measure(ment),21-5-I05-2048,bq |
</term>
themselves and achieving good
<term>
|
baseline results
|
</term>
in a short time . The tutorial will
|
#8097
Participants should be able, after attending this workshop, to set out building an SMT system themselves and achieving goodbaseline results in a short time. |
other,1-11-I05-2048,bq |
machine translation system
</term>
. The
<term>
|
source code
|
</term>
of the
<term>
tool kit
</term>
will be
|
#8192
Thesource code of the tool kit will be made available. |
other,10-3-I05-2048,bq |
<term>
translation systems
</term>
for new
<term>
|
language pairs
|
</term>
or new
<term>
domains
</term>
. This
|
#8051
This is particularly important when building translation systems for newlanguage pairs or new domains. |
other,14-1-I05-2048,bq |
currently one of the hot spots in
<term>
|
natural language processing
|
</term>
. Over the last few years dramatic
|
#8001
Statistical machine translation (SMT) is currently one of the hot spots innatural language processing. |
other,14-3-I05-2048,bq |
new
<term>
language pairs
</term>
or new
<term>
|
domains
|
</term>
. This workshop is intended to give
|
#8055
This is particularly important when building translation systems for new language pairs or newdomains. |
other,9-4-I05-2048,bq |
intended to give an introduction to
<term>
|
statistical machine translation
|
</term>
with a focus on practical considerations
|
#8066
This workshop is intended to give an introduction tostatistical machine translation with a focus on practical considerations. |
tech,0-1-I05-2048,bq |
made by the
<term>
WSD models
</term>
.
<term>
|
Statistical machine translation ( SMT )
|
</term>
is currently one of the hot spots
|
#7987
This tends to support the view that despite recent speculative claims to the contrary, current SMT models do have limitations in comparison with dedicated WSD models, and that SMT should benefit from the better predictions made by the WSD models.Statistical machine translation ( SMT ) is currently one of the hot spots in natural language processing. |
tech,15-5-I05-2048,bq |
workshop , to set out building an
<term>
|
SMT system
|
</term>
themselves and achieving good
<term>
|
#8091
Participants should be able, after attending this workshop, to set out building anSMT system themselves and achieving good baseline results in a short time. |
tech,17-10-I05-2048,bq |
translation modules
</term>
to build a
<term>
|
multi engine machine translation system
|
</term>
. The
<term>
source code
</term>
of the
|
#8185
It has also successfully been coupled with rule-based and example based machine translation modules to build amulti engine machine translation system. |
tech,18-8-I05-2048,bq |
introduced and used to build a working
<term>
|
translation system
|
</term>
.
<term>
STTK
</term>
has been developed
|
#8138
STTK, a statistical machine translation tool kit, will be introduced and used to build a workingtranslation system. |
tech,26-2-I05-2048,bq |
</term>
gives competitive results to
<term>
|
rule-based translation systems
|
</term>
, requiring significantly less development
|
#8031
Over the last few years dramatic improvements have been made, and a number of comparative evaluations have shown, that SMT gives competitive results torule-based translation systems, requiring significantly less development time. |
tech,3-8-I05-2048,bq |
into practice .
<term>
STTK
</term>
, a
<term>
|
statistical machine translation tool kit
|
</term>
, will be introduced and used to
|
#8123
STTK, astatistical machine translation tool kit, will be introduced and used to build a working translation system. |
tech,5-11-I05-2048,bq |
The
<term>
source code
</term>
of the
<term>
|
tool kit
|
</term>
will be made available . In this
|
#8196
The source code of thetool kit will be made available. |
tech,6-3-I05-2048,bq |
particularly important when building
<term>
|
translation systems
|
</term>
for new
<term>
language pairs
</term>
|
#8047
This is particularly important when buildingtranslation systems for new language pairs or new domains. |
tech,7-10-I05-2048,bq |
also successfully been coupled with
<term>
|
rule-based and example based machine translation modules
|
</term>
to build a
<term>
multi engine machine
|
#8175
It has also successfully been coupled withrule-based and example based machine translation modules to build a multi engine machine translation system. |
tool,0-8-I05-2048,bq |
Theory will be put into practice .
<term>
|
STTK
|
</term>
, a
<term>
statistical machine translation
|
#8120
Theory will be put into practice.STTK, a statistical machine translation tool kit, will be introduced and used to build a working translation system. |
tool,0-9-I05-2048,bq |
working
<term>
translation system
</term>
.
<term>
|
STTK
|
</term>
has been developed by the presenter
|
#8141
STTK, a statistical machine translation tool kit, will be introduced and used to build a working translation system.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. |
tool,22-9-I05-2048,bq |
is currently used as the basis of
<term>
|
CMU 's SMT system
|
</term>
. It has also successfully been coupled
|
#8163
STTK has been developed by the presenter and co-workers over a number of years and is currently used as the basis ofCMU 's SMT system. |