other,141P011070,bq 
experiments centering on the construction of
<term>

statistical

models
</term>
of
<term>
WHquestions
</term>

#2138
We describe a set of supervised machine learning experiments centering on the construction ofstatistical models of WHquestions. 
tech,172N031004,bq 
mechanisms
</term>
and the other adopting
<term>

statistical

techniques
</term>
. We present our
<term>

#2369
The answering agents adopt fundamentally different strategies, one utilizing primarily knowledgebased mechanisms and the other adoptingstatistical techniques. 
tech,111N032036,bq 
phrasebased unigram model
</term>
for
<term>

statistical

machine translation
</term>
that uses a much

#3400
In this paper, we describe a phrasebased unigram model forstatistical machine translation that uses a much simpler set of model parameters than similar phrasebased models. 
tech,132N033010,bq 
Finite State Model ( FSM )
</term>
and
<term>

Statistical

Learning Model ( SLM )
</term>
.
<term>
FSM

#3509
We build this based on both Finite State Model (FSM) andStatistical Learning Model (SLM). 
tech,04N033010,bq 
little robustness and flexibility .
<term>

Statistical

approach
</term>
is much more robust but

#3534
FSM provides two strategies for language understanding and have a high accuracy but little robustness and flexibility.Statistical approach is much more robust but less accurate. 
other,115P031031,bq 
this
<term>
ambiguity
</term>
based on
<term>

statistical

information
</term>
obtained from
<term>
dialogue

#4227
This paper proposes a method for resolving this ambiguity based onstatistical information obtained from dialogue corpora. 
tech,62P031050,bq 
<term>
stemming model
</term>
is based on
<term>

statistical

machine translation
</term>
and it uses an

#4452
The stemming model is based onstatistical machine translation and it uses an English stemmer and a small (10K sentences) parallel corpus as its sole training resources. 
tech,201C041112,bq 
for
<term>
Dutch
</term>
which combines
<term>

statistical

classification ( maximum entropy )
</term>

#5999
In this paper, we present a corpusbased supervised word sense disambiguation (WSD) system for Dutch which combinesstatistical classification (maximum entropy) with linguistic information. 
tech,91N041022,bq 
BayesRisk ( MBR ) decoding
</term>
for
<term>

statistical

machine translation
</term>
. This statistical

#6552
We present Minimum BayesRisk (MBR) decoding forstatistical machine translation. 

statistical machine translation
</term>
. This

statistical

approach aims to minimize
<term>
expected

#6557
This statistical approach aims to minimize expected loss of translation errors under loss functions that measure translation performance. 
tech,115N041022,bq 
decoding
</term>
can be used to tune
<term>

statistical

MT
</term>
performance for specific
<term>

#6637
Our results show that MBR decoding can be used to tunestatistical MT performance for specific loss functions. 
tech,41H051095,bq 
This paper presents a
<term>
phrasebased

statistical

machine translation method
</term>
, based

#7342
This paper presents a phrasebased statistical machine translation method, based on noncontiguous phrases, i.e. phrases with gaps. 
tech,13H051095,bq 
wordaligned corpora
</term>
is proposed . A
<term>

statistical

translation model
</term>
is also presented

#7371
Astatistical 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. 
tech,314I052014,bq 
texts
</term>
with , for instance ,
<term>

statistical

MT systems
</term>
which usually segment

#7777
The use of BLEU at the character level eliminates the word segmentation problem: it makes it possible to directly compare commercial systems outputting unsegmented texts with, for instance,statistical MT systems which usually segment their outputs. 
tech,133I052021,bq 
improvements in the
<term>
BLEU scores
</term>
of
<term>

statistical

machine translation ( SMT )
</term>
suggests

#7869
At the same time, the recent improvements in the BLEU scores ofstatistical machine translation (SMT) suggests that SMT models are good at predicting the right translation of the words in source language sentences. 
tech,01I052048,bq 
made by the
<term>
WSD models
</term>
.
<term>

Statistical

machine translation ( SMT )
</term>
is currently

#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. 
other,94I052048,bq 
intended to give an introduction to
<term>

statistical

machine translation
</term>
with a focus

#8066
This workshop is intended to give an introduction tostatistical machine translation with a focus on practical considerations. 
tech,38I052048,bq 
into practice .
<term>
STTK
</term>
, a
<term>

statistical

machine translation tool kit
</term>
, will

#8123
STTK, astatistical machine translation tool kit, will be introduced and used to build a working translation system. 
tech,184J054003,bq 
performance of a stateoftheart
<term>

statistical

machine translation system
</term>
. We also

#9063
We evaluate the quality of the extracted data by showing that it improves the performance of a stateoftheartstatistical machine translation system. 
tech,101P051032,bq 
data structure
</term>
for
<term>
phrasebased

statistical

machine translation
</term>
which allows

#9132
In this paper we describe a novel data structure for phrasebased statistical machine translation which allows for the retrieval of arbitrarily long phrases while simultaneously using less memory than is required by current decoder implementations. 