|
trained with a little
<term>
corpus
</term>
|
of
|
100,000
<term>
words
</term>
, the system guesses
|
#11237
After several experiments, and trained with a little corpusof 100,000 words, the system guesses correctly not placing commas with a precision of 96% and a recall of 98%. |
|
utterances
</term>
based on the
<term>
context
</term>
|
of
|
a
<term>
dialogue
</term>
. Since multiple
<term>
|
#4151
This process enables the system to understand user utterances based on the contextof a dialogue. |
|
investigate how well the
<term>
addressee
</term>
|
of
|
a
<term>
dialogue act
</term>
can be predicted
|
#10261
First, we investigate how well the addresseeof a dialogue act can be predicted based on gaze, utterance and conversational context features. |
|
program
</term>
[ 1 ] is funding the development
|
of
|
a
<term>
distributed message-passing infrastructure
|
#238
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. |
|
</term>
. This paper describes the framework
|
of
|
a
<term>
Korean phonological knowledge base
|
#16360
This paper describes the framework of a Korean phonological knowledge base system using the unification-based grammar formalism: Korean Phonology Structure Grammar (KPSG). |
|
</term>
. We describe the ongoing construction
|
of
|
a large ,
<term>
semantically annotated corpus
|
#4937
We describe the ongoing construction of a large, semantically annotated corpus resource as reliable basis for the large-scale acquisition of word-semantic information, e.g. the construction of domain-independent lexica. |
|
</term>
does not stall even in the presence
|
of
|
a
<term>
lexical unknown
</term>
, and a
<term>
|
#15898
Thus, a program does not stall even in the presence of a lexical unknown, and a hypothesis can be produced for covering that lexical gap. |
|
coherent
<term>
dictionary
</term>
on the basis
|
of
|
a
<term>
linguistic theory
</term>
. If we
|
#17255
The basic goal in building that editor was to provide an adequate tool to help lexicologists produce a valid and coherent dictionary on the basis of a linguistic theory. |
|
effort , the goals , the implementation
|
of
|
a
<term>
multi-site data collection paradigm
|
#18575
We summarize the motivation for this effort, the goals, the implementation of a multi-site data collection paradigm, and the accomplishments of MADCOW in monitoring the collection and distribution of 12,000 utterances of spontaneous speech from five sites for use in a multi-site common evaluation of speech, natural language and spoken language |
|
for automatically training
</term>
modules
|
of
|
a
<term>
natural language generator
</term>
|
#2017
Techniques for automatically training modules of a natural language generator have recently been proposed, but a fundamental concern is whether the quality of utterances produced with trainable components can compete with hand-crafted template-based or rule-based approaches. |
|
<term>
continuous speech recognition
</term>
|
of
|
a
<term>
natural language
</term>
, it has
|
#20621
In optical character recognition and continuous speech recognitionof a natural language, it has been difficult to detect error characters which are wrongly deleted and inserted. |
|
</term>
. This paper gives an overall account
|
of
|
a prototype
<term>
natural language question
|
#12842
This paper gives an overall account of a prototype natural language question answering system, called Chat-80. |
|
are sketched . In order to meet the needs
|
of
|
a publication of papers in English , many
|
#12218
In order to meet the needs of a publication of papers in English, many systems to run off texts have been developed. |
|
underspecified semantic representation ( USR )
</term>
|
of
|
a
<term>
scope ambiguity
</term>
, compute
|
#11137
We present an efficient algorithm for the redundancy elimination problem: Given an underspecified semantic representation (USR)of a scope ambiguity, compute an USR with fewer mutually equivalent readings. |
|
model
</term>
that a
<term>
word
</term>
consists
|
of
|
a sequence of
<term>
morphemes
</term>
in the
|
#4613
We approximate Arabic's rich morphology by a model that a word consists of a sequence of morphemes in the pattern prefix*-stem-suffix* (* denotes zero or more occurrences of a morpheme). |
|
exploits
<term>
context
</term>
on both sides
|
of
|
a
<term>
word
</term>
to be tagged , and evaluate
|
#5508
We present a new HMM tagger that exploits context on both sides of a word to be tagged, and evaluate it in both the unsupervised and supervised case. |
|
processing
</term>
meets the real world , the ideal
|
of
|
aiming for complete and correct interpretations
|
#17412
It is often assumed that when natural language processing meets the real world, the ideal of aiming for complete and correct interpretations has to be abandoned. |
|
printed text
</term>
. We present an application
|
of
|
<term>
ambiguity packing and stochastic disambiguation
|
#2788
We present an application of ambiguity packing and stochastic disambiguation techniques for Lexical-Functional Grammars (LFG) to the domain of sentence condensation. |
|
considers approaches which rerank the output
|
of
|
an existing
<term>
probabilistic parser
</term>
|
#8657
This article considers approaches which rerank the output of an existing probabilistic parser. |
|
the first known
<term>
empirical test
</term>
|
of
|
an increasingly common speculative claim
|
#7793
We present the first known empirical testof 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. |