1 a tree sequence alignment- based tree-to-tree translation model authors: min zhang, hongfei jiang,...
Post on 20-Dec-2015
221 views
TRANSCRIPT
![Page 1: 1 A Tree Sequence Alignment- based Tree-to-Tree Translation Model Authors: Min Zhang, Hongfei Jiang, Aiti Aw, et al. Reporter: 江欣倩 Professor: 陳嘉平](https://reader035.vdocuments.site/reader035/viewer/2022081514/56649d425503460f94a1dbac/html5/thumbnails/1.jpg)
1
A Tree Sequence Alignment-based Tree-to-Tree Translation ModelAuthors: Min Zhang, Hongfei Jiang, Aiti Aw, et
al.
Reporter: 江欣倩Professor: 陳嘉平
![Page 2: 1 A Tree Sequence Alignment- based Tree-to-Tree Translation Model Authors: Min Zhang, Hongfei Jiang, Aiti Aw, et al. Reporter: 江欣倩 Professor: 陳嘉平](https://reader035.vdocuments.site/reader035/viewer/2022081514/56649d425503460f94a1dbac/html5/thumbnails/2.jpg)
2
![Page 3: 1 A Tree Sequence Alignment- based Tree-to-Tree Translation Model Authors: Min Zhang, Hongfei Jiang, Aiti Aw, et al. Reporter: 江欣倩 Professor: 陳嘉平](https://reader035.vdocuments.site/reader035/viewer/2022081514/56649d425503460f94a1dbac/html5/thumbnails/3.jpg)
3
Introduction
Phrase-based modeling method cannot handle long-distance reorderings properly and does not exploit discontinuous phrases and linguistically syntactic structure features.
A model combine the strengths of phrase-based and syntax-based methods. The model adopts tree sequence as the basic tran
slation unit
![Page 4: 1 A Tree Sequence Alignment- based Tree-to-Tree Translation Model Authors: Min Zhang, Hongfei Jiang, Aiti Aw, et al. Reporter: 江欣倩 Professor: 陳嘉平](https://reader035.vdocuments.site/reader035/viewer/2022081514/56649d425503460f94a1dbac/html5/thumbnails/4.jpg)
4
Tree Sequence Translation Rule The pairs of source parse trees and target
parse trees with word alignments A tree sequence translation rule
is a source tree sequence, covering
the span [j1, j2] in
JfT 1
IeT 1
AeTSfTSr ii
jj
~,, 2
1
2
1
21
jjfT
JfT 1
![Page 5: 1 A Tree Sequence Alignment- based Tree-to-Tree Translation Model Authors: Min Zhang, Hongfei Jiang, Aiti Aw, et al. Reporter: 江欣倩 Professor: 陳嘉平](https://reader035.vdocuments.site/reader035/viewer/2022081514/56649d425503460f94a1dbac/html5/thumbnails/5.jpg)
5
Tree Sequence Translation Rule
![Page 6: 1 A Tree Sequence Alignment- based Tree-to-Tree Translation Model Authors: Min Zhang, Hongfei Jiang, Aiti Aw, et al. Reporter: 江欣倩 Professor: 陳嘉平](https://reader035.vdocuments.site/reader035/viewer/2022081514/56649d425503460f94a1dbac/html5/thumbnails/6.jpg)
6
Tree Sequence Translation Model Given the source and target sentences: and
and their parse trees: and The tree sequence-to-tree sequence translation
model
Jf1Ie1
JfT 1 IeT 1
)),(),(|Pr
),(|)(Pr
|)((Pr
|)(),(,Pr|Pr
1111
111
)(),(11
)(),(111111
11
11
JJII
JJI
eTfT
JJ
eTfT
JIJIJI
ffTeTe
ffTeT
ffT
feTfTefe
IJ
IJ
1
1
)(|)(Pr 11JI fTeT
![Page 7: 1 A Tree Sequence Alignment- based Tree-to-Tree Translation Model Authors: Min Zhang, Hongfei Jiang, Aiti Aw, et al. Reporter: 江欣倩 Professor: 陳嘉平](https://reader035.vdocuments.site/reader035/viewer/2022081514/56649d425503460f94a1dbac/html5/thumbnails/7.jpg)
7
Tree Sequence Translation Model The probability of each derivation θ is given as the p
roduct of the probabilities of all the rules p(ri) used in the derivation
ir
jj
iii
JIJI
AfTSeTSrp
fTeTfe
)~
),(),(:(
)(|)(Pr
2
1
2
1
1111 )|Pr(
![Page 8: 1 A Tree Sequence Alignment- based Tree-to-Tree Translation Model Authors: Min Zhang, Hongfei Jiang, Aiti Aw, et al. Reporter: 江欣倩 Professor: 陳嘉平](https://reader035.vdocuments.site/reader035/viewer/2022081514/56649d425503460f94a1dbac/html5/thumbnails/8.jpg)
8
Rule Extraction
Rules are extracted from word-aligned, bi-parsed sentence pairs initial rule
If all leaf nodes of the rule are terminals abstract rule
Otherwise
sub initial rule An initial rule
AeTSfTS ii
jj
~,, 2
1
2
1
AeTSfTS ii
jj
,, 4
3
4
3
AA~ˆ
![Page 9: 1 A Tree Sequence Alignment- based Tree-to-Tree Translation Model Authors: Min Zhang, Hongfei Jiang, Aiti Aw, et al. Reporter: 江欣倩 Professor: 陳嘉平](https://reader035.vdocuments.site/reader035/viewer/2022081514/56649d425503460f94a1dbac/html5/thumbnails/9.jpg)
9
Rule Extraction
1. Extracting initial rules
2. Extracting abstract rules
![Page 10: 1 A Tree Sequence Alignment- based Tree-to-Tree Translation Model Authors: Min Zhang, Hongfei Jiang, Aiti Aw, et al. Reporter: 江欣倩 Professor: 陳嘉平](https://reader035.vdocuments.site/reader035/viewer/2022081514/56649d425503460f94a1dbac/html5/thumbnails/10.jpg)
10
Three constraints for rules
The depth of a tree in a rule is not greater than h
The number of non-terminals as leaf nodes is not greater than c
The tree number in a rule is not greater than d
Initial rules have at most seven lexical words as leaf nodes
![Page 11: 1 A Tree Sequence Alignment- based Tree-to-Tree Translation Model Authors: Min Zhang, Hongfei Jiang, Aiti Aw, et al. Reporter: 江欣倩 Professor: 陳嘉平](https://reader035.vdocuments.site/reader035/viewer/2022081514/56649d425503460f94a1dbac/html5/thumbnails/11.jpg)
11
Decoding
Given , the decoder is to find the best derivation θ that generates
Thresholds α: the maximal number of rules used β: the minimal log probability of rules γ: the maximal number of translations yield
JfT 1
IJ eTfT 11 ,
i
I
I
ri
e
JI
e
rp
fTeTe
)(maxarg
)(|)(Prmaxargˆ
,
11
1
1
![Page 12: 1 A Tree Sequence Alignment- based Tree-to-Tree Translation Model Authors: Min Zhang, Hongfei Jiang, Aiti Aw, et al. Reporter: 江欣倩 Professor: 陳嘉平](https://reader035.vdocuments.site/reader035/viewer/2022081514/56649d425503460f94a1dbac/html5/thumbnails/12.jpg)
12
Decoding Algorithm
![Page 13: 1 A Tree Sequence Alignment- based Tree-to-Tree Translation Model Authors: Min Zhang, Hongfei Jiang, Aiti Aw, et al. Reporter: 江欣倩 Professor: 陳嘉平](https://reader035.vdocuments.site/reader035/viewer/2022081514/56649d425503460f94a1dbac/html5/thumbnails/13.jpg)
13
Experimental Settings
Chinese-to-English translation Translation model
FBIS corpus (7.2M+9.2M words) 4-gram LM
Xinhua portion of the English Gigaword corpus (181M words) Development set
NIST MT-2002 test set Test set
NIST MT-2005 test set Baseline systems
Moses SCFG-based tree-to-tree translation models STSG-based tree-to-tree translation models
Threshold d=4, h=6 α=20, β=-100, γ=100
![Page 14: 1 A Tree Sequence Alignment- based Tree-to-Tree Translation Model Authors: Min Zhang, Hongfei Jiang, Aiti Aw, et al. Reporter: 江欣倩 Professor: 陳嘉平](https://reader035.vdocuments.site/reader035/viewer/2022081514/56649d425503460f94a1dbac/html5/thumbnails/14.jpg)
14
Experimental Results
Compare the model with the three baseline systems
The model’s expressive ability by comparing the contributions made by different kinds of rules
The impact of maximal sub-tree number and sub-tree depth in the model
![Page 15: 1 A Tree Sequence Alignment- based Tree-to-Tree Translation Model Authors: Min Zhang, Hongfei Jiang, Aiti Aw, et al. Reporter: 江欣倩 Professor: 陳嘉平](https://reader035.vdocuments.site/reader035/viewer/2022081514/56649d425503460f94a1dbac/html5/thumbnails/15.jpg)
15
Experimental 1
BP: bilingual phrase (used in Moses) TR: tree rule (only 1 tree) TSR: tree sequence rule (> 1 tree), L: fully lexicalized, P: partially lexicalized, U: unlexicalized
![Page 16: 1 A Tree Sequence Alignment- based Tree-to-Tree Translation Model Authors: Min Zhang, Hongfei Jiang, Aiti Aw, et al. Reporter: 江欣倩 Professor: 陳嘉平](https://reader035.vdocuments.site/reader035/viewer/2022081514/56649d425503460f94a1dbac/html5/thumbnails/16.jpg)
16
Experiment 1
SCFG: d=1, h=2STSG: d=1, h=6The model: d=4, h=6
![Page 17: 1 A Tree Sequence Alignment- based Tree-to-Tree Translation Model Authors: Min Zhang, Hongfei Jiang, Aiti Aw, et al. Reporter: 江欣倩 Professor: 陳嘉平](https://reader035.vdocuments.site/reader035/viewer/2022081514/56649d425503460f94a1dbac/html5/thumbnails/17.jpg)
17
Experiment 2
Structure Reordering Rules (SRR): refers to the structure reordering rules that have at least two non-terminal leaf nodes with inverted order in the source and target sides, which are usually not captured by phrase-based models.Discontinuous Phrase Rules (DPR): refers to these rules having at least one non-terminal leaf node between two lexicalized leaf nodes
![Page 18: 1 A Tree Sequence Alignment- based Tree-to-Tree Translation Model Authors: Min Zhang, Hongfei Jiang, Aiti Aw, et al. Reporter: 江欣倩 Professor: 陳嘉平](https://reader035.vdocuments.site/reader035/viewer/2022081514/56649d425503460f94a1dbac/html5/thumbnails/18.jpg)
18
Experiment 3
![Page 19: 1 A Tree Sequence Alignment- based Tree-to-Tree Translation Model Authors: Min Zhang, Hongfei Jiang, Aiti Aw, et al. Reporter: 江欣倩 Professor: 陳嘉平](https://reader035.vdocuments.site/reader035/viewer/2022081514/56649d425503460f94a1dbac/html5/thumbnails/19.jpg)
19
Experiment 3
![Page 20: 1 A Tree Sequence Alignment- based Tree-to-Tree Translation Model Authors: Min Zhang, Hongfei Jiang, Aiti Aw, et al. Reporter: 江欣倩 Professor: 陳嘉平](https://reader035.vdocuments.site/reader035/viewer/2022081514/56649d425503460f94a1dbac/html5/thumbnails/20.jpg)
20
Conclusions and Future Work A tree sequence alignment-based translation
model combine the strengths of phrase-based and syntax-based methods
Rule optimization and pruning algorithms in future