other,11-1-E06-1035,bq |
problem of automatically predicting
<term>
|
segment boundaries
|
</term>
in
<term>
spoken multiparty dialogue
|
#10473
In this paper, we investigate the problem of automatically predictingsegment boundaries in spoken multiparty dialogue. |
other,14-1-E06-1035,bq |
predicting
<term>
segment boundaries
</term>
in
<term>
|
spoken multiparty dialogue
|
</term>
. We extend prior work in two ways
|
#10476
In this paper, we investigate the problem of automatically predicting segment boundaries inspoken multiparty dialogue. |
other,9-3-E06-1035,bq |
approaches that have been proposed for
<term>
|
predicting top-level topic shifts
|
</term>
to the problem of
<term>
identifying
|
#10497
We first apply approaches that have been proposed forpredicting top-level topic shifts to the problem of identifying subtopic boundaries. |
other,17-3-E06-1035,bq |
topic shifts
</term>
to the problem of
<term>
|
identifying subtopic boundaries
|
</term>
. We then explore the impact on
<term>
|
#10505
We first apply approaches that have been proposed for predicting top-level topic shifts to the problem ofidentifying subtopic boundaries. |
measure(ment),6-4-E06-1035,bq |
</term>
. We then explore the impact on
<term>
|
performance
|
</term>
of using
<term>
ASR output
</term>
as
|
#10515
We then explore the impact onperformance of using ASR output as opposed to human transcription. |
other,9-4-E06-1035,bq |
on
<term>
performance
</term>
of using
<term>
|
ASR output
|
</term>
as opposed to
<term>
human transcription
|
#10518
We then explore the impact on performance of usingASR output as opposed to human transcription. |
other,14-4-E06-1035,bq |
<term>
ASR output
</term>
as opposed to
<term>
|
human transcription
|
</term>
. Examination of the effect of
<term>
|
#10523
We then explore the impact on performance of using ASR output as opposed tohuman transcription. |
other,5-5-E06-1035,bq |
</term>
. Examination of the effect of
<term>
|
features
|
</term>
shows that
<term>
predicting top-level
|
#10531
Examination of the effect offeatures 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. |
other,8-5-E06-1035,bq |
of
<term>
features
</term>
shows that
<term>
|
predicting top-level and predicting subtopic boundaries
|
</term>
are two distinct tasks : ( 1 ) for
|
#10534
Examination of the effect of features shows thatpredicting 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. |
other,24-5-E06-1035,bq |
distinct tasks : ( 1 ) for predicting
<term>
|
subtopic boundaries
|
</term>
, the
<term>
lexical cohesion-based
|
#10550
Examination of the effect of features shows that predicting top-level and predicting subtopic boundaries are two distinct tasks: (1) for predictingsubtopic 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. |
tech,28-5-E06-1035,bq |
<term>
subtopic boundaries
</term>
, the
<term>
|
lexical cohesion-based approach
|
</term>
alone can achieve competitive results
|
#10554
Examination of the effect of features shows that predicting top-level and predicting subtopic boundaries are two distinct tasks: (1) for predicting subtopic boundaries, thelexical 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. |
other,41-5-E06-1035,bq |
achieve competitive results , ( 2 ) for
<term>
|
predicting top-level boundaries
|
</term>
, the
<term>
machine learning approach
|
#10567
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) forpredicting 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. |
tech,46-5-E06-1035,bq |
predicting top-level boundaries
</term>
, the
<term>
|
machine learning approach
|
</term>
that combines
<term>
lexical-cohesion
|
#10572
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, themachine 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. |
other,51-5-E06-1035,bq |
learning approach
</term>
that combines
<term>
|
lexical-cohesion and conversational features
|
</term>
performs best , and ( 3 )
<term>
conversational
|
#10577
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 combineslexical-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. |
other,62-5-E06-1035,bq |
features
</term>
performs best , and ( 3 )
<term>
|
conversational cues
|
</term>
, such as
<term>
cue phrases
</term>
|
#10588
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. |
other,67-5-E06-1035,bq |
conversational cues
</term>
, such as
<term>
|
cue phrases
|
</term>
and
<term>
overlapping speech
</term>
|
#10593
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 ascue phrases and overlapping speech, are better indicators for the top-level prediction task. |
other,70-5-E06-1035,bq |
such as
<term>
cue phrases
</term>
and
<term>
|
overlapping speech
|
</term>
, are better indicators for the top-level
|
#10596
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 andoverlapping speech, are better indicators for the top-level prediction task. |
other,5-6-E06-1035,bq |
prediction task . We also find that the
<term>
|
transcription errors
|
</term>
inevitable in
<term>
ASR output
</term>
|
#10613
We also find that thetranscription 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. |
other,9-6-E06-1035,bq |
transcription errors
</term>
inevitable in
<term>
|
ASR output
|
</term>
have a negative impact on models
|
#10617
We also find that the transcription errors inevitable inASR 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. |
other,19-6-E06-1035,bq |
negative impact on models that combine
<term>
|
lexical-cohesion and conversational features
|
</term>
, but do not change the general preference
|
#10627
We also find that the transcription errors inevitable in ASR output have a negative impact on models that combinelexical-cohesion and conversational features, but do not change the general preference of approach for the two tasks. |