Upload
kellen-mckenzie
View
217
Download
0
Tags:
Embed Size (px)
Citation preview
July 11, 2010ACL 2010 Tutorial, Uppsala,
Sweden 1
Tree-based and Forest-based Translation
Yang Liu Liang HuangInstitute of Computing
TechnologyChinese Academy of Sciences
Information Sciences InstituteUniversity of Southern
California
July 11, 2010ACL 2010 Tutorial, Uppsala,
Sweden 2
Outline
Part 1: Tree-based Translation Overview and Motivation Tree-to-String Model and Decoding Tree-to-String Rule Extraction Language Model-Integrated Decoding: Cube Pruning
Part 2: Forest-based Translation Packed Forest Forest-based Decoding Forest-based Rule Extraction
Part 3: Extensions Tree-to-Tree Translation Tree Sequence-based Translation Joint Parsing and Translation
Part 4: Conclusion
July 11, 2010ACL 2010 Tutorial, Uppsala,
Sweden 3
Natural Languages are Different
I love you
By Google Translate
我爱你
Je t'aime
Ich liebe dich
Eu te amo
Te quiero
Я люблю тебя
わたしは、あなたを愛しています
당신을 사랑합니다
دارم دوست را شما من
Jag älskar dig
Ti amo Miluji tě
Ik hou van je
Tôi yêu bạn
אני אוהב אותך
ผมรั�กคุ�ณ
July 11, 2010ACL 2010 Tutorial, Uppsala,
Sweden 4
Translation is Hard!
connocting poopie
HELP ONESELF TERMINATING MACHINE
July 11, 2010ACL 2010 Tutorial, Uppsala,
Sweden 5
Machine Translation
布什 与 沙龙 举行 了 会谈bushi yu shalong juxing le huitan
Bush held a talk with Sharon
July 11, 2010ACL 2010 Tutorial, Uppsala,
Sweden 6
Word-based MT
bushi yu shalong juxing le huitan
Bush held a talk with Sharon
(Brown et al., 1993)
July 11, 2010ACL 2010 Tutorial, Uppsala,
Sweden 7
Phrase-based MT
bushi yu shalong juxing le huitan
Bush held a talk with Sharon
(Koehn et al., 2003; Och and Ney, 2004)
July 11, 2010ACL 2010 Tutorial, Uppsala,
Sweden 8
Hierarchical Phrase-based MT
bushi yu shalong juxing le huitan
Bush held a talk with Sharon
(Chiang, 2005; Chiang, 2007)
X1
X1
X2
X2
X3
X3X3->(X1 yu shalong X2, X1 X2 with
Sharon)
July 11, 2010ACL 2010 Tutorial, Uppsala,
Sweden 9
Syntax-based MT
bushi yu shalong juxing le huitan
Bush held a talk with Sharon
NNP VBD DT NN IN NNP
NP NP
PP
VP
NP
S(Yamda and Knight, 2001; Galley et al., 2006; Shen et
al., 2008)
July 11, 2010ACL 2010 Tutorial, Uppsala,
Sweden 10
Motivation
Human Translation Understand the source sentence Generate the target sentence
Compiling Parse input program into a syntax tree Generate code in machine language
July 11, 2010ACL 2010 Tutorial, Uppsala,
Sweden 11
Syntax-Directed Translation for Compiling
Input: y:=3*x+z Parsing:
:=
id +
* id
const id
(y)
(3) (x)
(z)
(Irons, 1961; Lewis and Stearns, 1968; Aho and Ullman., 1972)
July 11, 2010ACL 2010 Tutorial, Uppsala,
Sweden 12
Motivation
Human Translation Understand the source sentence Generate the target sentence
Compiling Parse input program into a syntax tree Generate code in machine language
Machine Translation Parse the source sentence into a tree Recursively transfer the tree into the target
language
July 11, 2010ACL 2010 Tutorial, Uppsala,
Sweden 13
Syntax-Directed Translation for MT Input: bushi yu shalong juxing le huitan Parsing:
bushi yu shalong juxing le huitan
NPB P NPB VS AS NPB
PP VPB
VP
IP
(Huang et al., 2006)
July 11, 2010ACL 2010 Tutorial, Uppsala,
Sweden 14
Outline
Part 1: Tree-based Translation Overview and Motivation Tree-to-String Model and Decoding Tree-to-String Rule Extraction Language Model-Integrated Decoding: Cube Pruning
Part 2: Forest-based Translation Packed Forest Forest-based Decoding Forest-based Rule Extraction
Part 3: Extensions Tree-to-Tree Translation Tree Sequence-based Translation Joint Parsing and Translation
Part 4: Conclusion
July 11, 2010ACL 2010 Tutorial, Uppsala,
Sweden 15
Tree-to-String Translation Recursive rewrite by pattern-matching
bushi yu shalong juxing le huitan
NPB P NPB VS AS NPB
PP VPB
VP
IP
IP
X1:NPB X2:VP
X1 X2
(Liu et al., 2006; Huang et al., 2006)
July 11, 2010ACL 2010 Tutorial, Uppsala,
Sweden 16
Tree-to-String Translation Recursive rewrite by pattern-matching
bushi yu shalong juxing le huitan
NPB P NPB VS AS NPB
PP VPB
VP
(Liu et al., 2006; Huang et al., 2006)
bushi
NPB
Bush
July 11, 2010ACL 2010 Tutorial, Uppsala,
Sweden 17
Tree-to-String Translation Recursive rewrite by pattern-matching
Bush yu shalong juxing le huitan
P NPB VS AS NPB
PP VPB
VP
(Liu et al., 2006; Huang et al., 2006)
VP
X1:PP X2:VPB
X2 X1
July 11, 2010ACL 2010 Tutorial, Uppsala,
Sweden 18
Tree-to-String Translation Recursive rewrite by pattern-matching
Bush yu shalong
P NPB
PP
juxing le huitan
VS AS NPB
VPB
(Liu et al., 2006; Huang et al., 2006)
VPB
VS AS X1:NPB
lejuxing
held a X1
July 11, 2010ACL 2010 Tutorial, Uppsala,
Sweden 19
Tree-to-String Translation Recursive rewrite by pattern-matching
Bush yu shalong
P NPB
PP
held a huitan
NPB
(Liu et al., 2006; Huang et al., 2006)
huitan
NPB
talk
July 11, 2010ACL 2010 Tutorial, Uppsala,
Sweden 20
Tree-to-String Translation Recursive rewrite by pattern-matching
Bush yu shalong
P NPB
PP
held a talk
(Liu et al., 2006; Huang et al., 2006)
yu
P X1:NPB
PP
with X1
July 11, 2010ACL 2010 Tutorial, Uppsala,
Sweden 21
Tree-to-String Translation Recursive rewrite by pattern-matching
Bush with shalong
NPB
held a talk
(Liu et al., 2006; Huang et al., 2006)
shalong
NPB
Sharon
July 11, 2010ACL 2010 Tutorial, Uppsala,
Sweden 22
Tree-to-String Translation Recursive rewrite by pattern-matching
Bush with Sharonheld a talk
(Liu et al., 2006; Huang et al., 2006)
Syntax-directed translation (e.g., Irons, 1961)
Tree transducer (e.g., Knight and Graehl, 2005)
Synchronous grammar (e.g., Eisner, 2003)
…
Tree-to-string translation
July 11, 2010ACL 2010 Tutorial, Uppsala,
Sweden 23
Expressive Power
PP
P NPB
yu shalong
with Sharon
phrasal translation non-constituent phrase non-contiguous phrase
VPB
VS AS X1:NPB
lejuxing
held a X1
PP
PLCP
dangX1:IP LC
hou
when X1
word omission
QP
X1:CD CLP
ben
X1
multilevel re-ordering
IP
X1:NP
VP
X2:IP X3:VPB
X1 X3 X2
lexicalized re-ordering
NP
DNP X2:NP
X1:NP DEG
X2 of X1
de
(Knight and Graehl, 2005)
July 11, 2010ACL 2010 Tutorial, Uppsala,
Sweden 24
Outline
Part 1: Tree-based Translation Overview and Motivation Tree-to-String Model and Decoding Tree-to-String Rule Extraction Language Model-Integrated Decoding: Cube Pruning
Part 2: Forest-based Translation Packed Forest Forest-based Decoding Forest-based Rule Extraction
Part 3: Extensions Tree-to-Tree Translation Tree Sequence-based Translation Joint Parsing and Translation
Part 4: Conclusion
July 11, 2010ACL 2010 Tutorial, Uppsala,
Sweden 25
NPBASVSNPBP
Tree-to-String Rule Extraction Compute target spans
Bush held a talk with Sharon
bushi yu shalong
juxing
le huitan
“Bush”
“with”
“Sharon”
“held”
“held”
“talk”
“with Sharon”
“held a talk”
“held … Sharon”
“Bush … Sharon”
NPB
VPB
VP
IP
PP
(Galley et al., 2004)
July 11, 2010ACL 2010 Tutorial, Uppsala,
Sweden 26
NPBASVSNPBP
Tree-to-String Rule Extraction Find admissible nodes
Bush held a talk with Sharon
bushi yu shalong
juxing
le huitan
“Bush”
“with”
“Sharon”
“held”
“held”
“talk”
“with Sharon”
“held a talk”
“held … Sharon”
“Bush … Sharon”
NPB
VPB
VP
IP
PP
(Galley et al., 2004)
July 11, 2010ACL 2010 Tutorial, Uppsala,
Sweden 27
NPBASVSNPBP
Tree-to-String Rule Extraction Extract minimal rules
Bush held a talk with Sharon
bushi yu shalong
juxing
le huitan
“Bush”
“with”
“Sharon”
“held”
“held”
“talk”
“with Sharon”
“held a talk”
“held … Sharon”
“Bush … Sharon”
NPB
VPB
VP
IP
PP
(Galley et al., 2004)
bushi
NPB
Bush
July 11, 2010ACL 2010 Tutorial, Uppsala,
Sweden 28
NPBASVSNPBP
Tree-to-String Rule Extraction Extract minimal rules
Bush held a talk with Sharon
bushi yu shalong
juxing
le huitan
“Bush”
“with”
“Sharon”
“held”
“held”
“talk”
“with Sharon”
“held a talk”
“held … Sharon”
“Bush … Sharon”
NPB
VPB
VP
IP
PP
(Galley et al., 2004)
VP
X1:PP X2:VPB
X2 X1
July 11, 2010ACL 2010 Tutorial, Uppsala,
Sweden 29
NPBASVSNPBP
Tree-to-String Rule Extraction Extract minimal rules
Bush held a talk with Sharon
bushi yu shalong
juxing
le huitan
“Bush”
“with”
“Sharon”
“held”
“held”
“talk”
“with Sharon”
“held a talk”
“held … Sharon”
“Bush … Sharon”
NPB
VPB
VP
IP
PP
(Galley et al., 2004)
VPB
VS AS X1:NPB
lejuxing
held a X1
July 11, 2010ACL 2010 Tutorial, Uppsala,
Sweden 30
Tree-to-String Rule Extraction Get composed rules
VPB
VS AS X1:NPB
lejuxing
held a X1
huitan
NPB
talk
VPB
VS AS NPB
lejuxing
held a
huitan
talk
+ =
(Galley et al., 2006)
tree substitution
July 11, 2010ACL 2010 Tutorial, Uppsala,
Sweden 31
Outline
Part 1: Tree-based Translation Overview and Motivation Tree-to-String Model and Decoding Tree-to-String Rule Extraction Language Model-Integrated Decoding: Cube
Pruning Part 2: Forest-based Translation
Packed Forest Forest-based Decoding Forest-based Rule Extraction
Part 3: Extensions Tree-to-Tree Translation Tree Sequence-based Translation Joint Parsing and Translation
Part 4: Conclusion
July 11, 2010ACL 2010 Tutorial, Uppsala,
Sweden 32
Bottom-up Decoding
bushi yu shalong juxing le huitan
NPB P NPB VS AS NPB
PP VPB
VP
IP
bushi
NPB
Bush
Bush
(Liu et al., 2006; Huang et al., 2006)
July 11, 2010ACL 2010 Tutorial, Uppsala,
Sweden 33
Bottom-up Decoding
bushi yu shalong juxing le huitan
NPB P NPB VS AS NPB
PP VPB
VP
IP
Bush
shalong
NPB
Sharon
Sharon
(Liu et al., 2006; Huang et al., 2006)
July 11, 2010ACL 2010 Tutorial, Uppsala,
Sweden 34
Bottom-up Decoding
bushi yu shalong juxing le huitan
NPB P NPB VS AS NPB
PP VPB
VP
IP
BushSharon
huitan
NPB
talk
talk
(Liu et al., 2006; Huang et al., 2006)
July 11, 2010ACL 2010 Tutorial, Uppsala,
Sweden 35
Bottom-up Decoding
bushi yu shalong juxing le huitan
NPB P NPB VS AS NPB
PP VPB
VP
IP
BushSharon talk
yu
P X1:NPB
PP
with X1
with Sharon
(Liu et al., 2006; Huang et al., 2006)
July 11, 2010ACL 2010 Tutorial, Uppsala,
Sweden 36
Bottom-up Decoding
bushi yu shalong juxing le huitan
NPB P NPB VS AS NPB
PP VPB
VP
IP
BushSharon talk
with Sharon
VPB
VS AS X1:NPB
lejuxing
held a X1
held a talk
(Liu et al., 2006; Huang et al., 2006)
July 11, 2010ACL 2010 Tutorial, Uppsala,
Sweden 37
Bottom-up Decoding
bushi yu shalong juxing le huitan
NPB P NPB VS AS NPB
PP VPB
VP
IP
BushSharon talk
with Sharonheld a talk
VP
X1:PP X2:VPB
X2 X1
held a talk with Sharon
(Liu et al., 2006; Huang et al., 2006)
July 11, 2010ACL 2010 Tutorial, Uppsala,
Sweden 38
Bottom-up Decoding
bushi yu shalong juxing le huitan
NPB P NPB VS AS NPB
PP VPB
VP
IP
BushSharon talk
with Sharonheld a talk
held a talk with Sharon
IP
X1:NPB X2:VP
X1 X2
Bush held a talk with Sharon
(Liu et al., 2006; Huang et al., 2006)
July 11, 2010ACL 2010 Tutorial, Uppsala,
Sweden 39
Beam Search
bushi yu shalong juxing le huitan
NPB P NPB VS AS NPB
PP VPB
VP
IP
(Liu et al., 2006; Huang et al., 2006)
July 11, 2010ACL 2010 Tutorial, Uppsala,
Sweden 40
Exhaustive Search
VP
X1:PP X2:VPB
X2 X1
held a talkheld talkshold a talkhold talks
VPB3,6PP1,3
VP1,6
held a talk with Sharonheld a talk and Sharonheld talks with Sharonheld talks and Sharon…
with Sharonand SharonSharon withSharon and
July 11, 2010ACL 2010 Tutorial, Uppsala,
Sweden 41
Update Bigram LM Probability
with Sharon held a talk
p1=p(“with’’) * p(“Sharon”|”with”)
p2=p(“held’’) * p(“a”|”held”)*p(“talk”|”a”)
with Sharon held a talk
held a talk with Sharon
p1*p2*p(“held”|”Sharon”)/p(“held”)
p1*p2*p(“with”|”talk”)/p(“with”)
Only boundary words are used to update LM probability!
July 11, 2010ACL 2010 Tutorial, Uppsala,
Sweden 42
Exhaustive Search with a Bigram Language Model
VP
X1:PP X2:VPB
X2 X1
held * talkheld * talkshold * talkhold * talks
VPB3,6PP1,3
VP1,6
held * Sharonhold * Sharonheld * withhold * with…
with * Sharonand * SharonSharon * withSharon * and
July 11, 2010ACL 2010 Tutorial, Uppsala,
Sweden 43
Monotonicity
VPB3,6PP1,3
VP1,6
1.0 3.0 4.0
1.0 2.0 4.0 5.0
1.1 2.1 4.1 5.1
2.0 6.0
held * talk
held * talkshold * talkhold * talks
with
* Sha
ron
and
* Sha
ron
Sharo
n *
with
Sharo
n *
and
6.5
7.5
7.6
8.5
3.5 4.5 6.5 7.5 10.0
3.0 5.0VPB3,6
PP1,3
(Huang and Chiang, 2005, 2007; Chiang, 2007)
monotonic
July 11, 2010ACL 2010 Tutorial, Uppsala,
Sweden 44
Non-Monotonicity
VPB3,6PP1,3
VP1,6
1.0 3.0 4.0
1.0 2.0 + 0.54.0 + 2.05.0 + 4.0
1.1 2.1 + 0.34.1 + 1.55.1 + 3.5
2.0 6.0 + 4.0
held * talk
held * talkshold * talkhold * talks
with
* Sha
ron
and
* Sha
ron
Sharo
n *
with
Sharo
n *
and
6.5
7.5 + 4.0
7.6 + 3.0
8.5 + 4.0
3.5 4.5 + 0.36.5 + 1.57.5 + 3.510 + 3.5
3.0 + 0.55.0 + 2.0VPB3,6
PP1,3
(Huang and Chiang, 2005, 2007; Chiang, 2007)
log(p(with|talk))-log(p(with))
LM introduces non-monotonicity
July 11, 2010ACL 2010 Tutorial, Uppsala,
Sweden 45
Cube Pruning
1.0 3.0 4.0
1.0 2.5 6.0 9.0
1.1 2.4 5.6 8.6
2.0 10.0
held * talk
held * talkshold * talkhold * talks
with
* Sha
ron
and
* Sha
ron
Sharo
n *
with
Sharo
n *
and
6.5
11.5
10.6
12.5
3.5 4.8 8.0 11.0 13.5
3.5 7.0VPB3,6
PP1,3
queue
4-best
(Huang and Chiang, 2005, 2007; Chiang, 2007)
July 11, 2010ACL 2010 Tutorial, Uppsala,
Sweden 46
Cube Pruning
1.0 3.0 4.0
1.0 2.5 6.0 9.0
1.1 2.4 5.6 8.6
2.0 10.0
held * talk
held * talkshold * talkhold * talks
with
* Sha
ron
and
* Sha
ron
Sharo
n *
with
Sharo
n *
and
6.5
11.5
10.6
12.5
3.5 4.8 8.0 11.0 13.5
3.5 7.0VPB3,6
PP1,3
queue
4-best
2.5
(Huang and Chiang, 2005, 2007; Chiang, 2007)
July 11, 2010ACL 2010 Tutorial, Uppsala,
Sweden 47
Cube Pruning
1.0 3.0 4.0
1.0 2.5 6.0 9.0
1.1 2.4 5.6 8.6
2.0 10.0
held * talk
held * talkshold * talkhold * talks
with
* Sha
ron
and
* Sha
ron
Sharo
n *
with
Sharo
n *
and
6.5
11.5
10.6
12.5
3.5 4.8 8.0 11.0 13.5
3.5 7.0VPB3,6
PP1,3
queue
4-best 2.5
2.4 6.0
(Huang and Chiang, 2005, 2007; Chiang, 2007)
July 11, 2010ACL 2010 Tutorial, Uppsala,
Sweden 48
Cube Pruning
1.0 3.0 4.0
1.0 2.5 6.0 9.0
1.1 2.4 5.6 8.6
2.0 10.0
held * talk
held * talkshold * talkhold * talks
with
* Sha
ron
and
* Sha
ron
Sharo
n *
with
Sharo
n *
and
6.5
11.5
10.6
12.5
3.5 4.8 8.0 11.0 13.5
3.5 7.0VPB3,6
PP1,3
queue
4-best 2.4
3.5 5.6
2.5
6.0
(Huang and Chiang, 2005, 2007; Chiang, 2007)
July 11, 2010ACL 2010 Tutorial, Uppsala,
Sweden 49
Cube Pruning
1.0 3.0 4.0
1.0 2.5 6.0 9.0
1.1 2.4 5.6 8.6
2.0 10.0
held * talk
held * talkshold * talkhold * talks
with
* Sha
ron
and
* Sha
ron
Sharo
n *
with
Sharo
n *
and
6.5
11.5
10.6
12.5
3.5 4.8 8.0 11.0 13.5
3.5 7.0VPB3,6
PP1,3
queue
4-best 2.4
4.8
2.5
5.6
3.5
(Huang and Chiang, 2005, 2007; Chiang, 2007)
6.0 7.0
July 11, 2010ACL 2010 Tutorial, Uppsala,
Sweden 50
Cube Pruning
1.0 3.0 4.0
1.0 2.5 6.0 9.0
1.1 2.4 5.6 8.6
2.0 10.0
held * talk
held * talkshold * talkhold * talks
with
* Sha
ron
and
* Sha
ron
Sharo
n *
with
Sharo
n *
and
6.5
11.5
10.6
12.5
3.5 4.8 8.0 11.0 13.5
3.5 7.0VPB3,6
PP1,3
queue
4-best 2.4 4.82.5
5.6
3.5
(Huang and Chiang, 2005, 2007; Chiang, 2007)
6.07.0
July 11, 2010ACL 2010 Tutorial, Uppsala,
Sweden 51
Cube Pruning within Rule GroupVPB
VS AS X1:NPB
lejuxing
held a X1
VPB
VS AS X1:NPB
lejuxing
held X1
VPB
VS AS X1:NPB
lejuxing
hold a X1
1.0
1.4
2.0
1.0 2.0 2.5
2.1
3.2
3.1
5.0
4.0
6.0
3.7
5.0
4.7
held a X1
held X1
hold a X1
talk
talk
sm
eetin
g
Group rules that have the same LHS
NPB5,6
(Huang and Chiang, 2005, 2007; Chiang, 2007)
July 11, 2010ACL 2010 Tutorial, Uppsala,
Sweden 52
Cube Pruning within Node
VP1,6
PP1,3 VPB3,6 NPB2,3 NPB5,6 NPB2,3 VPB3,6
process all rules simultaneously!significant savings of computation
(Huang and Chiang, 2005, 2007; Chiang, 2007)
July 11, 2010ACL 2010 Tutorial, Uppsala,
Sweden 53
Outline
Part 1: Tree-based Translation Overview and Motivation Tree-to-String Model and Decoding Tree-to-String Rule Extraction Language Model-Integrated Decoding: Cube Pruning
Part 2: Forest-based Translation Packed Forest Forest-based Decoding Forest-based Rule Extraction
Part 3: Extensions Tree-to-Tree Translation Tree Sequence-based Translation Joint Parsing and Translation
Part 4: Conclusion
July 11, 2010ACL 2010 Tutorial, Uppsala,
Sweden 54
Syntactic Ambiguity
bushi yu shalong juxing le huitan
NPB P NPB VS AS NPB
PP VPB
VP
IP
bushi yu shalong juxing le huitan
NPB CC NPB VS AS NPB
NP VPB
IP
with and
``Bush held a talk with Sharon’’
``Bush and Sharon held a talk’’
It is important to choose a correct tree for producing a good translation!
July 11, 2010ACL 2010 Tutorial, Uppsala,
Sweden 55
Parsing Mistake Propagation
parsing mistakes potentially introduce translation mistakes!
(Quirk and Corston-Oliver, 2006)
parse translatesourcetarget
string tree
string
July 11, 2010ACL 2010 Tutorial, Uppsala,
Sweden 56
1-best Trees => n-best Trees?
bushi yu shalong juxing le huitan
NPB P NPB VS AS NPB
PP VPB
VP
IP
bushi yu shalong juxing le huitan
NPB CC NPB VS AS NPB
NP VPB
IP
Very few variations among the n-best trees!
July 11, 2010ACL 2010 Tutorial, Uppsala,
Sweden 57
Packed Forest
bushi yu shalong juxing le huitan
NPB0,1CC1,2 NPB2,3 VS3,4 AS4,5 NPB5,6
PP1,3 VPB3,6
VP1,6
IP0,6
P1,2
NP0,3
(Billot and Lang, 1989; Klein and Manning, 2001; Huang and Chiang, 2005)
July 11, 2010ACL 2010 Tutorial, Uppsala,
Sweden 58
Outline
Part 1: Tree-based Translation Overview and Motivation Tree-to-String Model and Decoding Tree-to-String Rule Extraction Language Model-Integrated Decoding: Cube Pruning
Part 2: Forest-based Translation Packed Forest Forest-based Decoding Forest-based Rule Extraction
Part 3: Extensions Tree-to-Tree Translation Tree Sequence-based Translation Joint Parsing and Translation
Part 4: Conclusion
July 11, 2010ACL 2010 Tutorial, Uppsala,
Sweden 59
Pattern Matching on Forest
bushi yu shalong juxing le huitan
NPB0,1CC1,2 NPB2,3 VS3,4 AS4,5 NPB5,6
PP1,3 VPB3,6
VP1,6
IP0,6
P1,2
NP0,3
IP
NP X3:VPB
X1:NPB CC X2:NPB
yu
X1 X3 with X2
(Mi et al., 2008)
July 11, 2010ACL 2010 Tutorial, Uppsala,
Sweden 60
Translation Forest
(Mi et al., 2008)bushi yu shalong juxing le huitan
NPB0,1CC1,2 NPB2,3 VS3,4 AS4,5 NPB5,6
PP1,3 VPB3,6
VP1,6
IP0,6
P1,2
NP0,3
bushi
NPB
Bush
NPB0,1
July 11, 2010ACL 2010 Tutorial, Uppsala,
Sweden 61
Translation Forest
(Mi et al., 2008)bushi yu shalong juxing le huitan
NPB0,1CC1,2 NPB2,3 VS3,4 AS4,5 NPB5,6
PP1,3 VPB3,6
VP1,6
IP0,6
P1,2
NP0,3
bushi
NPB
Bush
NPB0,1
shalong
NPB
Sharon
NPB2,3
July 11, 2010ACL 2010 Tutorial, Uppsala,
Sweden 62
Translation Forest
(Mi et al., 2008)bushi yu shalong juxing le huitan
NPB0,1CC1,2 NPB2,3 VS3,4 AS4,5 NPB5,6
PP1,3 VPB3,6
VP1,6
IP0,6
P1,2
NP0,3
bushi
NPB
Bush
NPB0,1
shalong
NPB
Sharon
NPB2,3
huitan
NPB
talk
NPB5,6
July 11, 2010ACL 2010 Tutorial, Uppsala,
Sweden 63
Translation Forest
(Mi et al., 2008)bushi yu shalong juxing le huitan
NPB0,1CC1,2 NPB2,3 VS3,4 AS4,5 NPB5,6
PP1,3 VPB3,6
VP1,6
IP0,6
P1,2
NP0,3
bushi
NPB
Bush
NPB0,1
shalong
NPB
Sharon
NPB2,3
huitan
NPB
talk
NPB5,6
VPB
VS ASX1:NPB
lejuxing
held a X1
VPB3,6
July 11, 2010ACL 2010 Tutorial, Uppsala,
Sweden 64
Translation Forest
(Mi et al., 2008)bushi yu shalong juxing le huitan
NPB0,1CC1,2 NPB2,3 VS3,4 AS4,5 NPB5,6
PP1,3 VPB3,6
VP1,6
IP0,6
P1,2
NP0,3
bushi
NPB
Bush
NPB0,1
shalong
NPB
Sharon
NPB2,3
huitan
NPB
talk
NPB5,6
VPB
VS ASX1:NPB
lejuxing
held a X1
VPB3,6
IP
NP X3:VPB
X1:NPB CC X2:NPB
yu
X1 X3 with X2
IP0,6
``Bush’’
``Sharon’’
``talk’’
``held a talk’’
``Bush held a talk with Sharon’’
July 11, 2010ACL 2010 Tutorial, Uppsala,
Sweden 65
N-best Trees Vs. Forest
(Mi et al., 2008)
July 11, 2010ACL 2010 Tutorial, Uppsala,
Sweden 66
Forest as Virtual ∞-best list How often is the ith-best tree picked by the
decoder?
(Mi et al., 2008)
July 11, 2010ACL 2010 Tutorial, Uppsala,
Sweden 67
Outline
Part 1: Tree-based Translation Overview and Motivation Tree-to-String Model and Decoding Tree-to-String Rule Extraction Language Model-Integrated Decoding: Cube Pruning
Part 2: Forest-based Translation Packed Forest Forest-based Decoding Forest-based Rule Extraction
Part 3: Extensions Tree-to-Tree Translation Tree Sequence-based Translation Joint Parsing and Translation
Part 4: Conclusion
July 11, 2010ACL 2010 Tutorial, Uppsala,
Sweden 68
Forest-based Rule Extraction
bushi yu shalong juxing le huitan
NPB0,1CC1,2 NPB2,3 VS3,4 AS4,5 NPB5,6
PP1,3 VPB3,6
VP1,6
IP0,6
P1,2
NP0,3
Compute target spans
Bush held a talk with Sharon
“Bush”
“with”
“with”
“Sharon”
“held”
“held”
“talk”
“Bush □ with Sharon”
“with Sharon” “held … talk”
“held … Sharon”
“Bush … Sharon”
(Mi and Huang, 2008)
July 11, 2010ACL 2010 Tutorial, Uppsala,
Sweden 69
Forest-based Rule Extraction
bushi yu shalong juxing le huitan
NPB0,1CC1,2 NPB2,3 VS3,4 AS4,5 NPB5,6
PP1,3 VPB3,6
VP1,6
IP0,6
P1,2
NP0,3
Compute admissible nodes
Bush held a talk with Sharon
“Bush”
“with”
“with”
“Sharon”
“held”
“held”
“talk”
“Bush □ with Sharon”
“with Sharon” “held … talk”
“held … Sharon”
“Bush … Sharon”
(Mi and Huang, 2008)
July 11, 2010ACL 2010 Tutorial, Uppsala,
Sweden 70
Forest-based Rule Extraction
bushi yu shalong juxing le huitan
NPB0,1CC1,2 NPB2,3 VS3,4 AS4,5 NPB5,6
PP1,3 VPB3,6
VP1,6
IP0,6
P1,2
NP0,3
Extract minimal rules
Bush held a talk with Sharon
“Bush”
“with”
“with”
“Sharon”
“held”
“held”
“talk”
“Bush □ with Sharon”
“with Sharon” “held … talk”
“held … Sharon”
“Bush … Sharon” bushi
NPB
Bush
(Mi and Huang, 2008)
July 11, 2010ACL 2010 Tutorial, Uppsala,
Sweden 71
Forest-based Rule Extraction
bushi yu shalong juxing le huitan
NPB0,1CC1,2 NPB2,3 VS3,4 AS4,5 NPB5,6
PP1,3 VPB3,6
VP1,6
IP0,6
P1,2
NP0,3
Extract minimal rules
Bush held a talk with Sharon
“Bush”
“with”
“with”
“Sharon”
“held”
“held”
“talk”
“Bush □ with Sharon”
“with Sharon” “held … talk”
“held … Sharon”
“Bush … Sharon”
VP
X1:PP X2:VPB
X2 X1
(Mi and Huang, 2008)
July 11, 2010ACL 2010 Tutorial, Uppsala,
Sweden 72
Forest-based Rule Extraction
bushi yu shalong juxing le huitan
NPB0,1CC1,2 NPB2,3 VS3,4 AS4,5 NPB5,6
PP1,3 VPB3,6
VP1,6
IP0,6
P1,2
NP0,3
Extract minimal rules
Bush held a talk with Sharon
“Bush”
“with”
“with”
“Sharon”
“held”
“held”
“talk”
“Bush □ with Sharon”
“with Sharon” “held … talk”
“held … Sharon”
“Bush … Sharon”
VPB
VS AS X1:NPB
lejuxing
held a X1
(Mi and Huang, 2008)
July 11, 2010ACL 2010 Tutorial, Uppsala,
Sweden 73
Forest-based Rule Extraction
bushi yu shalong juxing le huitan
NPB0,1CC1,2 NPB2,3 VS3,4 AS4,5 NPB5,6
PP1,3 VPB3,6
VP1,6
IP0,6
P1,2
NP0,3
Extract minimal rules
Bush held a talk with Sharon
“Bush”
“with”
“with”
“Sharon”
“held”
“held”
“talk”
“Bush □ with Sharon”
“with Sharon” “held … talk”
“held … Sharon”
“Bush … Sharon”
IP
X1:NPB X2:VP
X1 X2
(Mi and Huang, 2008)
July 11, 2010ACL 2010 Tutorial, Uppsala,
Sweden 74
Forest-based Rule Extraction
bushi yu shalong juxing le huitan
NPB0,1CC1,2 NPB2,3 VS3,4 AS4,5 NPB5,6
PP1,3 VPB3,6
VP1,6
IP0,6
P1,2
NP0,3
Extract minimal rules
Bush held a talk with Sharon
“Bush”
“with”
“with”
“Sharon”
“held”
“held”
“talk”
“Bush □ with Sharon”
“with Sharon” “held … talk”
“held … Sharon”
“Bush … Sharon”
IP
NP X4:VPB
X1:NPBX2:CCX3:NPB
X1 X3 X4 X2
(Mi and Huang, 2008)
July 11, 2010ACL 2010 Tutorial, Uppsala,
Sweden 75
Rule Probabilities and Rule Count
': '
': '
': '
|'
|'
|'
r lhs r lhs r
r rhs r rhs r
r root lhs r root lhs r
c rP r lhs r
c r
c rP r rhs r
c r
c rP r root lhs r
c r
How often does a rule occur in training examples?
July 11, 2010ACL 2010 Tutorial, Uppsala,
Sweden 76
Fractional Count
bushi yu shalong juxing le huitan
NPB0,1CC1,2 NPB2,3 VS3,4 AS4,5 NPB5,6
PP1,3 VPB3,6
VP1,6
IP0,6
P1,2
NP0,3
Bush held a talk with Sharon
“Bush”
“with”
“with”
“Sharon”
“held”
“held”
“talk”
“Bush □ with Sharon”
“with Sharon” “held … talk”
“held … Sharon”
“Bush … Sharon”
VP
X1:PP X2:VPB
X2 X1
(Mi and Huang, 2008)
Q: What ‘s the count of this rule on this training example?
July 11, 2010ACL 2010 Tutorial, Uppsala,
Sweden 77
Fractional Count
bushi yu shalong juxing le huitan
NPB0,1CC1,2 NPB2,3 VS3,4 AS4,5 NPB5,6
PP1,3 VPB3,6
VP1,6
IP0,6
P1,2
NP0,3
Bush held a talk with Sharon
“Bush”
“with”
“with”
“Sharon”
“held”
“held”
“talk”
“Bush □ with Sharon”
“with Sharon” “held … talk”
“held … Sharon”
“Bush … Sharon”
(Mi and Huang, 2008)
1,6 1,3 3,6VP PP VPB
TOP
e p e
lhs rc r
1,6VP
1,3PP 3,6VPB
p e
July 11, 2010ACL 2010 Tutorial, Uppsala,
Sweden 78
Results
1-best tree forest
1-best tree 0.2560 0.2674
forest 0.2679 0.2816
decoding
rule
extra
ction
(Mi and Huang, 2008)
July 11, 2010ACL 2010 Tutorial, Uppsala,
Sweden 79
Outline
Part 1: Tree-based Translation Overview and Motivation Tree-to-String Model and Decoding Tree-to-String Rule Extraction Language Model-Integrated Decoding: Cube Pruning
Part 2: Forest-based Translation Packed Forest Forest-based Decoding Forest-based Rule Extraction
Part 3: Extensions Tree-to-Tree Translation Tree Sequence-based Translation Joint Parsing and Translation
Part 4: Conclusion
July 11, 2010ACL 2010 Tutorial, Uppsala,
Sweden 80
Tree-to-Tree Translation Recursive rewrite by pattern-matching
bushi yu shalong juxing le huitan
NPB P NPB VS AS NPB
PP VPB
VP
IP
NP
VP
S
IP
X1:NPB X2:VP
S
X1:NP X2:VP
(Eisner 2003, Zhang, 2007)
July 11, 2010ACL 2010 Tutorial, Uppsala,
Sweden 81
Tree-to-Tree Translation Recursive rewrite by pattern-matching
bushi yu shalong juxing le huitan
NPB P NPB VS AS NPB
PP VPB
VP
NP
VP
S
NP
Bush
NNP
bushi
NPB
Bush
NNP
NP
(Eisner 2003, Zhang, 2007)
July 11, 2010ACL 2010 Tutorial, Uppsala,
Sweden 82
Tree-to-Tree Translation Recursive rewrite by pattern-matching
yu shalong juxing le huitan
P NPB VS AS NPB
PP VPB
VP
NP
VP
S
NP
Bush
NNP
juxing le
VS ASX2:NPB
X1:PP VPB
VP
held a
VBD DT X2:NN
NP
X1:PP
VP
held a
VBD DT NN
NP
PP
(Eisner 2003, Zhang, 2007)
July 11, 2010ACL 2010 Tutorial, Uppsala,
Sweden 83
Tree-to-Tree Translation Recursive rewrite by pattern-matching
yu shalong huitan
P NPB NPB
PP
NP
VP
S
NP
Bush
NNP
held a
VBD DT NN
NP
PP
yu shalong
P NPB
PP
with Sharon
IN NNP
NP
PP
with Sharon
IN NNP
NP
(Eisner 2003, Zhang, 2007)
July 11, 2010ACL 2010 Tutorial, Uppsala,
Sweden 84
Tree-to-Tree Translation Recursive rewrite by pattern-matching
huitan
NPB
NP
VP
S
NP
Bush
NNP
held a
VBD DT NN
NP
PP
with Sharon
IN NNP
NP
huitan
NPB
talk
NN
talk
(Eisner 2003, Zhang, 2007)
July 11, 2010ACL 2010 Tutorial, Uppsala,
Sweden 85
Tree-to-Tree Translation Recursive rewrite by pattern-matching
NP
VP
S
NP
Bush
NNP
held a
VBD DT NN
NP
PP
with Sharon
IN NNP
NP
talk
(Eisner 2003, Zhang, 2007)
July 11, 2010ACL 2010 Tutorial, Uppsala,
Sweden 86
Tree-to-Tree Rule Extraction Find admissible node pairs
bushi yu shalong juxing le huitan
NPB P NPB VS AS NPB
PP VPB
VP
IP
Bush held a talk with Sharon
NNP VBD DT NN IN NNP
NP NP NP
PP
VP
S (Zhang, 2007, Liu et al., 2009a)
July 11, 2010ACL 2010 Tutorial, Uppsala,
Sweden 87
Tree-to-Tree Rule Extraction Extract minimal rules
bushi yu shalong juxing le huitan
NPB P NPB VS AS NPB
PP VPB
VP
IP
Bush held a talk with Sharon
NNP VBD DT NN IN NNP
NP NP NP
PP
VP
S
bushi
NPB
Bush
NNP
NP
(Zhang, 2007, Liu et al., 2009a)
July 11, 2010ACL 2010 Tutorial, Uppsala,
Sweden 88
Tree-to-Tree Rule Extraction Extract minimal rules
bushi yu shalong juxing le huitan
NPB P NPB VS AS NPB
PP VPB
VP
IP
Bush held a talk with Sharon
NNP VBD DT NN IN NNP
NP NP NP
PP
VP
S
juxing le
VS ASX2:NPB
X1:PP VPB
VP
held a
VBD DT X2:NN
NP
X1:PP
VP
(Zhang, 2007, Liu et al., 2009a)
July 11, 2010ACL 2010 Tutorial, Uppsala,
Sweden 89
Tree-to-Tree Rule Extraction Extract minimal rules
bushi yu shalong juxing le huitan
NPB P NPB VS AS NPB
PP VPB
VP
IP
Bush held a talk with Sharon
NNP VBD DT NN IN NNP
NP NP NP
PP
VP
S
IP
X1:NPB X2:VP
S
X1:NP X2:VP
(Zhang, 2007, Liu et al., 2009a)
July 11, 2010ACL 2010 Tutorial, Uppsala,
Sweden 90
Tree-to-Tree Rule Extraction Get composed rules
juxing le
VS ASX2:NPB
X1:PP VPB
VP
held a
VBD DT X2:NN
NP
X1:PP
VP
huitan
NPB
talk
NN
juxing le
VS AS NPB
X1:PP VPB
VP
held a
VBD DT NN
NP
X1:PP
VP
huitan
talk
+ =
(Zhang, 2007, Liu et al., 2009a)
July 11, 2010ACL 2010 Tutorial, Uppsala,
Sweden 91
Challenges
Tree-to-tree translation is over-constrained Poorest rule coverage Suffers from parsing mistake propagation
on both sides Recent advances
Use tree sequence (Zhang et al., 2008) Use packed forest (Liu et al., 2009a) Fuzzy extraction and decoding (Chiang,
2010)
July 11, 2010ACL 2010 Tutorial, Uppsala,
Sweden 92
Outline
Part 1: Tree-based Translation Overview and Motivation Tree-to-String Model and Decoding Tree-to-String Rule Extraction Language Model-Integrated Decoding: Cube Pruning
Part 2: Forest-based Translation Packed Forest Forest-based Decoding Forest-based Rule Extraction
Part 3: Extensions Tree-to-Tree Translation Tree Sequence-based Translation Joint Parsing and Translation
Part 4: Conclusion
July 11, 2010ACL 2010 Tutorial, Uppsala,
Sweden 93
Non-Constituent Phrase Pairs
bushi yu shalongjuxing le huitan
NPB CC NPB VS AS NPB
NP VPB
IP
Bush held a talk with Sharon
(Marcu et al., 2006)
July 11, 2010ACL 2010 Tutorial, Uppsala,
Sweden 94
Non-Constituent Phrase Pairs
bushi yu shalong juxing le huitan
Bush held a talk with Sharon
NNP VBD DT NN IN NNP
NP NP NP
PP
VP
S(Marcu et al., 2006)
July 11, 2010ACL 2010 Tutorial, Uppsala,
Sweden 95
Non-Constituent Phrase Pairs
bushi yu shalong juxing le huitan
NPB P NPB VS AS NPB
PP VPB
VP
IP
Bush held a talk with Sharon
NNP VBD DT NN IN NNP
NP NP NP
PP
VP
S
(Marcu et al., 2006)
July 11, 2010ACL 2010 Tutorial, Uppsala,
Sweden 96
Rule Coverage
bushi yu shalong juxing le huitan
NPB P NPB VS AS NPB
PP VPB
VP
IP
Bush held a talk with Sharon
NNP VBD DT NN IN NNP
NP NP NP
PP
VP
S
(bushi, Bush)
(yu, with)
(shalong, Sharon)(huitan, talk)
(yu shalong, with Sharon)(juxing le, held)
(juxing … huitan, held … talk)(yu … huitan, held … Sharon)(bushi … huitan, Bush … Sharon)
s2s t2s s2t t2t√√√
√
√
√
√
√
√
√√√
√
√
√
√
√
√√√
√
√
√
√
√
√√√
√
√
√
√
×
×
×
×
phrase pair
100%89% 89%78%
July 11, 2010ACL 2010 Tutorial, Uppsala,
Sweden 97
Rule Coverage
model human automatic
string-to-string 100% 100%
tree-to-string 78% 75%
string-to-tree 76% 72%
tree-to-tree 68% 60%Results from (Chiang, 2010)
July 11, 2010ACL 2010 Tutorial, Uppsala,
Sweden 98
Solutions Extend to larger rules
bushi yu shalongjuxing le huitan
NPB CC NPB VS AS NPB
NP VPB
IP
Bush held a talk with Sharon
VPB
VS AS X1:NPB
lejuxing
held a X1
(Galley et al., 2006)
July 11, 2010ACL 2010 Tutorial, Uppsala,
Sweden 99
Solutions Add pseudo nodes
bushi yu shalongjuxing le huitan
NPB CC NPB VS AS NPB
NP VPB
IP
Bush held a talk with Sharon
VPB
X1:*VPB_*NPB X2:NPB
X1 a X2
*VPB_*NPB
VS AS
lejuxing
held
(Marcu et al., 2006)
July 11, 2010ACL 2010 Tutorial, Uppsala,
Sweden 100
Solutions Use tree sequences
bushi yu shalongjuxing le huitan
NPB CC NPB VS AS NPB
NP VPB
IP
Bush held a talk with Sharon
VPB
X1:VS X2:NPB
X1 a X2
VS AS
lejuxing
held
X1:AS
(Liu et al., 2007; Zhang et al., 2008)
July 11, 2010ACL 2010 Tutorial, Uppsala,
Sweden 101
Tree-Sequence + Forest
system input ruleBLEU
Moses string string-to-string 25.7
tree-to-string
treetree-to-string 26.1
tree-sequence-to-string 27.0
foresttree-to-string 27.7
tree-sequence-to-string 28.8
Results from (Zhang et al., 2009)
July 11, 2010ACL 2010 Tutorial, Uppsala,
Sweden 102
Other Solutions
Re-structure syntax-trees (Wang et al., 2007)
Offer more trees (Mi and Huang, 2008) Re-align syntax trees and strings (May
and Knight, 2007) Well-formed dependency structures
(Shen et al., 2008) Gibbs sampling (Cohn and Blunsom,
2009) Joint decoding (Liu et al., 2009b)
July 11, 2010ACL 2010 Tutorial, Uppsala,
Sweden 103
Outline
Part 1: Tree-based Translation Overview and Motivation Tree-to-String Model and Decoding Tree-to-String Rule Extraction Language Model-Integrated Decoding: Cube Pruning
Part 2: Forest-based Translation Packed Forest Forest-based Decoding Forest-based Rule Extraction
Part 3: Extensions Tree-to-Tree Translation Tree Sequence-based Translation Joint Parsing and Translation
Part 4: Conclusion
July 11, 2010ACL 2010 Tutorial, Uppsala,
Sweden 104
Separate Parsing and Translation
parse translatesourcetarget
string tree/forest
string
Separate grammar for parsing and translation
decoding is fast!
July 11, 2010ACL 2010 Tutorial, Uppsala,
Sweden 105
Joint Parsing and Translation
parse + translatesourcetarget
string tree/forest
string
• Its search space is larger than tree/forest• It is a translator as well as a parser• Parsing interacts with translation
(Liu and Liu, 2010)
July 11, 2010ACL 2010 Tutorial, Uppsala,
Sweden 106
Tree-to-String Translation as Parsing
bushi yu shalong juxing le huitan
bushi
NPB
Bush
NPB
Bush(Liu and Liu, 2010)
July 11, 2010ACL 2010 Tutorial, Uppsala,
Sweden 107
Tree-to-String Translation as Parsing
bushi yu shalong juxing le huitan
yu
P
withNPB P
withBush(Liu and Liu, 2010)
July 11, 2010ACL 2010 Tutorial, Uppsala,
Sweden 108
Tree-to-String Translation as Parsing
bushi yu shalong juxing le huitan
shalong
NPB
Sharon
NPB P
withBush
NPB
Sharon(Liu and Liu, 2010)
July 11, 2010ACL 2010 Tutorial, Uppsala,
Sweden 109
Tree-to-String Translation as Parsing
bushi yu shalong juxing le huitan
huitan
NPB
talk
NPB P
withBush
NPB
Sharon
NPB
talk(Liu and Liu, 2010)
July 11, 2010ACL 2010 Tutorial, Uppsala,
Sweden 110
Tree-to-String Translation as Parsing
bushi yu shalong juxing le huitan
NPB P
Bush
NPB
with Sharon
NPB
talk
X1:P
PP
X1 X2
X2:NPBPP
(Liu and Liu, 2010)
July 11, 2010ACL 2010 Tutorial, Uppsala,
Sweden 111
Tree-to-String Translation as Parsing
bushi yu shalong juxing le huitan
NPB P
Bush
NPB
with Sharon
NPB
talk
X1:P
PP
X1 X2
X2:NPBPP
(Liu and Liu, 2010)
July 11, 2010ACL 2010 Tutorial, Uppsala,
Sweden 112
Tree-to-String Translation as Parsing
bushi yu shalong juxing le huitan
NPB P
Bush
NPB
with Sharon
NPB
talk
PP
VPB
VS AS X1:NPB
lejuxing
held a X1
VS AS
VPB
(Liu and Liu, 2010)
July 11, 2010ACL 2010 Tutorial, Uppsala,
Sweden 113
Tree-to-String Translation as Parsing
bushi yu shalong juxing le huitan
NPB P
Bush
NPB
with Sharon
NPB
PP
VPB
VS AS X1:NPB
lejuxing
held a X1
VS AS
VPB
held a talk(Liu and Liu, 2010)
July 11, 2010ACL 2010 Tutorial, Uppsala,
Sweden 114
Tree-to-String Translation as Parsing
bushi yu shalong juxing le huitan
NPB P
Bush
NPB NPB
PP
VS AS
VPB
with Sharon held a talk
X1:PP
VP
X2 X1
X2:VPBVP
(Liu and Liu, 2010)
July 11, 2010ACL 2010 Tutorial, Uppsala,
Sweden 115
Tree-to-String Translation as Parsing
bushi yu shalong juxing le huitan
NPB P
Bush
NPB NPB
PP
VS AS
VPB
X1:PP
VP
X2 X1
X2:VPBVP
held a talk with Sharon(Liu and Liu, 2010)
July 11, 2010ACL 2010 Tutorial, Uppsala,
Sweden 116
Tree-to-String Translation as Parsing
bushi yu shalong juxing le huitan
NPB P NPB NPB
PP
VS AS
VPB
X1:NPB
IP
X1 X2
X2:VPVP
Bush held a talk with Sharon
IP
(Liu and Liu, 2010)
July 11, 2010ACL 2010 Tutorial, Uppsala,
Sweden 117
Tree-to-String Translation as Parsing
bushi yu shalong juxing le huitan
NPB P NPB NPB
PP
VS AS
VPB
X1:NPB
IP
X1 X2
X2:VPVP
held a talk with Sharon
IP
Bush(Liu and Liu, 2010)
July 11, 2010ACL 2010 Tutorial, Uppsala,
Sweden 118
Translation Evaluationalgorithm input
parsing model rules BLEU time
matching
tree none 1.2M 29.8 0.56
forest PCFG 1.9M 31.6 9.49
parsing string
none
7.7M
32.0 51.41
PCFG 32.4 55.52
Lex 32.6 89.35
PCFG+Lex 32.7 91.72
(Liu and Liu, 2010)
July 11, 2010ACL 2010 Tutorial, Uppsala,
Sweden 119
Parsing Evaluation
parsing model F1 time
none 62.7 23.9
PCFG 65.4 24.7
Lex 79.8 48.8
PCFG + Lex 80.6 50.4
(Liu and Liu, 2010)
July 11, 2010ACL 2010 Tutorial, Uppsala,
Sweden 120
Results on Tree-to-Tree
task extraction rules features BLEU
Chinese
string-to-string 440M 1K 23.7
tree-to-tree 50M 5K 23.9
Arabic
string-to-string 790M 1K 48.9
tree-to-tree 38M 5K 47.5Results from (Chiang, 2010)
July 11, 2010ACL 2010 Tutorial, Uppsala,
Sweden 121
Outline
Part 1: Tree-based Translation Overview and Motivation Tree-to-String Model and Decoding Tree-to-String Rule Extraction Language Model-Integrated Decoding: Cube Pruning
Part 2: Forest-based Translation Packed Forest Forest-based Decoding Forest-based Rule Extraction
Part 3: Extensions Tree-to-Tree Translation Tree Sequence-based Translation Joint Parsing and Translation
Part 4: Conclusion
July 11, 2010ACL 2010 Tutorial, Uppsala,
Sweden 122
Conclusion Statistical machine translation
Word-based Phrase-based Syntax-based
String-to-String String-to-Tree Tree-to-String Tree-to-Tree
flat
hierarchical
July 11, 2010ACL 2010 Tutorial, Uppsala,
Sweden 123
Conclusion
Tree-based translation Pros: simplicity, faster decoding, expressive
grammar, no need for binarization Cons: commits to 1-best tree
Forest-based translation Compromise between tree-based and
string-based, combining the advantages of both Fast decoding, but does not commit to 1-best
trees Significant improvement of translation
performance over tree-based
July 11, 2010ACL 2010 Tutorial, Uppsala,
Sweden 124
Thank you
谢谢 大家
VV PN
VP
July 11, 2010ACL 2010 Tutorial, Uppsala,
Sweden 125
Bibliography Alfred V. Aho and Jeffrey D. Ullman. 1972. The Theory of Parsing,
Translation, and Compiling, volume I: parsing. Prentice Hall, Englewood Cliffs, New Jersey.
Peter F. Brown, Stephan A. Della Pietra, Vincent J. Della Pietra, and Robert L. Mercer. 1993. The mathematics of statistical machine translation: Parameter estimation. Computational Linguistics, 19(2): 263-311.
Sylvie Billot and Bernard Lang. 1989. The structure of shared forests in ambiguous parsing. In Proceedings of ACL 1989.
David Chiang, 2005. A hierarchical phrase-based model for statistical machine translation. In Proceedings of ACL 2005.
David Chiang, 2007. Hierarchical phrase-based translation. Computational Linguistics, 33(2): 201-228.
David Chiang, 2010. Learning to translate with source and target syntax. In Proceedings of ACL 2010.
Trevor Cohn and Phil Blunsom. 2009. A bayesian model for syntax-directed tree to string grammar induction. In Proceedings of EMNLP 2009.
Michel Galley, Mark Hopkins, Kevin Knight, and Daniel Marcu. 2004. What’s in a translation rule? In Proceedings of HLT-NAACL 2004.
Michel Galley, Jonathan Graehl, Kevin Knight, Daniel Marcu, Steve DeNeefe, Wei Wang, and Ignacio Thayer. 2006. Scalable inference and training of context-rich syntactic translation models. In Proceedings of COLING-ACL 2006.
July 11, 2010ACL 2010 Tutorial, Uppsala,
Sweden 126
Bibliography Liang Huang and David Chiang. 2005. Better k-best parsing. In
Proceedings of IWPT 2005. Liang Huang and David Chiang. 2007. Forest rescoring: Faster
decoding with integrated language models. In Proceedings of ACL 2007.
Liang Huang, Kevin Knight, and Aravind Joshi. 2006. Statistical syntax-directed translation with extended domain of locality. In Proceedings of AMTA 2006.
Liang Huang. 2008. Forest reranking: Discriminative parsing with non-local features. In Proceedings. of ACL-HLT 2008.
E. T. Irons. 1961. A syntax-directed compiler for ALGOL 60. Comm. ACM, 4(1): 51-55.
Kevin Knight and Jonathan Graehl. 2005. An overview of probabilistic tree transducers for natural language processing. In Proceedings of CICLing 2005.
Dan Klein and Christopher D. Manning. 2001. Parsing and hypergraphs. In Proceedings of IWPT 2001.
Philipp Koehn, Franz Och, and Daniel Marcu. 2003. Statistical phrase-based translation In Proceedings of HLT-NAACL 2003.
P. M. Lewis and R. E. Stearns. 1968. Syntax-directed transduction. Journal of the ACM, 15(3): 465-488.
Yang Liu, Qun Liu, and Shouxun Lin. 2006. Tree-to-string alignment template for statistical machine translation. In Proceedings of COLING-ACL 2006.
July 11, 2010ACL 2010 Tutorial, Uppsala,
Sweden 127
Bibliography Yang Liu, Yun Huang, Qun Liu, and Shouxun Lin. 2007. Forest-to-
string statistical translation rules. In Proceedings of ACL 2007. Yang Liu, Yajuan Lu, and Qun Liu. 2009a. Improving tree-to-tree
translation with packed forests. In Proceedings of ACL-IJCNLP 2009. Yang Liu, Haitao Mi, Yang Feng, and Qun Liu. 2009b. Joint decoding
with multiple translation models. In Proceeding of ACL-IJCNLP 2009. Yang Liu and Qun Liu. 2010. Joint parsing and translation. Submitted
to COLING 2010. Daniel Marcu, Wei Wang, Abdessamad Echihabi, and Kevin Knight.
2006. SPMT: Statistical machine translation with syntactified target language phrases. In Proceedings of EMNLP 2006.
Jonathan May and Kevin Knight. 2007. Syntax re-alignment models for machine translation. In Proceedings of EMNLP 2007.
Haitao Mi and Liang Huang. 2008. Forest-based translation rule extraction. In Proceedings of EMNLP 2008.
Haitao Mi, Liang Huang, and Qun Liu. 2008. Forest-based translation. In Proceedings of ACL-HLT 2008.
Franz Och and Hermann Ney. 2004. The alignment template approach to statistical machine translation. Computational Linguistics, 30(4): 417-449.
July 11, 2010ACL 2010 Tutorial, Uppsala,
Sweden 128
Bibliography Libin Shen, Jinxi Xu, and Ralph Weischedel. 2008. A new string-to-
dependency machine translation algorithm with a target dependency language model. In Proceedings of ACL-HLT 2008.
Ashish Venugopal, Andreas Zollmann, Noah Smith, and Stephan Vogel. 2008. Wider pipelines: n-best alignments and parses in mt training. In Proceedings of AMTA 2008.
Wei Wang, Kevin Knight, and Daniel Marcu. 2007. Binarizing syntax trees to improve syntax-based machine translation accuracy. In Proceedings of EMNLP 2007.
Kenji Yamada and Kevin Knight. 2001. A syntax-based statistical machine translation model. In Proceedings of ACL 2001.
Hui Zhang, Min Zhang, Haizhou Li, Aiti Aw, and Chew Lin Tan. 2009. Forest-based tree sequence to string translation model. In Proceedings of ACL-IJCNLP 2009.
Min Zhang, Hongfei Jiang, Aiti Aw, Jun Sun, Sheng Li, and Chew Lin Tan. 2007. A tree-to-tree alignment-based model for statistical machine translation. In Proceedings of MT Summit 2007.
Min Zhang, Hongfei Jiang, Aiti Aw, Haizhou Li, Chew Lin Tan, and Sheng Li. 2008. A tree sequence alignment-based tree-to-tree translation model. In Proceedings of ACL-HLT 2008.