In this paper we present
<term>
ONTOSCORE
</term>
, a system for scoring sets of
<term>
concepts
</term>
on the basis of an
<term>
ontology
</term>
.
#2441In this paper we presentONTOSCORE, a system for scoring sets of concepts on the basis of an ontology.
other,18-3-N03-1012,ak
We conducted an
<term>
annotation experiment
</term>
and showed that
<term>
human annotators
</term>
can reliably differentiate between semantically coherent and incoherent
<term>
speech recognition hypotheses
</term>
.
#2498We conducted an annotation experiment and showed that human annotators can reliably differentiate between semantically coherent and incoherentspeech recognition hypotheses.
tech,19-1-N03-1012,ak
In this paper we present
<term>
ONTOSCORE
</term>
, a system for scoring sets of
<term>
concepts
</term>
on the basis of an
<term>
ontology
</term>
.
#2455In this paper we present ONTOSCORE, a system for scoring sets of concepts on the basis of anontology.
other,20-2-N03-1012,ak
We apply our
<term>
system
</term>
to the task of scoring alternative
<term>
speech recognition hypotheses ( SRH )
</term>
in terms of their
<term>
semantic coherence
</term>
.
#2477We apply our system to the task of scoring alternative speech recognition hypotheses (SRH) in terms of theirsemantic coherence.
tech,4-4-N03-1012,ak
An evaluation of our
<term>
system
</term>
against the
<term>
annotated data
</term>
shows that , it successfully classifies 73.2 % in a
<term>
German corpus
</term>
of 2.284
<term>
SRHs
</term>
as either coherent or incoherent ( given a
<term>
baseline
</term>
of 54.55 % ) .
#2506An evaluation of oursystem against the annotated data shows that, it successfully classifies 73.2% in a German corpus of 2.284 SRHs as either coherent or incoherent (given a baseline of 54.55%).
other,3-3-N03-1012,ak
We conducted an
<term>
annotation experiment
</term>
and showed that
<term>
human annotators
</term>
can reliably differentiate between semantically coherent and incoherent
<term>
speech recognition hypotheses
</term>
.
#2483We conducted anannotation experiment and showed that human annotators can reliably differentiate between semantically coherent and incoherent speech recognition hypotheses.
other,23-4-N03-1012,ak
An evaluation of our
<term>
system
</term>
against the
<term>
annotated data
</term>
shows that , it successfully classifies 73.2 % in a
<term>
German corpus
</term>
of 2.284
<term>
SRHs
</term>
as either coherent or incoherent ( given a
<term>
baseline
</term>
of 54.55 % ) .
#2525An evaluation of our system against the annotated data shows that, it successfully classifies 73.2% in a German corpus of 2.284SRHs as either coherent or incoherent (given a baseline of 54.55%).
other,8-3-N03-1012,ak
We conducted an
<term>
annotation experiment
</term>
and showed that
<term>
human annotators
</term>
can reliably differentiate between semantically coherent and incoherent
<term>
speech recognition hypotheses
</term>
.
#2488We conducted an annotation experiment and showed thathuman annotators can reliably differentiate between semantically coherent and incoherent speech recognition hypotheses.
other,10-2-N03-1012,ak
We apply our
<term>
system
</term>
to the task of scoring alternative
<term>
speech recognition hypotheses ( SRH )
</term>
in terms of their
<term>
semantic coherence
</term>
.
#2467We apply our system to the task of scoring alternativespeech recognition hypotheses ( SRH ) in terms of their semantic coherence.
lr,19-4-N03-1012,ak
An evaluation of our
<term>
system
</term>
against the
<term>
annotated data
</term>
shows that , it successfully classifies 73.2 % in a
<term>
German corpus
</term>
of 2.284
<term>
SRHs
</term>
as either coherent or incoherent ( given a
<term>
baseline
</term>
of 54.55 % ) .
#2521An evaluation of our system against the annotated data shows that, it successfully classifies 73.2% in aGerman corpus of 2.284 SRHs as either coherent or incoherent (given a baseline of 54.55%).
measure(ment),32-4-N03-1012,ak
An evaluation of our
<term>
system
</term>
against the
<term>
annotated data
</term>
shows that , it successfully classifies 73.2 % in a
<term>
German corpus
</term>
of 2.284
<term>
SRHs
</term>
as either coherent or incoherent ( given a
<term>
baseline
</term>
of 54.55 % ) .
#2534An evaluation of our system against the annotated data shows that, it successfully classifies 73.2% in a German corpus of 2.284 SRHs as either coherent or incoherent (given abaseline of 54.55%).
other,13-1-N03-1012,ak
In this paper we present
<term>
ONTOSCORE
</term>
, a system for scoring sets of
<term>
concepts
</term>
on the basis of an
<term>
ontology
</term>
.
#2449In this paper we present ONTOSCORE, a system for scoring sets ofconcepts on the basis of an ontology.
lr,7-4-N03-1012,ak
An evaluation of our
<term>
system
</term>
against the
<term>
annotated data
</term>
shows that , it successfully classifies 73.2 % in a
<term>
German corpus
</term>
of 2.284
<term>
SRHs
</term>
as either coherent or incoherent ( given a
<term>
baseline
</term>
of 54.55 % ) .
#2509An evaluation of our system against theannotated data shows that, it successfully classifies 73.2% in a German corpus of 2.284 SRHs as either coherent or incoherent (given a baseline of 54.55%).
tech,3-2-N03-1012,ak
We apply our
<term>
system
</term>
to the task of scoring alternative
<term>
speech recognition hypotheses ( SRH )
</term>
in terms of their
<term>
semantic coherence
</term>
.
#2460We apply oursystem to the task of scoring alternative speech recognition hypotheses (SRH) in terms of their semantic coherence.