#2139We describe a set of supervised machine learning experiments centering on the construction ofstatistical models of WH-questions.
knowledge-based mechanisms and the other adopting
statistical
techniques . We present our
<term>
multi-level
#2370The answering agents adopt fundamentally different strategies, one utilizing primarily knowledge-based mechanisms and the other adopting statistical techniques.
tech,11-1-N03-2036,ak
phrase-based unigram model
</term>
for
<term>
statistical
machine translation
</term>
that uses a much
#3401In this paper, we describe a phrase-based unigram model forstatistical machine translation that uses a much simpler set of model parameters than similar phrase-based models.
tech,13-2-N03-3010,ak
Finite State Model ( FSM )
</term>
and
<term>
Statistical
Learning Model ( SLM )
</term>
.
<term>
FSM
#3510We build this based on both Finite State Model (FSM) andStatistical Learning Model (SLM).
tech,0-4-N03-3010,ak
little robustness and flexibility .
<term>
Statistical
approach
</term>
is much more robust but
#3535FSM 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,11-5-P03-1031,ak
this
<term>
ambiguity
</term>
based on
<term>
statistical
information
</term>
obtained from
<term>
dialogue
#4229This paper proposes a method for resolving this ambiguity based onstatistical information obtained from dialogue corpora.
tech,6-2-P03-1050,ak
<term>
stemming model
</term>
is based on
<term>
statistical
machine translation
</term>
and it uses an
#4454The 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,4-1-H05-1095,ak
This paper presents a
<term>
phrase-based
statistical
machine translation method
</term>
, based
#5586This paper presents a phrase-based statistical machine translation method, based on non-contiguous phrases, i.e. phrases with gaps.
model,1-3-H05-1095,ak
word-aligned corpora
</term>
is proposed . A
<term>
statistical
translation model
</term>
is also presented
#5615Astatistical 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,31-4-I05-2014,ak
unsegmented texts with , for instance ,
<term>
statistical
MT systems
</term>
which usually segment
#6320The 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,13-3-I05-2021,ak
improvements in the
<term>
BLEU scores
</term>
of
<term>
statistical
machine translation ( SMT )
</term>
suggests
#6412At 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,0-1-I05-2048,ak
dependency accuracy
</term>
by 10.08 % .
<term>
Statistical
machine translation ( SMT )
</term>
is currently
#6737In experimental evaluation, our proposed method outperforms previous shift-reduce dependency parsers for the Chine language, showing improvement of dependency accuracy by 10.08%.Statistical machine translation (SMT) is currently one of the hot spots in natural language processing.
tech,9-4-I05-2048,ak
intended to give an introduction to
<term>
statistical
machine translation
</term>
with a focus
#6816This workshop is intended to give an introduction tostatistical machine translation with a focus on practical considerations.
tech,3-8-I05-2048,ak
into practice .
<term>
STTK
</term>
, a
<term>
statistical
machine translation tool kit
</term>
, will
#6873STTK, astatistical machine translation tool kit, will be introduced and used to build a working translation system.
tech,10-1-P05-1032,ak
data structure
</term>
for
<term>
phrase-based
statistical
machine translation
</term>
which allows
#8770In this paper we describe a novel data structure for phrase-based statistical machine translation which allows for the retrieval of arbitrarily long phrases while simultaneously using less memory than is required by current decoder implementations.
tech,6-1-P05-1034,ak
</term>
. We describe a novel approach to
<term>
statistical
machine translation
</term>
that combines
#8845We describe a novel approach tostatistical machine translation that combines syntactic information in the source language with recent advances in phrasal translation.
measure(ment),16-1-P05-1048,ak
sense disambigation models
</term>
help
<term>
statistical
machine translation quality
</term>
? We
#9184We directly investigate a subject of much recent debate: do word sense disambigation models helpstatistical machine translation quality?
tech,15-3-P05-1048,ak
candidates
</term>
for a typical
<term>
IBM
statistical
MT system
</term>
, we find that
<term>
word
#9220Using a state-of-the-art Chinese word sense disambiguation model to choose translation candidates for a typical IBM statistical MT system, we find that word sense disambiguation does not yield significantly better translation quality than the statistical machine translation system alone.
tech,35-3-P05-1048,ak
translation quality
</term>
than the
<term>
statistical
machine translation system
</term>
alone
#9239Using a state-of-the-art Chinese word sense disambiguation model to choose translation candidates for a typical IBM statistical MT system, we find that word sense disambiguation does not yield significantly better translation quality than thestatistical machine translation system alone.
other,16-4-P05-1048,ak
including inherent limitations of current
<term>
statistical
MT architectures
</term>
. Extracting
<term>
#9261Error analysis suggests several key factors behind this surprising finding, including inherent limitations of currentstatistical MT architectures.