|
improved
<term>
speech recognition
</term>
|
has
|
brought to light a new problem : as
<term>
|
#936
However, the improved speech recognitionhas brought to light a new problem: as dialog systems understand more of what the user tells them, they need to be more sophisticated at responding to the user. |
|
system response
</term>
to
<term>
users
</term>
|
has
|
been extensively studied by the
<term>
natural
|
#975
The issue of system response to usershas been extensively studied by the natural language generation community, though rarely in the context of dialog systems. |
|
</term>
, where each
<term>
word string
</term>
|
has
|
been obtained by using a different
<term>
|
#1106
The oracle knows the reference word string and selects the word string with the best performance (typically, word or semantic error rate) from a list of word strings, where each word stringhas been obtained by using a different LM. |
|
concatenation grammar [ RCG ] formalism
</term>
|
has
|
revealed many attractive properties which
|
#1609
The theoretical study of the range concatenation grammar [RCG] formalismhas revealed many attractive properties which may be used in NLP. |
|
shortcomings of different strategies and
|
has
|
all the advantages of the three strategies
|
#3563
Cooperative Model incorporates all the three strategies together and thus can suppress all the shortcomings of different strategies and has all the advantages of the three strategies. |
|
baseline methods
</term>
. Previous research
|
has
|
demonstrated the utility of
<term>
clustering
|
#3886
Previous research has demonstrated the utility of clustering in inducing semantic verb classes from undisambiguated corpus data. |
|
system
</term>
.
<term>
Link detection
</term>
|
has
|
been regarded as a core technology for
|
#4044
Link detectionhas been regarded as a core technology for the Topic Detection and Tracking tasks of new event detection. |
|
Kyoto city bus information system
</term>
that
|
has
|
been developed at our laboratory . Experimental
|
#4396
Dialogue strategies based on the user modeling are implemented in Kyoto city bus information system that has been developed at our laboratory. |
|
that our
<term>
filtering mechanism
</term>
|
has
|
a significant positive effect on both tasks
|
#5487
Our evaluation shows that our filtering mechanismhas a significant positive effect on both tasks. |
|
an approach to
<term>
summarization
</term>
|
has
|
been shown to work in
<term>
documents
</term>
|
#6210
While sentence extraction as an approach to summarizationhas 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. |
|
estimate the
<term>
confidence
</term>
the system
|
has
|
in the correctness of each
<term>
extracted
|
#6802
For many reasons, it is highly desirable to accurately estimate the confidence the system has in the correctness of each extracted field. |
|
, a
<term>
probabilistic model
</term>
which
|
has
|
performed well on
<term>
information extraction
|
#6833
The information extraction system we evaluate is based on a linear-chain conditional random field (CRF), a probabilistic model which has performed well on information extraction tasks because of its ability to capture arbitrary, overlapping features of the input in a Markov model. |
|
lexical sample task
</term>
. Much effort
|
has
|
been put in designing and evaluating dedicated
|
#7831
Much effort has been put in designing and evaluating dedicated word sense disambiguation (WSD) models, in particular with the Senseval series of workshops. |
|
accuracy
</term>
of
<term>
SMT models
</term>
|
has
|
never been evaluated and compared with
|
#7903
Surprisingly however, the WSD accuracy of SMT modelshas never been evaluated and compared with that of the dedicated WSD models. |
|
translation system
</term>
.
<term>
STTK
</term>
|
has
|
been developed by the presenter and co-workers
|
#8142
STTKhas 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. |
|
basis of
<term>
CMU 's SMT system
</term>
. It
|
has
|
also successfully been coupled with
<term>
|
#8169
It has also successfully been coupled with rule-based and example based machine translation modules to build a multi engine machine translation system. |
|
empirical MT research
</term>
. This piece of work
|
has
|
also laid a foundation for exploring and
|
#8297
This piece of work has also laid a foundation for exploring and harvesting English-Chinese bitexts in a larger volume from the Web. |
|
Arabic-English translation task
</term>
. Previous work
|
has
|
used
<term>
monolingual parallel corpora
</term>
|
#9656
Previous work has used monolingual parallel corpora to extract and generate paraphrases. |
|
measure
</term>
with
<term>
human judgment
</term>
|
has
|
been investigated systematically on two
|
#10414
The correlation of the new measure with human judgmenthas been investigated systematically on two different language pairs. |
|
evidence of its usefulness and usability , it
|
has
|
been used successfully in a research context
|
#10903
As evidence of its usefulness and usability, it has been used successfully in a research context to uncover relationships between language and behavioral patterns in two distinct domains: tutorial dialogue (Kumar et al., submitted) and on-line communities (Arguello et al., 2006). |