nonparametric bayesian machine transliteration with synchronous adaptor grammars
Báo cáo khoa học: "Bayesian Learning of Non-compositional Phrases with Synchronous Parsing" pot
Ngày tải lên :
17/03/2014, 02:20
... enumerate spans by position. Note that δ[m, R] ·
n
a=m+1
O(a) is within threshold iff there is a
span with right boundary m
′
< m within thresh-
old. Furthermore if δ[m, M] ·
n
a=m+1
O(a) is
... pruning. All produce the same set of bitext
cells, those within threshold of the best bitext cell.
within threshold, then m is the right boundary within
threshold. Using these facts, we can gradually
sweep ... left boundaries within threshold.
Likewise for the left edge, δ[l, M] ·
m
a=l+1
I(a) ·
n
a=m+1
O(a) is within threshold iff there is some
l
′
< l identifying a span (l
′
, m) within threshold.
Finally...
- 9
- 327
- 0
electric machine Chapter 5 Synchronous Machines
Ngày tải lên :
14/02/2014, 16:36
... 5.4 Synchronous -machine equivalent circuit showing air-gap and
leakage components of synchronous reactance and air-gap voltage.
4
Chapter 5 Synchronous Machines
Main features of synchronous ... synchronous machines:
A synchronous machine is an ac machine whose speed under steady-state conditions is
proportional to the frequency of the current in its armature.
The rotor, along with the ... Consider Fig. 5.12 in which a synchronous machine with generated voltage
and synchronous
is connected to a system whose Thevenin equivalent is a
voltage source
in series with a reactive impedance...
- 22
- 406
- 0
Tài liệu Báo cáo khoa học: "Bayesian Symbol-Refined Tree Substitution Grammars for Syntactic Parsing" pptx
Ngày tải lên :
19/02/2014, 19:20
... refinement. An adaptor grammar (Johnson
et al., 2007a) is a sort of nonparametric Bayesian
TSG model with symbol refinement, and is thus
closely related to our SR-TSG model. However,
an adaptor grammar ... DeNeefe and Kevin Knight. 2009. Synchronous
Tree Adjoining Machine Translation. In Proc. of
EMNLP, page 727.
Thomas S Ferguson. 1973. A Bayesian Analysis of
Some Nonparametric Problems. Annals ... Discriminative
Parsing with Non-Local Features. In Proc. of ACL,
19104:0.
Mark Johnson and Sharon Goldwater. 2009. Improving
nonparameteric Bayesian inference: experiments on
unsupervised word segmentation with adaptor...
- 9
- 411
- 0
Tài liệu Báo cáo khoa học: "Translation Model Adaptation for Statistical Machine Translation with Monolingual Topic Information" doc
Ngày tải lên :
19/02/2014, 19:20
... statistical machine
translation. Machine Translation, pages 187-207.
Nicola Ueffing, Gholamreza Haffari and Anoop Sarkar.
2008. Semi-supervised Model Adaptation for Statisti-
cal Machine Translation. Machine ... scores under the condition within the range
[25K, 80K] are all higher than the ones within the
range [5K, 20K]. When N is set to 55K, the BLEU
score of our system is 21.40, with 1.18 gains on the
baseline ... Statistical Machine Translation
with Domain Dictionary and Monolingual Corpora. In
Proc. of COLING 2008, pages 993-1000.
Richard Zens and Hermann Ney. 2004. Improvments in
phrase-based statistical machine...
- 10
- 533
- 0
Tài liệu Báo cáo khoa học: "Improving Statistical Machine Translation with Monolingual Collocation" pdf
Ngày tải lên :
20/02/2014, 04:20
... monolingual sentence,
i
denotes the number of words that are aligned
with
i
w
. Since a word never collocates with itself,
the alignment set is denoted as
}&],1[|),{( ialiaiA
ii
. ... 11-16 July 2010.
c
2010 Association for Computational Linguistics
Improving Statistical Machine Translation with
Monolingual Collocation
Zhanyi Liu
1
, Haifeng Wang
2
, Hua Wu
2
, Sheng Li
1
...
Table 5. Performances of Moses employing
our proposed methods (Significantly better than
baseline with p < 0.01)
using the same methods as those shown in Table
3. Here, we investigate three...
- 9
- 474
- 0
Tài liệu Báo cáo khoa học: "Corpus Expansion for Statistical Machine Translation with Semantic Role Label Substitution Rules" doc
Ngày tải lên :
20/02/2014, 04:20
... inter-
polating the phrase table with the baseline phrase ta-
ble, we observed improvement on Chinese-English
machine translation tasks and the performance is
comparable to system trained with larger manually
collected ... Baseline system, GS: System trained with only gen-
erated sentence pairs, IT: Interpolated phrase table with
GS and BL,. GA and IA are GS and IT systems trained
with baseline word alignment models ... observed in
the original corpus without substitution. In this pa-
per, we call a tuple of semantic frame and semantic
role a semantic signature. Two phrase pairs with the
same semantic signature...
- 5
- 416
- 0
Tài liệu Báo cáo khoa học: "Using adaptor grammars to identify synergies in the unsupervised acquisition of linguistic structure" docx
Ngày tải lên :
20/02/2014, 09:20
... the sam-
pled tree under the adaptor grammar and the PCFG
approximation.
3 Word segmentation with adaptor
grammars
We now turn to linguistic applications of adap-
tor grammars, specifically, to models ... syntax.
2 From PCFGs to Adaptor Grammars
This section introduces adaptor grammars as an ex-
tension of PCFGs; for a more detailed exposition see
Johnson et al. (2007b). Formally, an adaptor gram-
mar ... inde-
pendent given its label). Adaptor grammars relax
399
potheses about the interaction of morphology and
syllable structure with word segmentation. Techni-
cally, adaptor grammars are a way of specifying...
- 9
- 643
- 0
Tài liệu Báo cáo khoa học: "Machine Transliteration" ppt
Ngày tải lên :
22/02/2014, 03:20
... contextual disambiguation, either by
machine or as part of an interactive man -machine
system. We also plan to explore probabilistic models
for Arabic/English transliteration. Simply identify- ... vowel sounds (oo) are usu-
ally written with a long vowel mark (~-) but are
sometimes written with repeated katakana (~).
We combined corpus analysis with guidelines from
a Japanese textbook ...
We can now use the models to do a sample back-
transliteration. We start with a katakana phrase
as observed by OCR. We then serially compose it
with the models, in reverse order. Each intermedi-...
- 8
- 340
- 0
Báo cáo khoa học: "A Nonparametric Bayesian Approach to Acoustic Model Discovery" docx
Ngày tải lên :
07/03/2014, 18:20
... and
Glass (2009) trained a GMM with 50 components
to decode posteriorgrams for the feature frames, and
Zhang et al. (2012) used a deep Boltzmann machine
(DBM) trained with pseudo phone labels generated
from ... models to guide
its hypotheses on phone boundaries.
Bayesian Model for Segmentation Our model is
inspired by previous applications of nonparametric
Bayesian models to segmentation problems in NLP
and ... precision
of top hits by at least 22.1% with only some degra-
dation in equal error rate (EER), and outperforms
a language-mismatched acoustic model trained with
supervised data.
2 Related Work
Unsupervised...
- 10
- 477
- 0
Báo cáo khoa học: "Native Language Detection with Tree Substitution Grammars" pptx
Ngày tải lên :
07/03/2014, 18:20
... Compact but Accurate Tree-
Substitution Grammars. In Proceedings NAACL.
Trevor Cohn, and Phil Blunsom 2010. Blocked inference
in Bayesian tree substitution grammars. Association
for Computational ... proba-
bilistic context-free grammars. Association for Com-
putational Linguistics.
Sangati, Federico and Zuidema, Willem 2011. Accurate
Parsing with Compact Tree-Substitution Grammars:
Double-DOP. ... (note
that a CFG can be taken as a TSG with all frag-
ments having depth one). Second, in the method
we call BTSG, we use the Bayesian induction model
with the Dirichlet process’ concentration...
- 5
- 339
- 0
Báo cáo khoa học: "Enhancing Language Models in Statistical Machine Translation with Backward N-grams and Mutual Information Triggers" ppt
Ngày tải lên :
07/03/2014, 22:20
... statistical
machine translation: Parameter estimation. Computa-
tional Linguistics, 19(2):263–311.
Eugene Charniak, Kevin Knight, and Kenji Yamada.
2003. Syntax-based language models for statistical
machine ... tests for
machine translation evaluation. In Proceedings of
EMNLP 2004, pages 388–395, Barcelona, Spain, July.
Arne Mauser, Sa
ˇ
sa Hasan, and Hermann Ney. 2009. Ex-
tending statistical machine ... statistical machine translation. In Proceed-
ings of AMTA.
Sylvain Raybaud, Caroline Lavecchia, David Langlois,
and Kamel Sma
¨
ıli. 2009. New confidence measures
for statistical machine translation....
- 10
- 415
- 0
Báo cáo khoa học: "Unsupervised Coreference Resolution in a Nonparametric Bayesian Model" potx
Ngày tải lên :
08/03/2014, 02:21
... is then asso-
ciated with a multinomial emission distribution over
head words with parameters φ
h
Z
, which are drawn
from a symmetric Dirichlet over possible mention
heads with concentration λ
H
.
2
Note ... entities across a corpus by as-
suming that the pool of entities is global, with global
mixing weights β
0
drawn from a DP prior with
concentration parameter γ. Each document uses
852
port 67.1 F
1
and ... is
not labeled coreferent with the The Weir Group men-
tion. Examples such as these illustrate the regular (at
least in newswire) phenomenon that nominal men-
tions are used with informative intent,...
- 8
- 399
- 0
Báo cáo khoa học: "Jointly optimizing a two-step conditional random field model for machine transliteration and its fast decoding algorithm" pdf
Ngày tải lên :
17/03/2014, 00:20
... Proceedings of International Confer-
ence on Machine Learning, pages 282-289.
Haizhou Li, Min Zhang and Jian Su. 2004. A joint
source-channel model for machine transliteration,
Proceedings of the 42nd ... (DOM), which
performs the transliteration between two lan-
guages directly without using any intermediate
phonemic mapping, is recently gaining more at-
tention in the transliteration research ... information into the model for
275
Indian languages. In the “NEWS 2009 Machine
Transliteration Shared Task”, a new two-step CRF
model for transliteration task has been proposed
(Yang et al., 2009), in...
- 6
- 419
- 0
Báo cáo khoa học: "Issues Concerning Decoding with Synchronous Context-free Grammar" docx
Ngày tải lên :
17/03/2014, 00:20
... NP, with NP
NP → PP, romance PP
With the change, only the following rule is extracted:
NP
NPB
NNP
romance
PP
IN
with
NP
NPB
DT
the
JJ
snowy
NN
egret
白鹭 鸶 的 爱
Figure 1: A sentence fragment pair with ... Conclusion
In this paper, we discussed several issues concerning
decoding with synchronous context-free grammars,
focusing on grammars resulting from the GHKM
extraction method. We discussed different ... a pruning bin
with guesses of English words to insert without
any source-side lexical evidence.
The most obvious way of eliminating problem-
atic unary rules would be converting grammars into
Chomsky...
- 5
- 214
- 0
Báo cáo khoa học: "Machine Translation with a Stochastic Grammatical Channel" doc
Ngày tải lên :
17/03/2014, 07:20
... been analyzed mathematically, linguisti-
2With the exception of higher-order phenomena such as
neg-raising and wh-movement.
1409
Machine Translation with a Stochastic Grammatical Channel
Dekai ... grammatical channel
model for machine translation, that synthesizes sev-
eral desirable characteristics of both statistical and
grammatical machine translation. As with the
pure statistical translation ...
right of the dot are called subtree.
As with Wu's SBTG model, the algorithm max-
imizes a probabilistic objective function, Equa-
Machine Translation with a Stochastic Grammatical Channel...
- 8
- 350
- 0
