|
adaptive to
<term>
individual users
</term>
serve
|
as
|
good guidance for
<term>
novice users
</term>
|
#4415
Experimental evaluation shows that the cooperative responses adaptive to individual users serve as good guidance for novice users without increasing the dialogue duration for skilled users. |
|
sentences )
<term>
parallel corpus
</term>
|
as
|
its sole
<term>
training resources
</term>
|
#4470
The stemming model is based on statistical machine translation and it uses an English stemmer and a small (10K sentences) parallel corpusas its sole training resources. |
|
semantically annotated corpus
</term>
resource
|
as
|
reliable basis for the large-scale
<term>
|
#4945
We describe the ongoing construction of a large, semantically annotated corpus resource as reliable basis for the large-scale acquisition of word-semantic information, e.g. the construction of domain-independent lexica. |
|
a corpus-based sample and formulate them
|
as
|
<term>
probabilistic Horn clauses
</term>
.
|
#5177
We extract a set of heuristic principles from a corpus-based sample and formulate them as probabilistic Horn clauses. |
|
by noone ( e.g. , I walked is to to walk
|
as
|
I laughed is to to laugh , noted I walked
|
#5861
The reality of analogies between words is refuted by noone (e.g., I walked is to to walk as I laughed is to to laugh, noted I walked : to walk :: I laughed : to laugh). |
|
be valid on the level of
<term>
form
</term>
|
as
|
well as on the level of
<term>
meaning
</term>
|
#5954
As an analogy must be valid on the level of formas well as on the level of meaning, we relied on the idea that translation should preserve meaning to test for similar meanings. |
|
on the level of
<term>
form
</term>
as well
|
as
|
on the level of
<term>
meaning
</term>
, we
|
#5956
As an analogy must be valid on the level of form as well as on the level of meaning, we relied on the idea that translation should preserve meaning to test for similar meanings. |
|
aggregation system
</term>
using each author 's text
|
as
|
a coherent
<term>
corpus
</term>
. Our approach
|
#6134
This paper proposes a new methodology to improve the accuracy of a term aggregation system using each author's text as a coherent corpus. |
|
. While
<term>
sentence extraction
</term>
|
as
|
an approach to
<term>
summarization
</term>
|
#6205
While sentence extractionas an approach to summarization has been shown to work in documents of certain genres, because of the conversational nature of email communication where utterances are made in relation to one made previously, sentence extraction may not capture the necessary segments of dialogue that would make a summary coherent. |
|
<term>
multilingually aligned wordnets
</term>
|
as
|
<term>
BalkaNet
</term>
and
<term>
EuroWordNet
|
#6538
The same system used in a validation mode, can be used to check and spot alignment errors in multilingually aligned wordnetsas BalkaNet and EuroWordNet. |
|
<term>
unstructured data sources
</term>
, such
|
as
|
the
<term>
Web
</term>
or
<term>
newswire documents
|
#6767
Information extraction techniques automatically create structured databases from unstructured data sources, such as the Web or newswire documents. |
|
Processing ( NLP )
</term>
applications , such
|
as
|
<term>
Word Sense Disambiguation ( WSD )
</term>
|
#6947
Topic signatures can be useful in a number of Natural Language Processing (NLP) applications, such as Word Sense Disambiguation (WSD) and Text Summarisation. |
|
word alignment techniques
</term>
is shown
|
as
|
well as improvement on several
<term>
machine
|
#7316
Significant improvement over traditional word alignment techniques is shown as well as improvement on several machine translation tests. |
|
alignment techniques
</term>
is shown as well
|
as
|
improvement on several
<term>
machine translation
|
#7318
Significant improvement over traditional word alignment techniques is shown as well as improvement on several machine translation tests. |
|
presented that deals such
<term>
phrases
</term>
,
|
as
|
well as a
<term>
training method
</term>
based
|
#7382
A statistical translation model is also presented that deals such phrases, as well as a training method based on the maximization of translation accuracy, as measured with the NIST evaluation metric. |
|
deals such
<term>
phrases
</term>
, as well
|
as
|
a
<term>
training method
</term>
based on the
|
#7384
A statistical translation model is also presented that deals such phrases, as well as a training method based on the maximization of translation accuracy, as measured with the NIST evaluation metric. |
|
maximization of
<term>
translation accuracy
</term>
,
|
as
|
measured with the
<term>
NIST evaluation
|
#7396
A statistical translation model is also presented that deals such phrases, as well as a training method based on the maximization of translation accuracy, as measured with the NIST evaluation metric. |
|
</term>
. These
<term>
models
</term>
can be viewed
|
as
|
pairs of
<term>
probabilistic context-free
|
#7462
These models can be viewed as pairs of probabilistic context-free grammars working in a 'synchronous' way. |
|
Translation ( MT ) systems
</term>
, such
|
as
|
<term>
BLEU
</term>
or
<term>
NIST
</term>
, are
|
#7690
Automatic evaluation metrics for Machine Translation (MT) systems, such as BLEU or NIST, are now well established. |
|
a number of years and is currently used
|
as
|
the basis of
<term>
CMU 's SMT system
</term>
|
#8159
STTK has been developed by the presenter and co-workers over a number of years and is currently used as the basis of CMU's SMT system. |