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. |
tech,6-1-N03-2017,bq |
<term>
syntax-based constraint
</term>
for
<term>
|
word
|
alignment
</term>
, known as the
<term>
cohesion
|
#3234
We present a syntax-based constraint forword alignment, known as the cohesion constraint. |
model,14-4-N03-2036,bq |
projections
</term>
using an underlying
<term>
|
word
|
alignment
</term>
. We show experimental
|
#3458
During training, the blocks are learned from source interval projections using an underlyingword alignment. |
tech,4-1-H05-1012,bq |
This paper presents a
<term>
maximum entropy
|
word
|
alignment algorithm
</term>
for
<term>
Arabic-English
|
#7255
This paper presents a maximum entropy word alignment algorithm for Arabic-English based on supervised training data. |
tech,6-2-C04-1192,bq |
method exploits recent advances in
<term>
|
word
|
alignment
</term>
and
<term>
word clustering
|
#6456
The method exploits recent advances inword alignment and word clustering based on automatic extraction of translation equivalents and being supported by available aligned wordnets for the languages in the corpus. |
tech,14-2-P05-1034,bq |
segmentation
</term>
and an
<term>
unsupervised
|
word
|
alignment component
</term>
. We align a
<term>
|
#9240
This method requires a source-language dependency parser, target language word segmentation and an unsupervised word alignment component. |
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,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. |
measure(ment),16-3-H92-1016,bq |
combined to reduce the
<term>
speech recognition
|
word
|
and sentence error rates
</term>
by a factor
|
#18755
Together with the use of a larger training set, these modifications combined to reduce the speech recognition word and sentence error rates by a factor of 2.5 and 1.6, respectively, on the October '91 test set. |
other,8-10-H01-1042,bq |
Additionally , they were asked to mark the
<term>
|
word
|
</term>
at which they made this decision
|
#747
Additionally, they were asked to mark theword at which they made this decision. |
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. |
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,9-2-C04-1192,bq |
advances in
<term>
word alignment
</term>
and
<term>
|
word
|
clustering
</term>
based on
<term>
automatic
|
#6459
The method exploits recent advances in word alignment andword clustering based on automatic extraction of translation equivalents and being supported by available aligned wordnets for the languages in the corpus. |
other,11-1-P03-1051,bq |
</term>
by a
<term>
model
</term>
that a
<term>
|
word
|
</term>
consists of a sequence of
<term>
morphemes
|
#4611
We approximate Arabic's rich morphology by a model that aword consists of a sequence of morphemes in the pattern prefix*-stem-suffix* (* denotes zero or more occurrences of a morpheme). |
tech,6-3-E06-1018,bq |
approaches it utilizes
<term>
clustering of
|
word
|
co-occurrences
</term>
. This approach differs
|
#10133
Like most existing approaches it utilizes clustering of word co-occurrences. |
other,4-8-E06-1031,bq |
</term>
. Results from experiments with
<term>
|
word
|
dependent substitution costs
</term>
will
|
#10443
Results from experiments withword dependent substitution costs will demonstrate an additional increase of correlation between automatic evaluation measures and human judgment. |
other,31-6-A94-1007,bq |
analysis cost
</term>
, the improvement of
<term>
|
word
|
disambiguation
</term>
, the interpretation
|
#19846
The model is based on a balance matching operation for two lists of the feature sets, which provides four effects: the reduction of analysis cost, the improvement ofword disambiguation, the interpretation of ellipses, and robust analysis. |
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. |
measure(ment),14-4-H90-1060,bq |
recognition
</term>
, we achieved a 7.5 %
<term>
|
word
|
error rate
</term>
on a standard
<term>
grammar
|
#17084
With only 12 training speakers for SI recognition, we achieved a 7.5%word error rate on a standard grammar and test set from the DARPA Resource Management corpus. |
other,11-3-C04-1036,bq |
empirical quality of
<term>
distributional
|
word
|
feature vectors
</term>
and its impact on
|
#5335
Motivated by this semantic criterion we analyze the empirical quality of distributional word feature vectors and its impact on word similarity results, proposing an objective measure for evaluating feature vector quality. |