#2323Motivated by the success of ensemble methods in machine learning and other areas of natural language processing, we developed a multi-strategy and multi-source approach to question answering which is based on combining the results from different answering agents searching for answers in multiple corpora.
tech,13-1-N03-4010,ak
architecture
</term>
with a variety of
<term>
language
processing
modules
</term>
to provide an
<term>
open-domain
#3650The JAVELIN system integrates a flexible, planning-based architecture with a variety of language processing modules to provide an open-domain question answering capability on free text.
tech,1-1-I05-2043,ak
models
</term>
. Using
<term>
natural language
processing
</term>
, we carried out a trend survey on
#6533Using natural language processing, we carried out a trend survey on Japanese natural language processing studies that have been done over the last ten years.
tech,12-1-I05-2043,ak
survey on
<term>
Japanese natural language
processing
studies
</term>
that have been done over
#6545Using natural language processing, we carried out a trend survey on Japanese natural language processing studies that have been done over the last ten years.
tech,14-1-I05-2048,ak
of the hot spots in
<term>
natural language
processing
</term>
. Over the last few years dramatic
#6753Statistical machine translation (SMT) is currently one of the hot spots in natural language processing.
tech,14-1-I05-4007,ak
crucial role in
<term>
multilingual knowledge
processing
</term>
. Since there is no
<term>
homomorphism
#7071Parallel wordnets built upon correspondences between different languages can play a crucial role in multilingual knowledge processing.
tech,27-2-P05-1028,ak
that evidence obtained from
<term>
shallow
processing
</term>
of the graphic 's caption has a significant
#8721It then presents an implemented graphic interpretation system that takes into account a variety of communicative signals, and an evaluation study showing that evidence obtained from shallow processing of the graphic's caption has a significant impact on the system's success.
tech,18-1-J86-3001,ak
the role of
<term>
purpose
</term>
and
<term>
processing
</term>
in
<term>
discourse
</term>
. In this
#16281In this paper we explore a new theory of discourse structure that stresses the role of purpose andprocessing in discourse.
tech,8-10-J86-3001,ak
provides a framework for describing the
<term>
processing
</term>
of
<term>
utterances
</term>
in a
<term>
#16502This theory provides a framework for describing theprocessing of utterances in a discourse.
tech,0-11-J86-3001,ak
a
<term>
discourse
</term>
.
<term>
Discourse
processing
</term>
requires recognizing how the
<term>
#16510Discourse processing requires recognizing how the utterances of the discourse aggregate into segments, recognizing the intentions expressed in the discourse and the relationships among intentions, and tracking the discourse through the operation of the mechanisms associated with attentional state.
with
<term>
attentional state
</term>
. This
processing
description specifies in these
<term>
recognition
#16552This processing description specifies in these recognition tasks the role of information from the discourse and from the participants' knowledge of the domain.
</term>
and
<term>
PATR-II
</term>
. Typically the
processing
of these
<term>
formalisms
</term>
is organized
#17066Typically the processing of these formalisms is organized within a chart-parsing framework.
other,15-4-E87-1037,ak
into critical focus : to gain maximal
<term>
processing
efficiency
</term>
, one has to determine
#17116In particular, this brings the rule-invocation strategy into critical focus: to gain maximalprocessing efficiency, one has to determine the best way of putting the rules to use.
this mechanism has been implemented for
processing
<term>
definitions
</term>
from the
<term>
Longman
#17431An experimental system embodying this mechanism has been implemented for processing definitions from the Longman Dictionary of Contemporary English.
tech,12-8-J87-3001,ak
current experimental
<term>
natural language
processing
systems
</term>
: coping with an incomplete
#17585Thus the work reported addresses two robustness problems faced by current experimental natural language processing systems: coping with an incomplete lexicon and with incomplete knowledge of phrasal constructions.
tech,20-1-C88-1044,ak
implications for current
<term>
discourse
processing
algorithms
</term>
. We examine a broad range
#18037This paper presents necessary and sufficient conditions for the use of demonstrative expressions in English and discusses implications for current discourse processing algorithms.
tech,7-3-C88-2162,ak
representation
</term>
used by
<term>
language
processing
systems
</term>
is not geared to
<term>
learning
#18625For another, linguistic representation used by language processing systems is not geared to learning.
tech,26-3-C88-2166,ak
information
</term>
for use by
<term>
Natural Language
Processing
( NLP ) systems
</term>
. We have drawn primarily
#18833This paper presents our experience in planning and building COMPLEX, a computational lexicon designed to be a repository of shared lexical information for use by Natural Language Processing (NLP) systems.
tech,11-1-H89-2028,ak
recognition
</term>
and
<term>
natural language
processing
</term>
. This is a proposed
<term>
specification
#19990Spoken Language Systems will require integration of continuous speech recognition and natural language processing.
tech,8-1-C90-3072,ak
become an integral part of most
<term>
text
processing
software
</term>
. From different reasons
#20791Spelling-checkers have become an integral part of most text processing software.