tech,11-5-H01-1058,bq |
show the need for a
<term>
dynamic language
|
model
|
combination
</term>
to improve the
<term>
performance
|
#1144
We provide experimental results that clearly show the need for a dynamic language model combination to improve the performance further. |
model,12-3-N03-1001,bq |
first used to train a
<term>
phone n-gram
|
model
|
</term>
for a particular
<term>
domain
</term>
|
#2269
In our method, unsupervised training is first used to train a phone n-gram model for a particular domain; the output of recognition with this model is then passed to a phone-string classifier. |
model,26-3-N03-1001,bq |
of
<term>
recognition
</term>
with this
<term>
|
model
|
</term>
is then passed to a
<term>
phone-string
|
#2281
In our method, unsupervised training is first used to train a phone n-gram model for a particular domain; the output of recognition with thismodel is then passed to a phone-string classifier. |
model,4-1-N03-1017,bq |
propose a new
<term>
phrase-based translation
|
model
|
</term>
and
<term>
decoding algorithm
</term>
|
#2545
We propose a new phrase-based translation model and decoding algorithm that enables us to evaluate and compare several, previously proposed phrase-based translation models. |
model,7-1-N03-1018,bq |
probabilistic optical character recognition ( OCR )
|
model
|
</term>
that describes an end-to-end process
|
#2682
In this paper, we introduce a generative probabilistic optical character recognition (OCR) model that describes an end-to-end process in the noisy channel framework, progressing from generation of true text through its transformation into the noisy output of an OCR system. |
model,1-2-N03-1018,bq |
</term>
of an
<term>
OCR system
</term>
. The
<term>
|
model
|
</term>
is designed for use in
<term>
error
|
#2713
Themodel is designed for use in error correction, with a focus on post-processing the output of black-box OCR systems in order to make it more useful for NLP tasks. |
model,6-3-N03-1018,bq |
We present an implementation of the
<term>
|
model
|
</term>
based on
<term>
finite-state models
|
#2750
We present an implementation of themodel based on finite-state models, demonstrate the model's ability to significantly reduce character and word error rate, and provide evaluation results involving automatic extraction of translation lexicons from printed text. |
model,14-3-N03-1018,bq |
finite-state models
</term>
, demonstrate the
<term>
|
model
|
</term>
's ability to significantly reduce
|
#2758
We present an implementation of the model based on finite-state models, demonstrate themodel's ability to significantly reduce character and word error rate, and provide evaluation results involving automatic extraction of translation lexicons from printed text. |
model,23-2-N03-1026,bq |
forests
</term>
, and a
<term>
maximum-entropy
|
model
|
</term>
for
<term>
stochastic output selection
|
#2832
Our system incorporates a linguistic parser/generator for LFG, a transfer component for parse reduction operating on packed parse forests, and a maximum-entropy model for stochastic output selection. |
model,28-1-N03-2006,bq |
</term>
and , in addition , the
<term>
language
|
model
|
</term>
of an in-domain
<term>
monolingual
|
#3108
In order to boost the translation quality of EBMT based on a small-sized bilingual corpus, we use an out-of-domain bilingual corpus and, in addition, the language model of an in-domain monolingual corpus. |
model,27-3-N03-2006,bq |
the possibility of using the
<term>
language
|
model
|
</term>
. We describe a simple
<term>
unsupervised
|
#3151
The two evaluation measures of the BLEU score and the NIST score demonstrated the effect of using an out-of-domain bilingual corpus and the possibility of using the language model. |
model,7-1-N03-2036,bq |
we describe a
<term>
phrase-based unigram
|
model
|
</term>
for
<term>
statistical machine translation
|
#3398
In this paper, we describe a phrase-based unigram model for statistical machine translation that uses a much simpler set of model parameters than similar phrase-based models. |
other,21-1-N03-2036,bq |
</term>
that uses a much simpler set of
<term>
|
model
|
parameters
</term>
than similar
<term>
phrase-based
|
#3410
In this paper, we describe a phrase-based unigram model for statistical machine translation that uses a much simpler set ofmodel parameters than similar phrase-based models. |
model,6-3-N03-2036,bq |
decoding
</term>
, we use a
<term>
block unigram
|
model
|
</term>
and a
<term>
word-based trigram language
|
#3436
During decoding, we use a block unigram model and a word-based trigram language model. |
model,11-3-N03-2036,bq |
</term>
and a
<term>
word-based trigram language
|
model
|
</term>
. During
<term>
training
</term>
, the
|
#3442
During decoding, we use a block unigram model and a word-based trigram language model. |
model,16-2-P03-1033,bq |
kinds of
<term>
users
</term>
, the
<term>
user
|
model
|
</term>
we propose is more comprehensive
|
#4315
Unlike previous studies that focus on user's knowledge or typical kinds of users, the user model we propose is more comprehensive. |
model,1-2-P03-1050,bq |
Arabic ) stemmer
</term>
. The
<term>
stemming
|
model
|
</term>
is based on
<term>
statistical machine
|
#4448
The stemming model is based on statistical machine translation and it uses an English stemmer and a small (10K sentences) parallel corpus as its sole training resources. |
model,8-1-P03-1051,bq |
Arabic 's rich morphology
</term>
by a
<term>
|
model
|
</term>
that a
<term>
word
</term>
consists of
|
#4608
We approximate Arabic's rich morphology by amodel that a word consists of a sequence of morphemes in the pattern prefix*-stem-suffix* (* denotes zero or more occurrences of a morpheme). |
model,4-3-P03-1051,bq |
algorithm
</term>
uses a
<term>
trigram language
|
model
|
</term>
to determine the most probable
<term>
|
#4676
The algorithm uses a trigram language model to determine the most probable morpheme sequence for a given input. |
model,1-4-P03-1051,bq |
given
<term>
input
</term>
. The
<term>
language
|
model
|
</term>
is initially estimated from a small
|
#4691
The language model is initially estimated from a small manually segmented corpus of about 110,000 words. |