... the system generated by the boosting-
based system combination. The points at itera-
tion 1 stand for the performance of the baseline
systems. We see, first of all, that all the three
systems ... that the
boosting-based system combination seems to be
more helpful to the phrase-based system than to
the Hiero system and the syntax-based system.
For the phrase-based syste...
... learning model.
5.2 Systems and Evaluation Method
We used two commercial RBMT systems in our
experiments: System A for Chinese-English bidi-
rectional translation and System B for English-
Chinese ... Thus, for each system, we can get three
different translations for each input. These differ-
ent translations can serve as pseudo references for
the outputs of other systems. In o...
... Parsing for Machine Translation
Michel Galley
Computer Science Department
Stanford University
Stanford, CA 94305-9020
mgalley@cs.stanford.edu
Christopher D. Manning
Computer Science Department
Stanford ... Introduction
Hierarchical approaches to machine translation
have proven increasingly successful in recent
years (Chiang, 2005; Marcu et al., 2006; Shen
et al., 2008), and often outper...
... existing tools. For stemming we
use the TreeTagger (Schmid, 1994) for German
and the Snowball stemmer
1
for Finnish. A vari-
ety of ways for compound splitting have been in-
vestigated in machine translation ... applied before training and after gener-
ating the output in the target language. Normaliza-
tion of English/German inflectional morphology
to base forms for the purpose of...
... phrasal system
For the phrasal system, we performed integration
only with Method 1, using the top 1 or 100-
best translations. This is the most straightforward
method for combining with any system, ... %).
4 Machine translation systems and data
We integrated the inflection prediction model with
two types of machine translation systems: systems
that make use of syntax and surface ph...
... 2007.
c
2007 Association for Computational Linguistics
Tailoring Word Alignments to Syntactic Machine Translation
John DeNero
Computer Science Division
University of California, Berkeley
denero@berkeley.edu
Dan ... Klein
Computer Science Division
University of California, Berkeley
klein@cs.berkeley.edu
Abstract
Extracting tree transducer rules for syntac-
tic MT systems can be hindered...
... disambigua-
tion (WSD) systems can help to improve the
performance of statistical machine transla-
tion (MT) systems. In this paper, we suc-
cessfully integrate a state-of-the-art WSD
system into a state-of-the-art ... hierarchical
phrase-based MT system, Hiero. We show
for the first time that integrating a WSD sys-
tem improves the performance of a state-of-
the-art statistical MT sys...
... more information than the corre-
sponding bag of lexical items before parsing. Its
elements get enriched with additional informa-
tion instantiated during the parsing process. In-
formation ... lexicon was
used for content words. Only a bilingual lexi-
con for closed class words and a set of bilingual
templates were used. Therefore, new bilingual
entries were obtained for all th...
... t
b
rooted in ε
b
do
for all alignments α of the children of t
a
and t
b
do
β(ε
a
,ε
b
) +=
P
elem
(t
a
|ε
a
)P
align
(α|ε
i
)
(i,j)∈α
β(ε
i
,ε
j
)
end for
end for
end for
end for
end for
The outer ... k
1
,l
1
k
m
,l
m
do
β(ε
i
,k,l)+= P
order
(ρ|ε
i
)
m
j=1
β(ε
j
,k
j
,l
j
)
end for
end for
end for
end for
This algorithm has computational complexity
O(|T |N
m+2
), w...
... 312–319,
Prague, Czech Republic, June 2007.
c
2007 Association for Computational Linguistics
Improved Word-Level System Combination for Machine Translation
Antti-Veikko I. Rosti and Spyros Matsoukas ... network for the source sentence , is the
number of translation systems, is the th system
weight, is the accumulated confidence for word
produced by system between nodes and...