|
reconceptualize the task into two distinct phases .
|
First
|
, a very simple ,
<term>
randomized sentence-plan-generator
|
#1374
We reconceptualize the task into two distinct phases. First, a very simple, randomized sentence-plan-generator (SPG) generates a potentially large list of possible sentence plans for a given text-plan input. |
|
training two
<term>
successive learners
</term>
.
|
First
|
,
<term>
decision list
</term>
is used to learn
|
#3345
The bootstrapping procedure is implemented as training two successive learners. First, decision list is used to learn the parsing-based NE rules. |
|
and
<term>
Naive Bayes classifiers
</term>
.
|
First
|
, we investigate how well the
<term>
addressee
|
#10253
We present results on addressee identification in four-participants face-to-face meetings using Bayesian Network and Naive Bayes classifiers. First, we investigate how well the addressee of a dialogue act can be predicted based on gaze, utterance and conversational context features. |
|
examples in context . We identified two tasks :
|
First
|
, how
<term>
linguistic concepts
</term>
are
|
#15841
We identified two tasks: First, how linguistic concepts are acquired from training examples and organized in a hierarchy; this task was discussed in previous papers [Zernik87]. |
|
vocabulary continuous speech recognition
</term>
.
|
First
|
, we present a new paradigm for
<term>
speaker-independent
|
#16988
This paper reports on two contributions to large vocabulary continuous speech recognition. First, we present a new paradigm for speaker-independent (SI) training of hidden Markov models (HMM), which uses a large amount of speech from a few speakers instead of the traditional practice of using a little speech from many speakers. |
|
principle-and-parameters language framework
</term>
.
|
First
|
, by investigating the combinatorics of
|
#17361
The principle known as free indexation plays an important role in the determination of the referential properties of noun phrases in the principle-and-parameters language framework. First, by investigating the combinatorics of free indexation, we show that the problem of enumerating all possible indexings requires exponential time. |