|
To support engaging human users in robust ,
<term>
mixed-initiative speech dialogue interactions
</term>
which reach beyond current capabilities in
<term>
dialogue systems
</term>
, the
<term>
DARPA Communicator program
</term>
[ 1 ] is funding the development of a
<term>
distributed message-passing infrastructure
</term>
for
<term>
dialogue systems
</term>
which all
<term>
Communicator
</term>
participants are
using
.
|
#251
To support engaging human users in robust, mixed-initiative speech dialogue interactions which reach beyond current capabilities in dialogue systems, the DARPA Communicator program [1] is funding the development of a distributed message-passing infrastructure for dialogue systems which all Communicator participants are using. |
|
We tested this to see if similar criteria could be elicited from duplicating the experiment
using
<term>
machine translation output
</term>
.
|
#677
We tested this to see if similar criteria could be elicited from duplicating the experiment using machine translation output. |
|
The
<term>
oracle
</term>
knows the
<term>
reference word string
</term>
and selects the
<term>
word string
</term>
with the best
<term>
performance
</term>
( typically ,
<term>
word or semantic error rate
</term>
) from a list of
<term>
word strings
</term>
, where each
<term>
word string
</term>
has been obtained by
using
a different
<term>
LM
</term>
.
|
#1110
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 string has been obtained by using a different LM. |
|
Actually , the
<term>
oracle
</term>
acts like a
<term>
dynamic combiner
</term>
with
<term>
hard decisions
</term>
using
the
<term>
reference
</term>
.
|
#1127
Actually, the oracle acts like a dynamic combiner with hard decisionsusing the reference. |
|
We suggest a method that mimics the behavior of the
<term>
oracle
</term>
using
a
<term>
neural network
</term>
or a
<term>
decision tree
</term>
.
|
#1163
We suggest a method that mimics the behavior of the oracleusing a neural network or a decision tree. |
|
The method combines
<term>
domain independent acoustic models
</term>
with off-the-shelf
<term>
classifiers
</term>
to give
<term>
utterance classification performance
</term>
that is surprisingly close to what can be achieved
using
conventional
<term>
word-trigram recognition
</term>
requiring
<term>
manual transcription
</term>
.
|
#2247
The method combines domain independent acoustic models with off-the-shelf classifiers to give utterance classification performance that is surprisingly close to what can be achieved using conventional word-trigram recognition requiring manual transcription. |
|
In this paper , we show how
<term>
training data
</term>
can be supplemented with
<term>
text
</term>
from the
<term>
web
</term>
filtered to match the
<term>
style
</term>
and/or
<term>
topic
</term>
of the target
<term>
recognition task
</term>
, but also that it is possible to get bigger performance gains from the
<term>
data
</term>
by
using
<term>
class-dependent interpolation
</term>
of
<term>
N-grams
</term>
.
|
#3073
In this paper, we show how training data can be supplemented with text from the web filtered to match the style and/or topic of the target recognition task, but also that it is possible to get bigger performance gains from the data by using class-dependent interpolation of N-grams. |
|
The two
<term>
evaluation measures
</term>
of the
<term>
BLEU score
</term>
and the
<term>
NIST score
</term>
demonstrated the effect of
using
an out-of-domain
<term>
bilingual corpus
</term>
and the possibility of using the
<term>
language model
</term>
.
|
#3139
The two evaluation measures of the BLEU score and the NIST score demonstrated the effect of using an out-of-domain bilingual corpus and the possibility of using the language model. |
|
The two
<term>
evaluation measures
</term>
of the
<term>
BLEU score
</term>
and the
<term>
NIST score
</term>
demonstrated the effect of using an out-of-domain
<term>
bilingual corpus
</term>
and the possibility of
using
the
<term>
language model
</term>
.
|
#3148
The two evaluation measures of the BLEU score and the NIST score demonstrated the effect of using an out-of-domain bilingual corpus and the possibility of using the language model. |
|
A novel
<term>
bootstrapping approach
</term>
to
<term>
Named Entity ( NE ) tagging
</term>
using
<term>
concept-based seeds
</term>
and
<term>
successive learners
</term>
is presented .
|
#3296
A novel bootstrapping approach to Named Entity (NE) taggingusing concept-based seeds and successive learners is presented. |
|
During
<term>
training
</term>
, the
<term>
blocks
</term>
are learned from
<term>
source interval projections
</term>
using
an underlying
<term>
word alignment
</term>
.
|
#3455
During training, the blocks are learned from source interval projectionsusing an underlying word alignment. |
|
We describe a new approach which involves clustering
<term>
subcategorization frame ( SCF )
</term>
distributions
using
the
<term>
Information Bottleneck
</term>
and
<term>
nearest neighbour
</term>
methods .
|
#3916
We describe a new approach which involves clustering subcategorization frame (SCF) distributions using the Information Bottleneck and nearest neighbour methods. |
|
Moreover , the
<term>
models
</term>
are automatically derived by
<term>
decision tree learning
</term>
using
real
<term>
dialogue data
</term>
collected by the
<term>
system
</term>
.
|
#4362
Moreover, the models are automatically derived by decision tree learningusing real dialogue data collected by the system. |
|
Our
<term>
resource-frugal approach
</term>
results in 87.5 %
<term>
agreement
</term>
with a state of the art , proprietary
<term>
Arabic stemmer
</term>
built
using
<term>
rules
</term>
,
<term>
affix lists
</term>
, and
<term>
human annotated text
</term>
, in addition to an
<term>
unsupervised component
</term>
.
|
#4551
Our resource-frugal approach results in 87.5% agreement with a state of the art, proprietary Arabic stemmer built using rules, affix lists, and human annotated text, in addition to an unsupervised component. |
|
<term>
Task-based evaluation
</term>
using
<term>
Arabic information retrieval
</term>
indicates an improvement of 22-38 % in
<term>
average precision
</term>
over
<term>
unstemmed text
</term>
, and 96 % of the performance of the proprietary
<term>
stemmer
</term>
above .
|
#4571
Task-based evaluationusing Arabic information retrieval indicates an improvement of 22-38% in average precision over unstemmed text, and 96% of the performance of the proprietary stemmer above. |
|
The evaluation
using
another 23 subjects showed that the proposed method could effectively generate proper
<term>
referring expressions
</term>
.
|
#5713
The evaluation using another 23 subjects showed that the proposed method could effectively generate proper referring expressions. |
|
This paper proposes a new methodology to improve the
<term>
accuracy
</term>
of a
<term>
term aggregation system
</term>
using
each author 's text as a coherent
<term>
corpus
</term>
.
|
#6129
This paper proposes a new methodology to improve the accuracy of a term aggregation systemusing each author's text as a coherent corpus. |
|
Furthermore , we present a standalone system that resolves
<term>
pronouns
</term>
in
<term>
unannotated text
</term>
by
using
a fully automatic sequence of
<term>
preprocessing modules
</term>
that mimics the manual
<term>
annotation process
</term>
.
|
#7083
Furthermore, we present a standalone system that resolves pronouns in unannotated text by using a fully automatic sequence of preprocessing modules that mimics the manual annotation process. |
|
We describe a
<term>
method
</term>
for identifying systematic
<term>
patterns
</term>
in
<term>
translation data
</term>
using
<term>
part-of-speech tag sequences
</term>
.
|
#7639
We describe a method for identifying systematic patterns in translation datausing part-of-speech tag sequences. |
|
We present the first known
<term>
empirical test
</term>
of an increasingly common speculative claim , by evaluating a representative
<term>
Chinese-to-English SMT model
</term>
directly on
<term>
word sense disambiguation performance
</term>
,
using
standard
<term>
WSD evaluation methodology
</term>
and
<term>
datasets
</term>
from the
<term>
Senseval-3 Chinese lexical sample task
</term>
.
|
#7814
We present the first known empirical test of an increasingly common speculative claim, by evaluating a representative Chinese-to-English SMT model directly on word sense disambiguation performance, using standard WSD evaluation methodology and datasets from the Senseval-3 Chinese lexical sample task. |