|
In this paper we show how
two
standard outputs from
<term>
information extraction ( IE ) systems
</term>
-
<term>
named entity annotations
</term>
and
<term>
scenario templates
</term>
- can be used to enhance access to
<term>
text collections
</term>
via a standard
<term>
text browser
</term>
.
|
#280
In this paper we show how two standard outputs from information extraction (IE) systems - named entity annotations and scenario templates - can be used to enhance access to text collections via a standard text browser. |
|
The
<term>
CCLINC Korean-to-English translation system
</term>
consists of
two
<term>
core modules
</term>
,
<term>
language understanding and generation modules
</term>
mediated by a
<term>
language neutral meaning representation
</term>
called a
<term>
semantic frame
</term>
.
|
#418
The CCLINC Korean-to-English translation system consists of two core modules, language understanding and generation modules mediated by a language neutral meaning representation called a semantic frame. |
|
We reconceptualize the task into
two
distinct phases .
|
#1370
We reconceptualize the task into two distinct phases. |
|
Over
two
distinct
<term>
datasets
</term>
, we find that
<term>
indexing
</term>
according to simple
<term>
character bigrams
</term>
produces a
<term>
retrieval accuracy
</term>
superior to any of the tested
<term>
word N-gram models
</term>
.
|
#1532
Over two distinct datasets, we find that indexing according to simple character bigrams produces a retrieval accuracy superior to any of the tested word N-gram models. |
|
In order to perform an exhaustive comparison , we also evaluate a
<term>
hand-crafted template-based generation component
</term>
,
two
<term>
rule-based sentence planners
</term>
, and two
<term>
baseline sentence planners
</term>
.
|
#2088
In order to perform an exhaustive comparison, we also evaluate a hand-crafted template-based generation component, two rule-based sentence planners, and two baseline sentence planners. |
|
In order to perform an exhaustive comparison , we also evaluate a
<term>
hand-crafted template-based generation component
</term>
, two
<term>
rule-based sentence planners
</term>
, and
two
<term>
baseline sentence planners
</term>
.
|
#2094
In order to perform an exhaustive comparison, we also evaluate a hand-crafted template-based generation component, two rule-based sentence planners, and two baseline sentence planners. |
|
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>
.
|
#3124
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. |
|
We evaluate the utility of this
<term>
constraint
</term>
in
two
different
<term>
algorithms
</term>
.
|
#3267
We evaluate the utility of this constraint in two different algorithms. |
|
The
<term>
bootstrapping procedure
</term>
is implemented as training
two
<term>
successive learners
</term>
.
|
#3341
The bootstrapping procedure is implemented as training two successive learners. |
|
<term>
FSM
</term>
provides
two
strategies for
<term>
language understanding
</term>
and have a high accuracy but little robustness and flexibility .
|
#3518
FSM provides two strategies for language understanding and have a high accuracy but little robustness and flexibility. |
|
On a subset of the most difficult
<term>
SENSEVAL-2 nouns
</term>
, the
<term>
accuracy
</term>
difference between the
two
approaches is only 14.0 % , and the difference could narrow further to 6.5 % if we disregard the advantage that
<term>
manually sense-tagged data
</term>
have in their
<term>
sense coverage
</term>
.
|
#4884
On a subset of the most difficult SENSEVAL-2 nouns, the accuracy difference between the two approaches is only 14.0%, and the difference could narrow further to 6.5% if we disregard the advantage that manually sense-tagged data have in their sense coverage. |
|
We then use the
<term>
predicates
</term>
of such
<term>
clauses
</term>
to create a set of
<term>
domain independent features
</term>
to annotate an input
<term>
dataset
</term>
, and run
two
different
<term>
machine learning algorithms
</term>
:
<term>
SLIPPER
</term>
, a
<term>
rule-based learning algorithm
</term>
, and
<term>
TiMBL
</term>
, a
<term>
memory-based system
</term>
.
|
#5206
We then use the predicates of such clauses to create a set of domain independent features to annotate an input dataset, and run two different machine learning algorithms: SLIPPER, a rule-based learning algorithm, and TiMBL, a memory-based system. |
|
We tested the
<term>
clustering and filtering processes
</term>
on
<term>
electronic newsgroup discussions
</term>
, and evaluated their performance by means of
two
experiments : coarse-level
<term>
clustering
</term>
and simple
<term>
information retrieval
</term>
.
|
#5470
We tested the clustering and filtering processes on electronic newsgroup discussions, and evaluated their performance by means of two experiments: coarse-level clustering and simple information retrieval. |
|
In this paper , a novel framework for
<term>
machine transliteration/back transliteration
</term>
that allows us to carry out
<term>
direct orthographical mapping ( DOM )
</term>
between
two
different
<term>
languages
</term>
is presented .
|
#5767
In this paper, a novel framework for machine transliteration/back transliteration that allows us to carry out direct orthographical mapping (DOM) between two different languages is presented. |
|
We give
two
estimates , a lower one and a higher one .
|
#5932
We give two estimates, a lower one and a higher one. |
|
The correlation of the new
<term>
measure
</term>
with
<term>
human judgment
</term>
has been investigated systematically on
two
different
<term>
language pairs
</term>
.
|
#10419
The correlation of the new measure with human judgment has been investigated systematically on two different language pairs. |
|
We extend prior work in
two
ways .
|
#10485
We extend prior work in two ways. |
|
Examination of the effect of
<term>
features
</term>
shows that
<term>
predicting top-level and predicting subtopic boundaries
</term>
are
two
distinct tasks : ( 1 ) for predicting
<term>
subtopic boundaries
</term>
, the
<term>
lexical cohesion-based approach
</term>
alone can achieve competitive results , ( 2 ) for
<term>
predicting top-level boundaries
</term>
, the
<term>
machine learning approach
</term>
that combines
<term>
lexical-cohesion and conversational features
</term>
performs best , and ( 3 )
<term>
conversational cues
</term>
, such as
<term>
cue phrases
</term>
and
<term>
overlapping speech
</term>
, are better indicators for the top-level prediction task .
|
#10541
Examination of the effect of features shows that predicting top-level and predicting subtopic boundaries are two distinct tasks: (1) for predicting subtopic boundaries, the lexical cohesion-based approach alone can achieve competitive results, (2) for predicting top-level boundaries, the machine learning approach that combines lexical-cohesion and conversational features performs best, and (3) conversational cues, such as cue phrases and overlapping speech, are better indicators for the top-level prediction task. |
|
We also find that the
<term>
transcription errors
</term>
inevitable in
<term>
ASR output
</term>
have a negative impact on models that combine
<term>
lexical-cohesion and conversational features
</term>
, but do not change the general preference of approach for the
two
tasks .
|
#10643
We also find that the transcription errors inevitable in ASR output have a negative impact on models that combine lexical-cohesion and conversational features, but do not change the general preference of approach for the two tasks. |
|
This paper discusses
two
problems that arise in the
<term>
Generation of Referring Expressions
</term>
: ( a )
<term>
numeric-valued attributes
</term>
, such as size or location ; ( b )
<term>
perspective-taking in reference
</term>
.
|
#10649
This paper discusses two problems that arise in the Generation of Referring Expressions: (a) numeric-valued attributes, such as size or location; (b) perspective-taking in reference. |