Download - Constraint Based Hindi Dependency Parser
![Page 1: Constraint Based Hindi Dependency Parser](https://reader035.vdocuments.site/reader035/viewer/2022062801/568143db550346895db06850/html5/thumbnails/1.jpg)
Constraint Based Hindi Dependency Parser
Samar HusainLTRC, IIIT Hyderabad
![Page 2: Constraint Based Hindi Dependency Parser](https://reader035.vdocuments.site/reader035/viewer/2022062801/568143db550346895db06850/html5/thumbnails/2.jpg)
Introduction
Broad coverage parser Very crucial IL-IL MT systems, IE, co-reference resolution, etc.
Attempt to make an hybrid parser
![Page 3: Constraint Based Hindi Dependency Parser](https://reader035.vdocuments.site/reader035/viewer/2022062801/568143db550346895db06850/html5/thumbnails/3.jpg)
Levels of Language Analysis Morphological analysis (Morph Info.) Analysis in local context (POS tagging) Sentence analysis (Chunking, Parsing)
Semantic analysis (Word sense disambiguation, etc.)
Discourse processing (Anaphora resolution, Informational Structure, etc.)
![Page 4: Constraint Based Hindi Dependency Parser](https://reader035.vdocuments.site/reader035/viewer/2022062801/568143db550346895db06850/html5/thumbnails/4.jpg)
Example
rAma ne mohana ko KilOnA xiyA | Ram ‘ERG’ Mohana ‘DAT’ book gave
‘Ram gave a book to Mohan’
![Page 5: Constraint Based Hindi Dependency Parser](https://reader035.vdocuments.site/reader035/viewer/2022062801/568143db550346895db06850/html5/thumbnails/5.jpg)
Example – Parsed Output
xiyA ‘gave’
KilOnA ‘toy’
mohanarAma
k2k4k1
![Page 6: Constraint Based Hindi Dependency Parser](https://reader035.vdocuments.site/reader035/viewer/2022062801/568143db550346895db06850/html5/thumbnails/6.jpg)
The design
Constraint satisfaction problem Inviolable constraints
Rule based Violable constraints
![Page 7: Constraint Based Hindi Dependency Parser](https://reader035.vdocuments.site/reader035/viewer/2022062801/568143db550346895db06850/html5/thumbnails/7.jpg)
Inviolable constraints
Structural constraints Dependency tree structure
Verbal constraints Demand frames (and transformation)
Other non-verbal lexical constraints
![Page 8: Constraint Based Hindi Dependency Parser](https://reader035.vdocuments.site/reader035/viewer/2022062801/568143db550346895db06850/html5/thumbnails/8.jpg)
Implemented 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, complex verbs, etc
![Page 9: Constraint Based Hindi Dependency Parser](https://reader035.vdocuments.site/reader035/viewer/2022062801/568143db550346895db06850/html5/thumbnails/9.jpg)
Demand Frame for Verb
A demand frame or karaka frame for a verb indicates the demands the verb makes
It depends on the verbal semantics and the tense, aspect and modality (TAM) label.
A mapping is specified between karaka relations and vibhaktis (post-positions, suffix).
![Page 10: Constraint Based Hindi Dependency Parser](https://reader035.vdocuments.site/reader035/viewer/2022062801/568143db550346895db06850/html5/thumbnails/10.jpg)
Demand Frame
It specifies what karakas are mandatory or optional for the verb and what vibhaktis (post-positions) it takes
Each verb belongs to a specific verb class Each class has a basic karaka frame
Each TAM specifies a transformation rule
![Page 11: Constraint Based Hindi Dependency Parser](https://reader035.vdocuments.site/reader035/viewer/2022062801/568143db550346895db06850/html5/thumbnails/11.jpg)
Transformations
Basic frame rAma ø mohana ko KilOnA xiwA hE |
Transform basic frame based on the TAM rAma ne mohana ko KilOnA xiyA | rAma ko mohana ko KilOnA xenA padZA | Appropriate transformation applied
![Page 12: Constraint Based Hindi Dependency Parser](https://reader035.vdocuments.site/reader035/viewer/2022062801/568143db550346895db06850/html5/thumbnails/12.jpg)
Example
rAma ne mohana ko KilOnA xiyA |
![Page 13: Constraint Based Hindi Dependency Parser](https://reader035.vdocuments.site/reader035/viewer/2022062801/568143db550346895db06850/html5/thumbnails/13.jpg)
Karaka Frame: xe [_wA hE] (give)
![Page 14: Constraint Based Hindi Dependency Parser](https://reader035.vdocuments.site/reader035/viewer/2022062801/568143db550346895db06850/html5/thumbnails/14.jpg)
Transformation Rule – yA (TAM)
![Page 15: Constraint Based Hindi Dependency Parser](https://reader035.vdocuments.site/reader035/viewer/2022062801/568143db550346895db06850/html5/thumbnails/15.jpg)
Karaka Frame
rAma ne mohana ko KilOnA xiyA |
yA TAM
----------------------------------------------------------------------------------------arc-label necessity vibhakti lextype src-pos arc-dir
---------------------------------------------------------------------------------------- k1 m ne n l c k2 m 0|ko n l c k3 d se n l c k4 d ko n l c----------------------------------------------------------------------------------------
Transformed frame for xe after applying the yA trasformation
0 ne
![Page 16: Constraint Based Hindi Dependency Parser](https://reader035.vdocuments.site/reader035/viewer/2022062801/568143db550346895db06850/html5/thumbnails/16.jpg)
Parsed Output
xiyA ‘give’
KilOnA ‘toy’
mohanarAma
k2k4k1
![Page 17: Constraint Based Hindi Dependency Parser](https://reader035.vdocuments.site/reader035/viewer/2022062801/568143db550346895db06850/html5/thumbnails/17.jpg)
Steps in Parsing
Morph, POS tagging,Chunking
SENTENCE
Identify DemandGroups
Load Frames&
Transform
Find CandidatesApply
Constraints& Solve
Final Parse
![Page 18: Constraint Based Hindi Dependency Parser](https://reader035.vdocuments.site/reader035/viewer/2022062801/568143db550346895db06850/html5/thumbnails/18.jpg)
Example:
rAma ne mohana ko KilOnA xiyA |
![Page 19: Constraint Based Hindi Dependency Parser](https://reader035.vdocuments.site/reader035/viewer/2022062801/568143db550346895db06850/html5/thumbnails/19.jpg)
Identify the demand group,Load and Transform DF
xiyA The only verb
Transformed frame Use ‘yA’ TAM info.
----------------------------------------------------------------------------------------arc-label necessity vibhakti lextype src-pos arc-dir
---------------------------------------------------------------------------------------- k1 m ne n l c k2 m 0|ko n l c k3 d se n l c k4 d ko n l c----------------------------------------------------------------------------------------
![Page 20: Constraint Based Hindi Dependency Parser](https://reader035.vdocuments.site/reader035/viewer/2022062801/568143db550346895db06850/html5/thumbnails/20.jpg)
Candidates
rAma ne mohana ko KilOnA xiyA _ROOT_ |
k1
k2
k4
k2
main
![Page 21: Constraint Based Hindi Dependency Parser](https://reader035.vdocuments.site/reader035/viewer/2022062801/568143db550346895db06850/html5/thumbnails/21.jpg)
Structural constraints
C1: For each of the mandatory demands in a demand frame for each demand group, there should be exactly one outgoing edge labeled by the demand from the demand group.
C2: For each of the optional demands in a demand frame for each demand group, there should be at most one outgoing edge labeled by the demand from the demand group.
C3: There should be exactly one incoming arc into each source group.
![Page 22: Constraint Based Hindi Dependency Parser](https://reader035.vdocuments.site/reader035/viewer/2022062801/568143db550346895db06850/html5/thumbnails/22.jpg)
Inviolable constraints
A parse of a sentence is obtained by satisfying all the above constraints
Ambiguous sentences have multiple parses Ill formed sentences have no parse.
![Page 23: Constraint Based Hindi Dependency Parser](https://reader035.vdocuments.site/reader035/viewer/2022062801/568143db550346895db06850/html5/thumbnails/23.jpg)
Parse - I
rAma ne mohana ko KilOnA xiyA _ROOT_ |
k1
k4
k2
main
![Page 24: Constraint Based Hindi Dependency Parser](https://reader035.vdocuments.site/reader035/viewer/2022062801/568143db550346895db06850/html5/thumbnails/24.jpg)
Parse - I
xiyA
KilOnAmohanarAma
k2k4k1
_ROOT_
main
![Page 25: Constraint Based Hindi Dependency Parser](https://reader035.vdocuments.site/reader035/viewer/2022062801/568143db550346895db06850/html5/thumbnails/25.jpg)
Integer Programming Constraints
Xijk represents a possible arc from word group i to j with karaka label k
It takes a value 1 if the solution has that arc and 0 otherwise. It cannot take any other values.
The constraint rules are formulated into constraint equations.
![Page 26: Constraint Based Hindi Dependency Parser](https://reader035.vdocuments.site/reader035/viewer/2022062801/568143db550346895db06850/html5/thumbnails/26.jpg)
Constraint Equations
C1: For each demand group i, for each of its mandatory demands k, the following equalities must hold:
Mik : j xikj = 1
C2: For each demand group i, for each of its optional or desirable demands k, the following inequalities must hold:
Oik:j xikj <= 1
C3: For each of the source groups j, the following equalities must hold:
Sj : ik xikj = 1
![Page 27: Constraint Based Hindi Dependency Parser](https://reader035.vdocuments.site/reader035/viewer/2022062801/568143db550346895db06850/html5/thumbnails/27.jpg)
Multiple Frames
If more than one karaka frame for a verb Call Integer Programming package for each
frame If more than one demand groups (e.g.,
multiple verbs) in the sentence with multiple demand frames Call Integer Programming package for each
combination of such frames
![Page 28: Constraint Based Hindi Dependency Parser](https://reader035.vdocuments.site/reader035/viewer/2022062801/568143db550346895db06850/html5/thumbnails/28.jpg)
Other frames
Common karaka frame Attached to each karaka frame Preference given to main frame if there are
clashes
Fallback karaka frame required karaka frame is missing Graceful degradation
![Page 29: Constraint Based Hindi Dependency Parser](https://reader035.vdocuments.site/reader035/viewer/2022062801/568143db550346895db06850/html5/thumbnails/29.jpg)
Stage I: Types being handled
Simple Verbs Non-finite verbs
wA_huA wA_hI nA kara 0_rahe, etc.
Copula Genitive
![Page 30: Constraint Based Hindi Dependency Parser](https://reader035.vdocuments.site/reader035/viewer/2022062801/568143db550346895db06850/html5/thumbnails/30.jpg)
Example (Complex Sentence)
rAma ne phala khaakara mohana ko
Ram ‘ERG’ fruit ‘having eaten’ Mohan ‘DAT’
KilOnA xiyA
toy gave
‘Having eaten the fruit Ram gave the toy to Mohan’
![Page 31: Constraint Based Hindi Dependency Parser](https://reader035.vdocuments.site/reader035/viewer/2022062801/568143db550346895db06850/html5/thumbnails/31.jpg)
Candidates
rAma ne phala khaakara mohana ko KilOnA xiyA _ROOT_ |
X1: k1
X3: k2
X5: k4
X2: k2
X7: vmodX4: k2
X6: k2
X8: main
![Page 32: Constraint Based Hindi Dependency Parser](https://reader035.vdocuments.site/reader035/viewer/2022062801/568143db550346895db06850/html5/thumbnails/32.jpg)
Constraint Equations Verb ‘xe’
Mandatory Demands (C1) k1 x1 = 1 k2 x2 + x3 + x4 = 1
Optional Demands (C2) k4 x5 <= 1
Verb ‘khaa’ Mandatory Demands (C1)
k2 x6 = 1 vmod x7 = 1
_ROOT_ C1
Main x8 = 1
![Page 33: Constraint Based Hindi Dependency Parser](https://reader035.vdocuments.site/reader035/viewer/2022062801/568143db550346895db06850/html5/thumbnails/33.jpg)
Constraint Equations (contd.) Incoming Arcs into Source (C3)
rAma x1 = 1
phala x4 + x6 = 1
khaa x7 = 1
mohana x3 + x5 = 1
KilOnA x2 = 1
xe x8 = 1
![Page 34: Constraint Based Hindi Dependency Parser](https://reader035.vdocuments.site/reader035/viewer/2022062801/568143db550346895db06850/html5/thumbnails/34.jpg)
Solution Graph
xiyA
KilOnAmohanarAma
k2k4k1
_ROOT_
main
khaakara
phala
k2
vmod
![Page 35: Constraint Based Hindi Dependency Parser](https://reader035.vdocuments.site/reader035/viewer/2022062801/568143db550346895db06850/html5/thumbnails/35.jpg)
Steps in Parsing
Morph, POS tagging,Chunking
SENTENCE
Identify DemandGroups
Load Frames&
Transform
Find CandidatesApply
Constraints& Solve
Final ParseIs ComplexNO
YES
STAGE - II
![Page 36: Constraint Based Hindi Dependency Parser](https://reader035.vdocuments.site/reader035/viewer/2022062801/568143db550346895db06850/html5/thumbnails/36.jpg)
Stage - II
Handles: Conjuncts
Subordinating & Coordinating Relative clauses Complex predicates
Basic constraints similar to Stage-I New demand groups New candidates
![Page 37: Constraint Based Hindi Dependency Parser](https://reader035.vdocuments.site/reader035/viewer/2022062801/568143db550346895db06850/html5/thumbnails/37.jpg)
Steps (Stage II)
Identify NewDemandGroups
Load Frames&
Transform
FindCandidates
ApplyConstraints
& Solve
FINAL PARSE
Repair
Output ofSTAGE - I
![Page 38: Constraint Based Hindi Dependency Parser](https://reader035.vdocuments.site/reader035/viewer/2022062801/568143db550346895db06850/html5/thumbnails/38.jpg)
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’
![Page 39: Constraint Based Hindi Dependency Parser](https://reader035.vdocuments.site/reader035/viewer/2022062801/568143db550346895db06850/html5/thumbnails/39.jpg)
Output after Stage - I
xI
puswaka
mohanarAma
k2k4
k1
_ROOT_
jo
hEk1
prasixXa
k1s
mainmain
vaha
![Page 40: Constraint Based Hindi Dependency Parser](https://reader035.vdocuments.site/reader035/viewer/2022062801/568143db550346895db06850/html5/thumbnails/40.jpg)
Identify the demand group
xI ‘give’Main verb of the relative clause
![Page 41: Constraint Based Hindi Dependency Parser](https://reader035.vdocuments.site/reader035/viewer/2022062801/568143db550346895db06850/html5/thumbnails/41.jpg)
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 r|l p insert--------------------------------------------------------------------------------------------------------------
![Page 42: Constraint Based Hindi Dependency Parser](https://reader035.vdocuments.site/reader035/viewer/2022062801/568143db550346895db06850/html5/thumbnails/42.jpg)
Karaka Frame
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’
Main verb of relative clause
--------------------------------------------------------------------------------------------------------arc-label necessity vibhakti lextype src-pos arc-dir oprt--------------------------------------------------------------------------------------------------------nmod__relc m any n r|l p insert---------------------------------------------------------------------------------------------------------
Transformed frame for xe after applying the jo trasformation
New row inserted after
transformation
![Page 43: Constraint Based Hindi Dependency Parser](https://reader035.vdocuments.site/reader035/viewer/2022062801/568143db550346895db06850/html5/thumbnails/43.jpg)
Possible candidates
vaha puswaka jo rAma ne mohana ko xI hE prasixXa hE |
nmod__relc
![Page 44: Constraint Based Hindi Dependency Parser](https://reader035.vdocuments.site/reader035/viewer/2022062801/568143db550346895db06850/html5/thumbnails/44.jpg)
Output after Stage - II
xiyA hE
vaha puswaka
mohana rAma
k2k4
k1
_ROOT_
jo
hEk1
prasixXa
k1s
nmod__relc
main
![Page 45: Constraint Based Hindi Dependency Parser](https://reader035.vdocuments.site/reader035/viewer/2022062801/568143db550346895db06850/html5/thumbnails/45.jpg)
Example II – Coordination
sameer Ora abhay kala Aye | Sameer and Abhay yesterday came ‘Sameer and Abhay came yesterday’
![Page 46: Constraint Based Hindi Dependency Parser](https://reader035.vdocuments.site/reader035/viewer/2022062801/568143db550346895db06850/html5/thumbnails/46.jpg)
Output of Stage - I
sameer
_ROOT_
Ayek1
abhay
Ora
kala
k7t
dummydummy
main
![Page 47: Constraint Based Hindi Dependency Parser](https://reader035.vdocuments.site/reader035/viewer/2022062801/568143db550346895db06850/html5/thumbnails/47.jpg)
For Stage – II (Constraint Graph)
sameer
_ROOT_
Ayek1
abhay
Ora
kala
main
k7tccof
ccof
![Page 48: Constraint Based Hindi Dependency Parser](https://reader035.vdocuments.site/reader035/viewer/2022062801/568143db550346895db06850/html5/thumbnails/48.jpg)
Candidate Arcs
sameer
_ROOT_
Ayek1
abhay
Ora
main
k1
k1
ccofccof
![Page 49: Constraint Based Hindi Dependency Parser](https://reader035.vdocuments.site/reader035/viewer/2022062801/568143db550346895db06850/html5/thumbnails/49.jpg)
Solution Graph
sameer
_ROOT_
Aye
abhay
Ora
kala
k7t
maink1
ccofccof
![Page 50: Constraint Based Hindi Dependency Parser](https://reader035.vdocuments.site/reader035/viewer/2022062801/568143db550346895db06850/html5/thumbnails/50.jpg)
Parse tree
Aye
kalaOra
k7tk1
_ROOT_
sameer abhay
ccofccof
main
Output after Stage II
![Page 51: Constraint Based Hindi Dependency Parser](https://reader035.vdocuments.site/reader035/viewer/2022062801/568143db550346895db06850/html5/thumbnails/51.jpg)
Finite Verb Coordination
rAma Gara gayA Ora vaha so gayA | Ram home went and he sleep went
‘Ram went home and slept’
rAma
_ROOT_
soOra
vaha
k1
dummymain main
gayA
Gara
k1 k2
Output after Stage I
![Page 52: Constraint Based Hindi Dependency Parser](https://reader035.vdocuments.site/reader035/viewer/2022062801/568143db550346895db06850/html5/thumbnails/52.jpg)
Karaka Frame - Ora
Finite
Ora
v_finv_fin
Ora
sogayA
ccof ccofccof ccof
![Page 53: Constraint Based Hindi Dependency Parser](https://reader035.vdocuments.site/reader035/viewer/2022062801/568143db550346895db06850/html5/thumbnails/53.jpg)
Finite Verb Coordination (Parse Tree)
rAma
_ROOT_
so
Ora
vaha
k1
main
gayA
Gara
k1 k2
Output after Stage II
ccof ccof
![Page 54: Constraint Based Hindi Dependency Parser](https://reader035.vdocuments.site/reader035/viewer/2022062801/568143db550346895db06850/html5/thumbnails/54.jpg)
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’
KarIxI
puswakarAma
k2k1
_ROOT_
jo
hEk1
prasixXa
k1s
mainmain
Ora
jo
hEk1
saswI
k1s
maindummy
Output after Stage I
![Page 55: Constraint Based Hindi Dependency Parser](https://reader035.vdocuments.site/reader035/viewer/2022062801/568143db550346895db06850/html5/thumbnails/55.jpg)
Karaka Frame - Ora
Relative Clause
Ora
n
v_relv_rel
Ora
puswaka
hEhE
ccofccof ccof ccof
nmod__relcnmod__relc
![Page 56: Constraint Based Hindi Dependency Parser](https://reader035.vdocuments.site/reader035/viewer/2022062801/568143db550346895db06850/html5/thumbnails/56.jpg)
Relative Clause Coordination (Parse Tree)
KarIxI
puswakarAma
k2k1
_ROOT_
jo
hEk1
prasixXa
k1s
main
Ora
jo
hEk1
saswI
k1s
Output after Stage II
ccof ccof
nmod__relc
![Page 57: Constraint Based Hindi Dependency Parser](https://reader035.vdocuments.site/reader035/viewer/2022062801/568143db550346895db06850/html5/thumbnails/57.jpg)
Steps (Stage II)
Identify Nodes
Load Frames&
Transform
FindCandidates
ApplyConstraints
& Solve
FINAL PARSE
Repair
Identify NewDemandGroups
Output of STAGE - I
![Page 58: Constraint Based Hindi Dependency Parser](https://reader035.vdocuments.site/reader035/viewer/2022062801/568143db550346895db06850/html5/thumbnails/58.jpg)
Constraint Graph Nodes (Stage II)
Selected from the intermediate parse tree (Stage I)
Set-I (demand nodes)1. Conjuncts2. Nearest verbal ancestor of ‘jo’ (usually
just the parent)3. _ROOT_4. Children of _ROOT_ other than (1) and
(2).5. Other nodes which are added due to
nodes in Set 2
![Page 59: Constraint Based Hindi Dependency Parser](https://reader035.vdocuments.site/reader035/viewer/2022062801/568143db550346895db06850/html5/thumbnails/59.jpg)
Constraint Graph Nodes (Stage II)
Set-II (source nodes)1. Possible children and parents of
conjuncts
2. Possible heads of the relative clause.
Identification of nodes in Set-II will
generally trigger the repair.
![Page 60: Constraint Based Hindi Dependency Parser](https://reader035.vdocuments.site/reader035/viewer/2022062801/568143db550346895db06850/html5/thumbnails/60.jpg)
Steps (Stage II)
Identify Nodes
Load Frames&
Transform
FindCandidates
ApplyConstraints
& Solve
FINAL PARSE
Repair
Identify NewDemandGroups
Output of STAGE - I
![Page 61: Constraint Based Hindi Dependency Parser](https://reader035.vdocuments.site/reader035/viewer/2022062801/568143db550346895db06850/html5/thumbnails/61.jpg)
Identify the demand group
Ora Aye
![Page 62: Constraint Based Hindi Dependency Parser](https://reader035.vdocuments.site/reader035/viewer/2022062801/568143db550346895db06850/html5/thumbnails/62.jpg)
Steps (Stage II)
Identify Nodes
Load Frames&
Transform
FindCandidates
ApplyConstraints
& Solve
FINAL PARSE
Repair
Identify NewDemandGroups
Output of STAGE - I
![Page 63: Constraint Based Hindi Dependency Parser](https://reader035.vdocuments.site/reader035/viewer/2022062801/568143db550346895db06850/html5/thumbnails/63.jpg)
General Principles
Repair/Revision
1. Any node which becomes a potential child in stage 2, its arc to its existing parent is open to revision
sameer Ora abhay kala Aye
• Node 4 becomes potential child (of node 1)• Its parent (node 2) is open to revision
![Page 64: Constraint Based Hindi Dependency Parser](https://reader035.vdocuments.site/reader035/viewer/2022062801/568143db550346895db06850/html5/thumbnails/64.jpg)
General Principles
Repair/Revision after parse of stage I
2. Any node which becomes a potential parent must be re-looked at.
sameer Ora abhay kala Aye
• Node 2 becomes potential parent (of 1)• Its child (node 4) is open to revision
![Page 65: Constraint Based Hindi Dependency Parser](https://reader035.vdocuments.site/reader035/viewer/2022062801/568143db550346895db06850/html5/thumbnails/65.jpg)
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.
![Page 66: Constraint Based Hindi Dependency Parser](https://reader035.vdocuments.site/reader035/viewer/2022062801/568143db550346895db06850/html5/thumbnails/66.jpg)
An example
sameer aura abhay kala aaye ’Sameer’ ’and’ ’Abhay’ ’yesterday’ ‘came’
Sameer and Abhay came yesterday
Output after stage I sameer
_ROOT_
Ayek1
abhay
Ora
kala
k7t
dummydummy
main
![Page 67: Constraint Based Hindi Dependency Parser](https://reader035.vdocuments.site/reader035/viewer/2022062801/568143db550346895db06850/html5/thumbnails/67.jpg)
Identify Nodes
Set 1 nodes
Set 1 and Set 2sameer
_ROOT_
Ayek1
abhay
Ora
kala
k7t
dummydummy
main
sameer
_ROOT_
Ayek1
abhay
Ora
kala
k7t
dummydummy
main
![Page 68: Constraint Based Hindi Dependency Parser](https://reader035.vdocuments.site/reader035/viewer/2022062801/568143db550346895db06850/html5/thumbnails/68.jpg)
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)
sameer
_ROOT_
Aye
abhay
Ora
ccof
ccof
k1
k1
main
![Page 69: Constraint Based Hindi Dependency Parser](https://reader035.vdocuments.site/reader035/viewer/2022062801/568143db550346895db06850/html5/thumbnails/69.jpg)
Example
Final Parse Aye
kalaOra
k7tk1
_ROOT_
sameer abhay
ccofccof
main
![Page 70: Constraint Based Hindi Dependency Parser](https://reader035.vdocuments.site/reader035/viewer/2022062801/568143db550346895db06850/html5/thumbnails/70.jpg)
Types of complex sentences
Relative clauses Initial Final Medial
Conjuncts Coordination
Simple clauseRelative clauseNon-finiteNominal, adjectival, adverbial
Subordination
![Page 71: Constraint Based Hindi Dependency Parser](https://reader035.vdocuments.site/reader035/viewer/2022062801/568143db550346895db06850/html5/thumbnails/71.jpg)
Evaluation Two data driven parsers
Malt (version 0.4) MST (version 0.4b)
Tuned for Hindi Trained on a subset of a Hindi Treebank ~ 1800 sentences
average length of 19.85 words 6585 unique tokens.
Training set = 1185 sentences, Development = 268 sentences Test set = 220 sentences.
![Page 72: Constraint Based Hindi Dependency Parser](https://reader035.vdocuments.site/reader035/viewer/2022062801/568143db550346895db06850/html5/thumbnails/72.jpg)
Overall performance
UA L LA
CBP 86.1 65 63
CBP’’ 90.1 76.9 75
MST 95.7 71.3 69.6
Malt 86.6 70.6 68.0
UA: unlabeled attachments accuracy, L : labeled accuracyLA: labeled attachment accuracy
![Page 73: Constraint Based Hindi Dependency Parser](https://reader035.vdocuments.site/reader035/viewer/2022062801/568143db550346895db06850/html5/thumbnails/73.jpg)
Core labels
k1 k1s k2 k3 k4 k5
L LA L LA L LA L LA L LA L LA
CBP’’ P 74.9 74.4 71.5 71.5 54.0 53.7 66.6 66.6 28.5 28.5 33.3 16.6
R 71.9 71.4 69.5 69.5 54.0 53.7 66.6 66.6 28.5 28.5 33.3 16.6
MST P 59.2 57 64.5 64.5 52.9 50.9 0 0 0 0 0 0
R 80.3 77.3 48.7 48.7 50.9 49.0 0 0 0 0 0 0
Malt P 77.6 76.4 66.6 66.6 56.7 51.6 33.3 33.3 0 0 20 20
R 81 80 43.4 43.4 58.2 52.9 16.6 16.6 0 0 50 50
P: Precision, R: Recall, L: Labeled accuracy, LA: Labeled attachment accuracy
![Page 74: Constraint Based Hindi Dependency Parser](https://reader035.vdocuments.site/reader035/viewer/2022062801/568143db550346895db06850/html5/thumbnails/74.jpg)
Core labels
k7 r6 ccof relc nmod vmod Main
L LA L LA L LA L LA L LA L LA L LA
CBP’’ P 75 71.1 85.5 84.2 98 98 66 66 41.6 33.3 81.1 77.7 91.3 91.3
R 75 71.1 85.5 84.2 77 77 66 66 41.6 33.3 81.1 77.7 96.8 96.8
MST P 62.7 62.7 89.6 88.3 94.3 91 100 100 25.0 12.5 83.5 79.7 98.5 98.9
R 31.6 31.6 89.6 88.3 97.4 94.1 57.1 57.1 57.1 28.5 69.4 66.3 98.9 98.9
Malt P 60.9 54.8 86.3 84.8 84.9 79.3 0 0 0 0 78.6 78.6 92.5 92.5
R 53.1 47.8 74 72.7 83.5 78.1 0 0 0 0 53.9 53.9 92 92
P: Precision, R: Recall, L: Labeled accuracy, LA: Labeled attachment accuracy
![Page 75: Constraint Based Hindi Dependency Parser](https://reader035.vdocuments.site/reader035/viewer/2022062801/568143db550346895db06850/html5/thumbnails/75.jpg)
References R. Begum, S. Husain, A. Dhwaj, D. Sharma, L. Bai, and R. Sangal. 2008a.
Dependency annotation scheme for Indian languages. In Proceedings of IJCNLP-2008.
Akshar Bharati, Rajeev Sangal, T Papi Reddy. 2002. A Constraint Based Parser Using Integer Programming In Proc. of ICON-2002.
J. Nivre, 2005. Dependency Grammar and Dependency Parsing. MSI report 05133. Växjö University:
I. A. Mel'Cuk. 1988. Dependency Syntax: Theory and Practice, State University Press of New York.
Tara Mohanan, 1994. Arguments in Hindi. CSLI Publications. S. M. Shieber. 1985. Evidence against the context-freeness of natural language. In
Linguistics and Philosophy, p. 8, 334–343. R. McDonald, F. Pereira, K. Ribarov, and J. Hajic. 2005. Non-projective dependency
parsing using spanning tree algorithms. In Proc. of HLT/EMNLP, pp. 523–530. J. Nivre, J. Hall, J. Nilsson, A. Chanev, G. Eryigit, S. Kübler, S. Marinov and E Marsi.
2007b. MaltParser: A language-independent system for data-driven dependency parsing. Natural Language Engineering, 13(2), 95-135.
J. Nivre. 2006. Inductive Dependency Parsing. Springer.
![Page 76: Constraint Based Hindi Dependency Parser](https://reader035.vdocuments.site/reader035/viewer/2022062801/568143db550346895db06850/html5/thumbnails/76.jpg)
THANKS!!