how to train your multi bottom-up tree transducer
TRANSCRIPT
How to train yourmulti bottom-up tree transducer
Andreas Maletti
Universität StuttgartInstitute for Natural Language Processing
Stuttgart, Germany
Portland, OR — June 22, 2011
How to train your multi bottom-up tree transducer A. Maletti · 1
Synchronous Tree SubstitutionGrammar
q q
Used rule Next rule
q q—
S
CONJ
wa
q
How to train your multi bottom-up tree transducer A. Maletti · 2
Synchronous Tree SubstitutionGrammar
q S
CONJ
wa
q
Used rule
q q—
S
CONJ
wa
q
Next rule
S
q1 VP
p q2
q—S
p q1 q2
How to train your multi bottom-up tree transducer A. Maletti · 2
Synchronous Tree SubstitutionGrammar
S
q1 VP
p q2
S
CONJ
wa
S
p q1 q2
Used rule
S
q1 VP
p q2
q—S
p q1 q2
Next rule
V
sawp—
V
ra’aa
How to train your multi bottom-up tree transducer A. Maletti · 2
Synchronous Tree SubstitutionGrammar
S
q1 VP
V
saw
q2
S
CONJ
wa
S
V
ra’aa
q1 q2
Used rule
V
sawp—
V
ra’aa
Next rule
NP
DT
the
r q1—NP
r
How to train your multi bottom-up tree transducer A. Maletti · 2
Synchronous Tree SubstitutionGrammar
S
NP
DT
the
r
VP
V
saw
q2
S
CONJ
wa
S
V
ra’aa
NP
r
q2
Used rule
NP
DT
the
r q1—NP
r
Next rule
N
boyr—
N
atefl
How to train your multi bottom-up tree transducer A. Maletti · 2
Synchronous Tree SubstitutionGrammar
S
NP
DT
the
N
boy
VP
V
saw
q2
S
CONJ
wa
S
V
ra’aa
NP
N
atefl
q2
Used rule
N
boyr—
N
atefl
Next rule
NP
DT
the
r q2—NP
r
How to train your multi bottom-up tree transducer A. Maletti · 2
Synchronous Tree SubstitutionGrammar
S
NP
DT
the
N
boy
VP
V
saw
NP
DT
the
r
S
CONJ
wa
S
V
ra’aa
NP
N
atefl
NP
r
Used rule
NP
DT
the
r q2—NP
r
Next rule
N
doorr—
N
albab
How to train your multi bottom-up tree transducer A. Maletti · 2
Synchronous Tree SubstitutionGrammar
S
NP
DT
the
N
boy
VP
V
saw
NP
DT
the
N
door
S
CONJ
wa
S
V
ra’aa
NP
N
atefl
NP
N
albab
Used rule
N
doorr—
N
albab
Next rule
How to train your multi bottom-up tree transducer A. Maletti · 2
Synchronous Tree SubstitutionGrammar
Rule shape
• states can occur only once in lhs and rhs• states in rhs = states in lhs• exactly one lhs and one rhs→ bijective synchronization relation
S
q1 VP
p q2
q—S
p q1 q2
How to train your multi bottom-up tree transducer A. Maletti · 3
Synchronous Tree SubstitutionGrammar
Rule shape
• states can occur only once in lhs and rhs• states in rhs = states in lhs• exactly one lhs and one rhs→ bijective synchronization relation
S
q1 VP
p q2
q—S
p q1 q2
How to train your multi bottom-up tree transducer A. Maletti · 3
Synchronous Tree SubstitutionGrammar
Rule shape
• states can occur only once in lhs and rhs• states in rhs = states in lhs• exactly one lhs and one rhs→ bijective synchronization relation
Notes
• version with states (instead of locality tests)• equivalent to linear nondeleting extended tree transducers• implemented in TIBURON [May, Knight 2006]
How to train your multi bottom-up tree transducer A. Maletti · 3
Multi Bottom-up Tree Transducer
q q
Used rule Next rule
S
q pq—
S
wa VP
p p q
How to train your multi bottom-up tree transducer A. Maletti · 4
Multi Bottom-up Tree Transducer
S
q p
S
wa VP
p p q
Used rule
S
q pq—
S
wa VP
p p q
Next rule
VP
signed rp— twlY
NP-OBJ
NP
AltwqyE
r
How to train your multi bottom-up tree transducer A. Maletti · 4
Multi Bottom-up Tree Transducer
S
q VP
signed r
S
wa VP
twlY NP-OBJ
NP
AltwqyE
r
q
Used rule
VP
signed rp— twlY
NP-OBJ
NP
AltwqyE
r
Next rule
NP-SBJ
p′ Voislavq—
NP-SBJ
p′ NP
fwyslAf
How to train your multi bottom-up tree transducer A. Maletti · 4
Multi Bottom-up Tree Transducer
S
NP-SBJ
p′ Voislav
VP
signed r
S
wa VP
twlY NP-OBJ
NP
AltwqyE
r
NP-SBJ
p′ NP
fwyslAf
Used rule
NP-SBJ
p′ Voislavq—
NP-SBJ
p′ NP
fwyslAf
Next rule
NML
Yugoslav Presidentp′—
NP
Alr}ys AlywgwslAfy
How to train your multi bottom-up tree transducer A. Maletti · 4
Multi Bottom-up Tree Transducer
S
NP-SBJ
NML
Yugoslav President
Voislav
VP
signed r
S
wa VP
twlY NP-OBJ
NP
AltwqyE
r
NP-SBJ
NP
Alr}ys AlywgwslAfy
. . .
Used rule
NML
Yugoslav Presidentp′—
NP
Alr}ys AlywgwslAfy
Next rule
PP
for NP
Serbia
r—
PP
en NP
SrbyA
How to train your multi bottom-up tree transducer A. Maletti · 4
Multi Bottom-up Tree Transducer
S
NP-SBJ
NML
Yugoslav President
Voislav
VP
signed PP
for NP
Serbia
S
wa VP
twlY NP-OBJ
NP
AltwqyE
PP
en NP
SrbyA
. . .
Used rule
PP
for NP
Serbia
r—
PP
en NP
SrbyA
Next rule
How to train your multi bottom-up tree transducer A. Maletti · 4
Multi Bottom-up Tree Transducer
Rule shape
• STSG: states can occur only once in lhs and rhsMBOT: states can occur only once in lhs
• STSG: states in rhs = states in lhsMBOT: states in rhs ⊆ states in lhs
• STSG: exactly one lhs and one rhsMBOT: exactly one lhs
→ STSG: bijective synchronization relationMBOT: inverse synchronization relation is functional
S
q pq—
S
wa VP
p p q
How to train your multi bottom-up tree transducer A. Maletti · 5
Multi Bottom-up Tree Transducer
Rule shape
• STSG: states can occur only once in lhs and rhsMBOT: states can occur only once in lhs
• STSG: states in rhs = states in lhsMBOT: states in rhs ⊆ states in lhs
• STSG: exactly one lhs and one rhsMBOT: exactly one lhs
→ STSG: bijective synchronization relationMBOT: inverse synchronization relation is functional
S
q pq—
S
wa VP
p p q
How to train your multi bottom-up tree transducer A. Maletti · 5
Multi Bottom-up Tree Transducer
Rule shape
• STSG: states can occur only once in lhs and rhsMBOT: states can occur only once in lhs
• STSG: states in rhs = states in lhsMBOT: states in rhs ⊆ states in lhs
• STSG: exactly one lhs and one rhsMBOT: exactly one lhs
→ STSG: bijective synchronization relationMBOT: inverse synchronization relation is functional
VP
signed rp— twlY
NP-OBJ
NP
AltwqyE
r
How to train your multi bottom-up tree transducer A. Maletti · 5
Multi Bottom-up Tree Transducer
Rule shape
• STSG: states can occur only once in lhs and rhsMBOT: states can occur only once in lhs
• STSG: states in rhs = states in lhsMBOT: states in rhs ⊆ states in lhs
• STSG: exactly one lhs and one rhsMBOT: exactly one lhs
→ STSG: bijective synchronization relationMBOT: inverse synchronization relation is functional
S
q pq—
S
wa VP
p p q
How to train your multi bottom-up tree transducer A. Maletti · 5
STSG vs. MBOT
property STSG MBOTsimple and natural 3 ?
symmetric 3 7
preserves regularity 3 7
inverse pres. regularity 3 3
binarizable 7 3
closed under composition 7 3
input parsing O(|M|nx) O(|M|n3)output parsing O(|M|nx) O(|M|ny )
where x = 2 rk(M) + 5 andy = 2 rk(M) + 2
How to train your multi bottom-up tree transducer A. Maletti · 6
Additional Expressive Power
Finite copying
{〈t , σ(t , t)〉 | t ∈ TΣ}
3 desirable [ATANLP participants, 2010]e.g., for cross-serial dependencies
7 harms preservation of regularity
Non-contiguous rules
3 +0.64 BLEU [Sun, Zhang, Tan, 2009] 25.92→ 26.563 do not harm preservation of regularity
How to train your multi bottom-up tree transducer A. Maletti · 7
Additional Expressive Power
Finite copying
{〈t , σ(t , t)〉 | t ∈ TΣ}
3 desirable [ATANLP participants, 2010]e.g., for cross-serial dependencies
7 harms preservation of regularity
Non-contiguous rules
3 +0.64 BLEU [Sun, Zhang, Tan, 2009] 25.92→ 26.563 do not harm preservation of regularity
How to train your multi bottom-up tree transducer A. Maletti · 7
Approach
Old approach
1 extract STSG rules2 train STSG3 convert to MBOT4 work with MBOT
New approach
1 extract (restricted) MBOT rules2 train MBOT3 work with MBOT
How to train your multi bottom-up tree transducer A. Maletti · 8
Approach
Old approach
1 extract STSG rules2 train STSG3 convert to MBOT4 work with MBOT
New approach
1 extract (restricted) MBOT rules2 train MBOT3 work with MBOT
How to train your multi bottom-up tree transducer A. Maletti · 8
Roadmap
1 Motivation
2 Relation to STSSG
3 Rule Extraction and Training
4 Preservation of Recognizability
How to train your multi bottom-up tree transducer A. Maletti · 9
Synchronous Tree-SequenceSubstitution Grammar
Rule shape
• STSG: states can occur only once in lhs and rhsMBOT: states can occur only once in lhsSTSSG: (no restriction)
• STSG: states in rhs = states in lhsMBOT: states in rhs ⊆ states in lhsSTSSG: (no restriction)
• STSG: exactly one lhs and one rhsMBOT: exactly one lhsSTSSG: (no restriction)
How to train your multi bottom-up tree transducer A. Maletti · 10
Synchronous Tree-SequenceSubstitution Grammar
Rule shape
• STSG: states can occur only once in lhs and rhsMBOT: states can occur only once in lhsSTSSG: (no restriction)
• STSG: states in rhs = states in lhsMBOT: states in rhs ⊆ states in lhsSTSSG: (no restriction)
• STSG: exactly one lhs and one rhsMBOT: exactly one lhsSTSSG: (no restriction)
How to train your multi bottom-up tree transducer A. Maletti · 10
Synchronous Tree-SequenceSubstitution Grammar
Rule shape
• STSG: states can occur only once in lhs and rhsMBOT: states can occur only once in lhsSTSSG: (no restriction)
• STSG: states in rhs = states in lhsMBOT: states in rhs ⊆ states in lhsSTSSG: (no restriction)
• STSG: exactly one lhs and one rhsMBOT: exactly one lhsSTSSG: (no restriction)
How to train your multi bottom-up tree transducer A. Maletti · 10
Expressive Power
Corollary
STSG ⊆ MBOT ⊆ STSSG
Theorem
STSG ⊂ MBOT ⊂ STSSG
Claim
MBOT−1 ; MBOT = STSSG
How to train your multi bottom-up tree transducer A. Maletti · 11
Expressive Power
Corollary
STSG ⊆ MBOT ⊆ STSSG
Theorem
STSG ⊂ MBOT ⊂ STSSG
Claim
MBOT−1 ; MBOT = STSSG
How to train your multi bottom-up tree transducer A. Maletti · 11
Expressive Power
Corollary
STSG ⊆ MBOT ⊆ STSSG
Theorem
STSG ⊂ MBOT ⊂ STSSG
Claim
MBOT−1 ; MBOT = STSSG
How to train your multi bottom-up tree transducer A. Maletti · 11
STSG vs. MBOT vs. STSSG
property STSG MBOT STSSGsimple and natural 3 ? ??
symmetric 3 7 3
preserves regularity 3 7 7
inverse pres. regularity 3 3 7
binarizable 7 3 3
closed under composition 7 3 7
input parsing O(|M|nx) O(|M|n3) O(|M|ny )output parsing O(|M|nx) O(|M|ny ) O(|M|ny )
where x = 2 rk(M) + 5 andy = 2 rk(M) + 2
How to train your multi bottom-up tree transducer A. Maletti · 12
Roadmap
1 Motivation
2 Relation to STSSG
3 Rule Extraction and Training
4 Preservation of Recognizability
How to train your multi bottom-up tree transducer A. Maletti · 13
Rule Extraction
Input
• parallel bi-text• parses for input and output• word alignment
Output
• MBOT rules
How to train your multi bottom-up tree transducer A. Maletti · 14
Rule Extraction
Input
• parallel bi-text• parses for input and output• word alignment
Output
• MBOT rules
How to train your multi bottom-up tree transducer A. Maletti · 14
S
NP-SBJ
NML
JJ
Yugoslav
NNP
President
NNP
Voislav
VP
VBD
signed
PP
IN
for
NP
NNP
Serbia
S
CONJ
w
VP
PV
twlY
NP-OBJ
NP
DET-NN
AltwqyE
PP
PREP
En
NP
NN-PROP
SrbyA
NP-SBJ
NP
DET-NN
Alr}ys
DET-ADJ
AlywgwslAfy
NP
NN-PROP
fwyslAf
How to train your multi bottom-up tree transducer A. Maletti · 15
S
NP-SBJ
NML
JJ
Yugoslav
NNP
President
NNP
Voislav
VP
VBD
signed
PP
IN
for
NP
NNP
Serbia
S
CONJ
w
VP
PV
twlY
NP-OBJ
NP
DET-NN
AltwqyE
PP
PREP
En
NP
NN-PROP
SrbyA
NP-SBJ
NP
DET-NN
Alr}ys
DET-ADJ
AlywgwslAfy
NP
NN-PROP
fwyslAf
How to train your multi bottom-up tree transducer A. Maletti · 15
S
NP-SBJ
NML
JJ
Yugoslav
NNP
President
NNP
Voislav
VP
VBD
signed
PP
IN
for
NP
NNP
Serbia
S
CONJ
w
VP
PV
twlY
NP-OBJ
NP
DET-NN
AltwqyE
PP
PREP
En
NP
NN-PROP
SrbyA
NP-SBJ
NP
DET-NN
Alr}ys
DET-ADJ
AlywgwslAfy
NP
NN-PROP
fwyslAf
How to train your multi bottom-up tree transducer A. Maletti · 15
S
NP-SBJ
NML
JJ
Yugoslav
NNP
President
NNP
Voislav
VP
VBD
signed
PP
IN
for
NP
NNP
Serbia
S
CONJ
w
VP
PV
twlY
NP-OBJ
NP
DET-NN
AltwqyE
PP
PREP
En
NP
NN-PROP
SrbyA
NP-SBJ
NP
DET-NN
Alr}ys
DET-ADJ
AlywgwslAfy
NP
NN-PROP
fwyslAf
How to train your multi bottom-up tree transducer A. Maletti · 15
S
NP-SBJ
NML
JJ
Yugoslav
NNP
President
NNP
Voislav
VP
VBD
signed
PP
IN
for
NP
NNP
Serbia
S
CONJ
w
VP
PV
twlY
NP-OBJ
NP
DET-NN
AltwqyE
PP
PREP
En
NP
NN-PROP
SrbyA
NP-SBJ
NP
DET-NN
Alr}ys
DET-ADJ
AlywgwslAfy
NP
NN-PROP
fwyslAf
How to train your multi bottom-up tree transducer A. Maletti · 15
Rule Extraction
S
NP-SBJ
NML
JJ
Yugoslav
NNP
President
NNP
Voislav
VP
VBD
signed
PP
IN
for
NP
NNP
Serbia
S
CONJ
w
VP
PV
twlY
NP-OBJ
NP
DET-NN
AltwqyE
PP
PREP
En
NP
NN-PROP
SrbyA
NP-SBJ
NP
DET-NN
Alr}ys
DET-ADJ
AlywgwslAfy
NP
NN-PROP
fwyslAf
S
NP V P
S—
S
CONJ
w
VP
V P V P NP
How to train your multi bottom-up tree transducer A. Maletti · 16
Rule Extraction
S
NP-SBJ
NML
JJ
Yugoslav
NNP
President
NNP
Voislav
VP
VBD
signed
PP
IN
for
NP
NNP
Serbia
S
CONJ
w
VP
PV
twlY
NP-OBJ
NP
DET-NN
AltwqyE
PP
PREP
En
NP
NN-PROP
SrbyA
NP-SBJ
NP
DET-NN
Alr}ys
DET-ADJ
AlywgwslAfy
NP
NN-PROP
fwyslAf
S
NP V P
S—
S
CONJ
w
VP
V P V P NP
VP
VBD
signed
PP V P—PV
twlY
NP-OBJ
NP
DET-NN
AltwqyE
PP
How to train your multi bottom-up tree transducer A. Maletti · 16
Extracted Rules
STSG rule
S
NP VP
VBD
signed
PP
S—
VP
PV
twlY
NP-OBJ
NP
DET-NN
AltwqyE
PP
NP
MBOT rules STSSG rule
How to train your multi bottom-up tree transducer A. Maletti · 17
Extracted Rules
STSG rule
S
NP VP
VBD
signed
PP
S—
VP
PV
twlY
NP-OBJ
NP
DET-NN
AltwqyE
PP
NP
MBOT rulesS
NP V P
S—VP
V P V P NP
VP
VBD
signed
PP V P—PV
twlY
NP-OBJ
NP
DET-NN
AltwqyE
PP
STSSG rule
How to train your multi bottom-up tree transducer A. Maletti · 17
Extracted Rules
STSG rule
S
NP VP
VBD
signed
PP
S—
VP
PV
twlY
NP-OBJ
NP
DET-NN
AltwqyE
PP
NP
MBOT rulesS
NP V P
S—VP
V P V P NP
VP
VBD
signed
PP V P—PV
twlY
NP-OBJ
NP
DET-NN
AltwqyE
PP
STSSG rule
VBD
signed
IN
forq—
PV
twlY
NP
DET-NN
AltwqyE
PREP
En
How to train your multi bottom-up tree transducer A. Maletti · 17
Training
DefinitionA tree language is regular if it can be represented by a TSG(with states).
Example
{σ(t , t) | t ∈ TΣ}
is not regular.
How to train your multi bottom-up tree transducer A. Maletti · 18
Training
TheoremThe set of derivations of an MBOT is regular.
ConclusionMinimal adaptation of [Graehl, Knight, May 2008] can be used.
How to train your multi bottom-up tree transducer A. Maletti · 19
Training
TheoremThe set of derivations of an MBOT is regular.
ConclusionMinimal adaptation of [Graehl, Knight, May 2008] can be used.
How to train your multi bottom-up tree transducer A. Maletti · 19
Roadmap
1 Motivation
2 Relation to STSSG
3 Rule Extraction and Training
4 Preservation of Recognizability
How to train your multi bottom-up tree transducer A. Maletti · 20
Preservation of Regularity
Input
• MBOT M• regular tree language L
QuestionIs M(L) = {t | ∃s ∈ L : 〈s, t〉 ∈ M} regular?
Example
• M = {〈t , σ(t , t)〉 | t ∈ TΣ}• infinite, but regular tree language L ⊆ TΣ
Then M(L) = {σ(t , t) | t ∈ L} is not regular.
How to train your multi bottom-up tree transducer A. Maletti · 21
Preservation of Regularity
Input
• MBOT M• regular tree language L
QuestionIs M(L) = {t | ∃s ∈ L : 〈s, t〉 ∈ M} regular?
Example
• M = {〈t , σ(t , t)〉 | t ∈ TΣ}• infinite, but regular tree language L ⊆ TΣ
Then M(L) = {σ(t , t) | t ∈ L} is not regular.
How to train your multi bottom-up tree transducer A. Maletti · 21
Preservation of Regularity
Why desired?
• easy and efficient representation of output languages• allows intersection with (regular) language model• allows bucket-brigade algorithms
[May, Knight, Vogler, 2010]
How to train your multi bottom-up tree transducer A. Maletti · 22
Rule Composition
Input rules
S
NP V P
S—VP
V P V P NP
VP
VBD
signed
PP V P—PV
twlY
NP-OBJ
NP
DET-NN
AltwqyE
PP
Output rule
S
NP VP
VBD
signed
PP
S—
VP
PV
twlY
NP-OBJ
NP
DET-NN
AltwqyE
PP
NP
How to train your multi bottom-up tree transducer A. Maletti · 23
Rule Composition
Power MBOT
Mk = {R1 ◦ · · · ◦ Rk | R1, . . . ,Rk ∈ M}
Explanation
• Mk contains k -fold composed rules• composition fails if states do not match• composition succeeds (with no effect) if no matchable
states present
How to train your multi bottom-up tree transducer A. Maletti · 24
Finitely Collapsing
DefinitionM is finitely collapsing if there exists k ∈ N such that• every state occurs at most once in rhs of every rule of Mk .
Example
S
NP V P
S—VP
V P V P NP
VP
VBD
signed
PP V P—PV
twlY
NP-OBJ
NP
DET-NN
AltwqyE
PP
S
NP VP
VBD
signed
PP
S—
VP
PV
twlY
NP-OBJ
NP
DET-NN
AltwqyE
PP
NP
How to train your multi bottom-up tree transducer A. Maletti · 25
Finite Synchronization
DefinitionM has finite synchronization if there exists k ∈ N such that• all occurrences of a state occur in the same tree in the rhs
of every rule of Mk .
Theorem (Raoult, 1997)MBOT with finite synchronization and finitely collapsing MBOTpreserve regularity.
How to train your multi bottom-up tree transducer A. Maletti · 26
Finite Synchronization
DefinitionM has finite synchronization if there exists k ∈ N such that• all occurrences of a state occur in the same tree in the rhs
of every rule of Mk .
Theorem (Raoult, 1997)MBOT with finite synchronization and finitely collapsing MBOTpreserve regularity.
How to train your multi bottom-up tree transducer A. Maletti · 26
Copy-free
DefinitionM is copy-free if there exists k ∈ N such that for every ruleof Mk and all occurrences w of a state:• w is the root of a tree in the rhs or• w belongs to a fixed tree in the rhs.
Example (not copy-free)
X
xq—
X
c
X
c
X
qq—
X
a q
X
a q
X
qq—
X
b q
X
b qq S—
σ
q q
How to train your multi bottom-up tree transducer A. Maletti · 27
Copy-free
DefinitionM is copy-free if there exists k ∈ N such that for every ruleof Mk and all occurrences w of a state:• w is the root of a tree in the rhs or• w belongs to a fixed tree in the rhs.
Example (copy-free)
Y
X SS—
Z
X X S
X
XX— X X
X
Y
S1 S2
X— S1 S2
How to train your multi bottom-up tree transducer A. Maletti · 27
Main Result
TheoremCopy-free MBOT preserve regularity.
Theoremfinitely collapsing ⊂ finite synchronization ⊂ copy-free
NoteAll 3 restrictions can be guaranteed during rule extraction.
How to train your multi bottom-up tree transducer A. Maletti · 28
Main Result
TheoremCopy-free MBOT preserve regularity.
Theoremfinitely collapsing ⊂ finite synchronization ⊂ copy-free
NoteAll 3 restrictions can be guaranteed during rule extraction.
How to train your multi bottom-up tree transducer A. Maletti · 28
Main Result
TheoremCopy-free MBOT preserve regularity.
Theoremfinitely collapsing ⊂ finite synchronization ⊂ copy-free
NoteAll 3 restrictions can be guaranteed during rule extraction.
How to train your multi bottom-up tree transducer A. Maletti · 28
Thank you for your attention!
How to train your multi bottom-up tree transducer A. Maletti · 29
References1 ARNOLD, DAUCHET: Morphismes et bimorphismes d’arbres.
Theoret. Comput. Sci., 1982
2 ATANLP participants: Desired properties of syntax-based MT systems.ACL workshop, 2010
3 GRAEHL, KNIGHT, MAY: Training tree transducers.Computational Linguistics, 2008
4 MAY, KNIGHT: TIBURON — A weighted tree automata toolkit.In CIAA, 2006
5 MAY, KNIGHT, VOGLER: Efficient Inference through Cascades ofWeighted Tree Transducers.In ACL, 2010
6 RAOULT: Rational tree relations.Bull. Belg. Math. Soc. Simon Stevin, 1997
7 SUN, ZHANG, TAN: A non-contiguous tree sequence alignment-basedmodel for statistical machine translation.In ACL, 2009
How to train your multi bottom-up tree transducer A. Maletti · 30