... model to predict them.
520
Proceedings of ACL-08: HLT, pages 514–522,
Columbus, Ohio, USA, June 2008.
c
2008 Association for Computational Linguistics
Applying MorphologyGenerationModelstoMachine ... In the second setting, we
allow the model to use up to 100 translations, and
to automatically select the best number to use. As
seen in Table 3, (n=16) translations were chosen for
Russian and ... statistical machine translation. In
HLT-NAACL.
Xiaodong He. 2007. Using word-dependent transition
models in HMM based word alignment for statistical
machine translation. In ACL Workshop on Statistical
Machine...
... backoff model produced a
good translation, but the translation was a para-
phrase rather than an identical match to the ref-
erence translation. Since only a single reference
translation is available ... backoff models for combining in-domain and
42
Phrase-Based Backoff Models for MachineTranslation of Highly Inflected
Languages
Mei Yang
Department of Electrical Engineering
University of Washin g ton
Seattle, ... editors,
Proceedings of the Conference of the Association for
Machine Translation in the Americas, pages 115–
124, Washington, DC.
P. Koehn. 2005. Europarl: A parallel corpus for sta-
tistical machine...
... adapt
a machinetranslation metric to measure con-
tent coverage, apply an enhanced discourse
coherence model to evaluate summary read-
ability, and combine both in a trained regres-
sion model to ... between two machinetranslation systems
with regard to the BLEU score. We adapt this
method to compute the difference between two eval-
uation metrics in summarization:
1. Randomly choose n topics ... large-scale sup-
port vector machine learning practical. In Bernhard
Schlkopf, Christopher J. C. Burges, and Alexander J.
Smola, editors, Advances in Kernel Methods – Support
Vector Learning. MIT Press,...
... English -to- Turkish
translation, but without using any morphology.
6 Conclusions
We have presented a novel way to incorporate
source syntactic structure in English -to- Turkish
phrase-based machinetranslation ... of
the factors. We aligned our training sets using only
the root factor to conflate statistics from different
forms of the same root. The rest of the factors are
then automatically assumed to be aligned, ... Furthermore, in factored
models, we can employ different language models
for different factors. For the initial set of experi-
ments we used 3-gram LMs for all the factors.
For factored decoding,...
... English-Hindi Statistical Machine Translation.
In Proc. IJCNLP.
Roy Tromble. 2009. Search and Learning for the Lin-
ear Ordering Problem with an Application to Machine
Translation. Ph.D. Thesis.
Karthik ... since the
emerging of statistical machine translation. In
phrase-based models (Och, 2002; Koehn et al.,
2003), phrase is introduced to serve as the funda-
mental translation element and deal with ... converted to dependency trees us-
ing Stanford Parser (Marneffe et al., 2006). We con-
vert the tokens in training data to lower case, and
re-tokenize the sentences using the same tokenizer
from...
... their translations by the IN, OUT and En-
semble models are shown in Figure 2. The boxes
show how the Ensemble model is able to use n-
grams from the IN and OUT modelsto construct
a better translation ... april.
Nicola Bertoldi and Marcello Federico. 2009. Do-
main adaptation for statistical machinetranslation with
monolingual resources. In Proceedings of the Fourth
Workshop on Statistical Machine Translation, ... 2005), LOPs work best when all the
models accuracies are high and close to each other
with some degree of diversity. LOPs give veto power
to any of the component models and this perfectly
works...
... Case Study of Hindi to
Punjabi MachineTranslation System. International
Journal of Translation. (Accepted, In Print).
Goyal V., Lehal G.S. 2011a. Hindi to Punjabi
Machine Translation System. ...
2.6.3 Word -to- Word translation using
lexicon lookup
If token is not a title or a surname, it is looked
up in the HPDictionary database containing
Hindi to Punjabi direct word to word
translation. ... gives it totranslation engine
for analysis till the complete input text is read
and processed.
2.6 Translation Engine
The translation engine is the main component
of our Machine Translation...
... according to the automatic metric. For
this, we consider in each translation case c, the
worse automatic translation t that equals or im-
proves the human-aided translation t
h
according
to the automatic ... and
the Confusion of Tongues: an MT Metric. In Pro-
ceedings of the Workshop on MT Evaluation ”Who
did what to whom?” at MachineTranslation Summit
VIII, pages 55–59.
Christoph Tillmann, Stefan ... Labelled Dependencies in Machine
Translation Evaluation. In Proceedings of the ACL
Workshop on Statistical Machine Translation, pages
104–111.
Kishore Papineni, Salim Roukos, Todd Ward, and Wei-
Jing...
... USA
me@hal3.name
Abstract
We present a method to transliterate names
in the framework of end -to- end statistical
machine translation. The system is trained
to learn when to transliterate. For Arabic
to English MT, we developed ... apply it to any base SMT system, and
to human translationsas well. Our goal in augment-
ing abaseSMT systemis toincreasethis percentage.
A secondary goal is to make sure that our overall
translation ... transliterator described in section
3 to the tagged items. We limit this transliter-
ation to words that occur up to 50 times in the
training corpus for single token names (or up
to 100 and 150 times for...
... their
effect on translation. We also report on applying
Factored TranslationModels (Koehn and Hoang,
2007) for English -to- Arabic translation.
2 Previous Work
The only previous work on English -to- Arabic ... languages.
Koehn and Hoang (2007) present Factored Transla-
tion Models as an extension to phrase-based statisti-
cal machinetranslation models. Factored models al-
low the integration of additional ... techniques. We also report on the use
of Factored TranslationModels for English-
to- Arabic translation.
1 Introduction
Arabic has a complex morphology compared to
English. Words are inflected for gender,...
... Statistical Machine Translation
The goal of the translation process in statisti-
cal machinetranslation can be formulated as fol-
lows: A source language string
is to be translated into a target ... applies this approach
to the so-called IBM Candide system to build con-
text dependent models, compute automatic sen-
tence splitting and to improve word reordering in
translation. Similar techniques ... provided by the
translation system.
7 Conclusions
We have developed refined lexicon models for
statistical machinetranslation by using maximum
entropy models. We have been able to obtain a
significant...
...
4.2 The prototype
In order to evaluate the approach described
above and to concretely investigate the ins and
outs of such implementation, we built up a proto-
type of a machinetranslation ... Association for Computational Linguistics
Lexical Morphology in Machine Translation: a Feasibility Study
Bruno Cartoni
University of Geneva
cartonib@gmail.com
Abstract
This paper presents ...
methodological criteria that are needed to exploit
lexical morphology in machine translation.
2 Issues
Unknown words are a problematic issue in any
NLP tool. Depending on the studies (Ren and...
... Stuttgart
{durrani,sajjad,fraser,schmid}@ims.uni-stuttgart.de
Abstract
We present a novel approach to integrate
transliteration into Hindi -to- Urdu statisti-
cal machine translation. We propose two
probabilistic models, based on conditional
and joint probability ... opposed to Urdu where they are
ematical formulation of our two models, Model-1
and Model-2.
3.1 Model-1 : Conditional Probability Model
Applying a noisy channel model to compute the
most probable translation ... and the trans-
lation model. We refer to the words known to
the language model and to the translation model
as LM-known and TM-known words respectively
and to words that are unknown as LM-unknown
and...
... dependency language
model to improve translation quality. To some ex-
tent, these syntactically-informed language models
are consistent with syntax-based translation models
in capturing long-distance ... advance
translation models from word-based paradigm to
syntax-based philosophy, in recent years we have
also witnessed increasing efforts dedicated to ex-
tend standard n-gram language models ... corpora to train our translation
model and smaller corpora without the United Na-
tions corpus to build a maximum entropy based re-
ordering model (Xiong et al., 2006).
To train our language models...
... Linguistics
Improving On-line Handwritten Recognition using Translation Models
in Multimodal Interactive Machine Translation
Vicent Alabau, Alberto Sanchis, Francisco Casacuberta
Institut Tecnol
`
ogic ... ma-
chine translation (IMT) (Foster et al., 1998; Bar-
rachina et al., 2009; Koehn and Haddow, 2009) the
system goal is not to produce “perfect” translations
in a completely automatic way, but to help ... counterparts. Still, inverse IBM models
perform better than the n-grams alone. Log-linear
models show a bit of improvement with respect to
IBM models. However, linear interpolated models
perform the best....