other,4-3-H01-1058,bq |
<term>
oracle
</term>
knows the
<term>
reference
|
word
|
string
</term>
and selects the
<term>
word
|
#1075
The oracle knows the reference word string and selects the word string with the best performance (typically, word or semantic error rate) from a list of word strings, where each word string has been obtained by using a different LM. |
other,13-1-E06-1031,bq |
high
<term>
costs
</term>
to movements of
<term>
|
word
|
</term>
blocks . In many cases though such
|
#10336
Most state-of-the-art evaluation measures for machine translation assign high costs to movements ofword blocks. |
measure(ment),20-3-N03-1018,bq |
significantly reduce
<term>
character and
|
word
|
error rate
</term>
, and provide evaluation
|
#2766
We present an implementation of the model 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. |
other,25-2-C94-1030,bq |
Japanese bunsetsu
</term>
and an
<term>
English
|
word
|
</term>
, and to correct these
<term>
errors
|
#20667
In order to judge three types of the errors, which are characters wrongly substituted, deleted or inserted in a Japanese bunsetsu and an English word, and to correct these errors, this paper proposes new methods using m-th order Markov chain model for Japanese kanji-kana characters and English alphabets, assuming that Markov probability of a correct chain of syllables or kanji-kana characters is greater than that of erroneous chains. |
other,19-4-C04-1036,bq |
<term>
feature vectors
</term>
and better
<term>
|
word
|
similarity
</term>
performance . The work
|
#5375
Finally, a novel feature weighting and selection function is presented, which yields superior feature vectors and betterword similarity performance. |
tech,4-4-H05-1012,bq |
Significant improvement over traditional
<term>
|
word
|
alignment techniques
</term>
is shown as
|
#7311
Significant improvement over traditionalword alignment techniques is shown as well as improvement on several machine translation tests. |
other,20-5-P03-1051,bq |
<term>
stems
</term>
from a 155 million
<term>
|
word
|
</term><term>
unsegmented corpus
</term>
,
|
#4726
To improve the segmentation accuracy, we use an unsupervised algorithm for automatically acquiring new stems from a 155 millionword unsegmented corpus, and re-estimate the model parameters with the expanded vocabulary and training corpus. |
other,20-2-I05-2014,bq |
English-Japanese
</term>
, because of the
<term>
|
word
|
segmentation problem
</term>
. This study
|
#7720
Yet, they are scarcely used for the assessment of language pairs like English-Chinese or English-Japanese, because of theword segmentation problem. |
tech,7-1-C04-1112,bq |
we present a
<term>
corpus-based supervised
|
word
|
sense disambiguation ( WSD ) system
</term>
|
#5988
In this paper, we present a corpus-based supervised word sense disambiguation (WSD) system for Dutch which combines statistical classification (maximum entropy) with linguistic information. |
tech,22-6-E06-1018,bq |
) idea of
<term>
evaluation
</term>
of
<term>
|
word
|
sense disambiguation algorithms
</term>
is
|
#10205
Additionally, a novel and likewise automatic and unsupervised evaluation method inspired by Schutze's (1992) idea of evaluation ofword sense disambiguation algorithms is employed. |
tech,27-3-A94-1017,bq |
structural disambiguation
</term>
and
<term>
target
|
word
|
selection
</term>
. This paper will concentrate
|
#20256
We have already proposed a model, TDMT (Transfer-Driven Machine Translation), that translates a sentence utilizing examples effectively and performs accurate structural disambiguation and target word selection. |
measure(ment),23-1-I05-2021,bq |
Chinese-to-English SMT model
</term>
directly on
<term>
|
word
|
sense disambiguation performance
</term>
|
#7809
We present the first known empirical test of an increasingly common speculative claim, by evaluating a representative Chinese-to-English SMT model directly onword sense disambiguation performance, using standard WSD evaluation methodology and datasets from the Senseval-3 Chinese lexical sample task. |
other,19-6-P03-1051,bq |
test corpus
</term>
containing 28,449
<term>
|
word
|
tokens
</term>
. We believe this is a state-of-the-art
|
#4762
The resulting Arabic word segmentation system achieves around 97% exact match accuracy on a test corpus containing 28,449word tokens. |
tech,12-4-H01-1041,bq |
disambiguation
</term>
and accurate
<term>
|
word
|
order generation
</term>
of the
<term>
target
|
#489
(ii) High quality translation via word sense disambiguation and accurateword order generation of the target language. |
other,12-5-P05-1074,bq |
methods
</term>
using a set of
<term>
manual
|
word
|
alignments
</term>
, and contrast the
<term>
|
#9764
We evaluate our paraphrase extractio and ranking methods using a set of manual word alignments, and contrast the quality with paraphrases extracted from automatic alignments. |
other,18-3-P06-2110,bq |
<term>
LSA-based and the cooccurrence-based
|
word
|
vectors
</term>
better reflect
<term>
associative
|
#11558
The result of the comparison was that the dictionary-based word vectors better reflect taxonomic similarity, while the LSA-based and the cooccurrence-based word vectors better reflect associative similarity. |
tech,10-6-C90-3072,bq |
method has been developed for easy
<term>
|
word
|
classification
</term>
. We describe the
|
#16862
Further, a special method has been developed for easyword classification. |
tech,2-6-P03-1051,bq |
corpus
</term>
. The resulting
<term>
Arabic
|
word
|
segmentation system
</term>
achieves around
|
#4746
The resulting Arabic word segmentation system achieves around 97% exact match accuracy on a test corpus containing 28,449 word tokens. |
other,6-2-P04-2005,bq |
particular
<term>
concept
</term>
, or
<term>
|
word
|
sense
</term>
, a
<term>
topic signature
</term>
|
#6911
Given a particular concept, orword sense, a topic signature is a set of words that tend to co-occur with it. |
tech,10-2-I05-2021,bq |
designing and evaluating dedicated
<term>
|
word
|
sense disambiguation ( WSD ) models
</term>
|
#7839
Much effort has been put in designing and evaluating dedicatedword sense disambiguation (WSD) models, in particular with the Senseval series of workshops. |