Ram ERG. Mohana
    DAT. gave is famous is
  • The book which Ram gave to Mohana is famous

9
Output after Stage - I
_ROOT_
main
main
hE
xI
k1
k1s
prasixXa
puswaka
k2
k1
k4
vaha
jo
mohana
rAma
10
Identify the demand group
  • xiyA give
  • Main verb of the relative clause

11
Identify the demand group,Load and Transform DF
  • jo which transformation (special)
  • Transforms the demand frame of the main verb of
    the relative clause
  • --------------------------------------------------
    --------------------------------------------------
    ----------
  • arc-label necessity vibhakti
    lextype src-pos arc-dir
    oprt
  • --------------------------------------------------
    --------------------------------------------------
    ----------
  • nmod__relc m any
    n rl p
    insert
  • --------------------------------------------------
    --------------------------------------------------
    ----------

12
Karaka Frame
Main verb of relative clause
  • vaha puswaka jo rAma ne mohana
    ko xI prasixXa hE
  • that book which Ram ERG. Mohana
    DAT. gave famous is
  • The book which Ram gave to Mohana is famous

Transformed frame for xe after applying the jo
trasformation
--------------------------------------------------
--------------------------------------------------
---- arc-label necessity vibhakti
lextype src-pos arc-dir
oprt ---------------------------------------------
--------------------------------------------------
--------- nmod__relc m any
n rl
p insert --------------------------------
--------------------------------------------------
-----------------------
New row inserted after transformation
13
Possible candidates
nmod__relc
  • vaha puswaka jo rAma ne mohana ko xI hE
    prasixXa hE

14
Output after Stage - II
_ROOT_
main
hE
k1
k1s
prasixXa
vaha puswaka
nmod__relc
xiyA hE
k1
k2
k4
rAma
mohana
jo
15
Example II Coordination
  • rAma Ora siwA kala Aye
  • Ram and Sita yesterday came
  • Ram and Sita came yesterday

16
Output of Stage - I
_ROOT_
dummy
main
dummy
rAma
Aye
Ora
k1
k7t
siwA
kala
17
For Stage II (Constraint Graph)
_ROOT_
main
rAma
Aye
Ora
k1
k7t
ccof
siwA
ccof
kala
18
Candidate Arcs
_ROOT_
main
k1
rAma
Aye
Ora
k1
k1
ccof
siwA
ccof
kala
19
Solution Graph
_ROOT_
main
k1
rAma
Aye
Ora
k7t
ccof
siwA
ccof
kala
20
Parse tree
_ROOT_
main
Aye
k7t
k1
kala
Ora
ccof
ccof
siwA
rAma
Output after Stage II
21
Finite Verb Coordination
  • rAma Gara gayA Ora vaha so gayA
  • Ram home went and he
    sleep went
  • Ram went home and slept

_ROOT_
main
main
dummy
so
gayA
Ora
k1
k1
k2
vaha
rAma
Gara
Output after Stage I
22
Karaka Frame - Ora
Finite
Ora
Ora
ccof
ccof
ccof
ccof
v_fin
gayA
v_fin
so
23
Finite Verb Coordination (Parse Tree)
_ROOT_
main
Ora
ccof
ccof
gayA
so
k1
k1
k2
rAma
vaha
Gara
Output after Stage II
24
Relative Clause Coordination
  • rAma ne vaha puswaka KarIxI jo prasixXa hE Ora
    jo saswI hE
  • Ram purchased the book which is famous and
    which is cheap

_ROOT_
main
main
main
dummy
KarIxI
hE
Ora
hE
k1
k1s
k1
k1s
k2
k1
jo
prasixXa
jo
saswI
puswaka
rAma
Output after Stage I
25
Karaka Frame - Ora
Relative Clause
n
puswaka
nmod__relc
nmod__relc
Ora
Ora
ccof
ccof
ccof
ccof
v_rel
v_rel
hE
hE
26
Relative Clause Coordination (Parse Tree)
_ROOT_
main
KarIxI
k2
k1
puswaka
rAma
nmod__relc
Ora
ccof
ccof
hE
hE
k1
k1s
k1
k1s
jo
prasixXa
jo
saswI
Output after Stage II
27
Non-Finite Verb Coordination
  • rAma Kelakara Ora KAnA KAkara so
    gayA
  • Ram having played and food having
    eaten sleep went

_ROOT_
main
dummy
so
Ora
vmod
vmod
k1
rAma
Kelakara
KAkara
k2
KAnA
Output after Stage I
28
Karaka Frame - Ora
Non-Finite
so
v_fin
Ora
Ora
ccof
ccof
ccof
ccof
v_nfin
v_nfin
Kelakara
KAkara
29
Non-Finite Verb Coordination (Parse Tree)
_ROOT_
main
so
vmod
k1
Ora
rAma
ccof
ccof
KAkara
Kelakara
k2
KAnA
Output after Stage II
30
Nominal Coordination
  • rAma Ora siwA kala Aye
  • Ram and Sita yesterday
    came
  • Ram and Sita came yesterday

_ROOT_
dummy
main
dummy
rAma
Aye
Ora
k1
k7t
siwA
kala
Output after Stage I
31
Karaka Frame - Ora
Nominal
Ora
Ora
ccof
ccof
ccof
ccof
siwA
rAma
n
n
32
Nominal Coordination (Parse Tree)
_ROOT_
main
Aye
k7t
k1
kala
Ora
ccof
ccof
siwA
rAma
Output after Stage II
33
Example
  • rAma Ora siwA kala Aye

_ROOT_
dummy
main
dummy
rAma
Aye
Ora
k1
k7t
siwA
kala
34
Steps (Stage II)
Identify Nodes
Load Frames Transform
Identify New Demand Groups
Output of STAGE - I
Find Candidates
Repair
Apply Constraints Solve
FINAL PARSE
35
Constraint Graph Nodes (Stage II)
  • Selected from the intermediate parse tree (Stage
    I)
  • Set-I (demand nodes)
  • Conjuncts
  • Nearest verbal ancestor of jo (usually just the
    parent)
  • _ROOT_
  • Children of _ROOT_ other than (1) and (2).
  • Other nodes which are added due to nodes in Set 2

36
Constraint Graph Nodes (Stage II)
  • Set-II (source nodes)
  • Possible children and parents of conjuncts
  • Possible heads of the relative clause.
  • Identification of nodes in Set-II will generally
    trigger the repair.

37
Steps (Stage II)
Identify Nodes
Load Frames Transform
Identify New Demand Groups
Output of STAGE - I
Find Candidates
Repair
Apply Constraints Solve
FINAL PARSE
38
Identify the demand group
  • Ora
  • Aye

39
Steps (Stage II)
Identify Nodes
Load Frames Transform
Identify New Demand Groups
Output of STAGE - I
Find Candidates
Repair
Apply Constraints Solve
FINAL PARSE
40
General Principles
  • Repair/Revision
  • Any node which becomes a potential child in stage
    2, its arc to its existing parent is open to
    revision
  • rAma Ora siwA kala Aye
  • Node 4 becomes potential child (of node
  • 1)
  • Its parent (node 2) is open to revision

41
General Principles
  • Repair/Revision after parse of stage I
  • Any node which becomes a potential parent must be
    re-looked at.
  • rAma Ora siwA kala Aye
  • Node 2 becomes potential parent (of 1)
  • Its child (node 4) is open to revision

42
Algorithm
  • Identify nodes of the constraint graph
  • From Set 1, and
  • From Set 2
  • Remove all outgoing edges from _ROOT_.
  • Find possible candidates for demand nodes present
    in Set 1 from Set 2
  • Parent candidate for finite verb
  • Parent and children for conjuncts
  • Children of _ROOT_
  • Convert the formed constraint graph into integer
    programming (IP) problem.
  • Solve the IP equations to get the possible
    solution parse.

43
An example
  • raama aura sitaa kala aaye
  • Ram and Sita yesterday
    came
  • Ram and Sita came yesterday

_ROOT_
dummy
main
dummy
  • Output after stage I

rAma
Aye
Ora
k1
k7t
siwA
kala
44
Identify Nodes
_ROOT_
dummy
  • Set 1 nodes

main
dummy
rAma
Aye
Ora
k1
k7t
siwA
kala
_ROOT_
dummy
  • Set 1 and Set 2

main
dummy
rAma
Aye
Ora
k1
k7t
siwA
kala
45
Constraint Graph
  • New Constraint Graph
  • Ora, Aye and _ROOT_ are the demand groups
  • Note kala remains attached to its parent
    aaye (does not show up in stage 2)

_ROOT_
main
k1
ccof
Aye
Ora
rAma
k1
ccof
siwA
46
Example
_ROOT_
main
  • Final Parse

Aye
k7t
k1
kala
Ora
ccof
ccof
siwA
rAma
47
Types of complex sentences
  • Relative clauses
  • Initial
  • Final
  • Medial
  • Conjuncts (Coordination)
  • Simple clause
  • Relative clause
  • Non-finite
  • Nominal, adjectival, adverbial

48
Some other examples
  • rAma ne vaha puswaka KarIxI jo saswI hE Ora jo
    bAjZAra meM prasixXa hE
  • samIra Ora aBay ne vaha puswaka KarIxI jo saswI
    hE Ora jo bAjZAra meM prasixXa hE
  • rAma Ora mohana ke xoswa kI baccI Aye
  • Only baccI came, or
  • Both rAma and baccI came
  • Use of gnp of the main verb, Aye vs. AI

49
  • THANKS!!
Write a Comment
User Comments (0)
About PowerShow.com