... Combining Acoustic and Pragmatic Features to Predict Recognition
Performance in Spoken Dialogue Systems
Malte Gabsdil
Department of Computational Linguistics
Saarland University
Germany
gabsdil@coli.uni-sb.de
Oliver ... combination of acoustic confi-
dence and pragmatic plausibility features (i.e. com-
puted from dialogue context) to predict the qual-
ity of...
... white-
board/projector screen when addressing the group,
thus drawing the listeners’ gaze in this direction.
Future work will involve expanding our data-
set, and investigating new potentially predictive
features. ... with plural addressing.
Information about dialogue acts also plays a
role in distinguishing between singular and plu-
ral interpretations. Questions tend to be addr...
... helpful in a tutoring spoken dia-
logue system. From the users’ perspective,
our results show that the NM presence al-
lows them to better identify and follow the
tutoring plan and to better integrate ... in most cases, users have
knowledge about the task. However, in complex
domains things are different. Take for example
tutoring. A tutoring dialogue system has to di...
... for manipulating data. Objects
can be classified into classes and instances. A class defines
a procedure [called a method) for handling incoming
messages of its instances. A class inherits methods ... flexible
means of abstracting modules and sharing common knowledge.
1.
Introduction
The goal of this paper is to elaborate a domain-independent
way of organizing linguistic knowled...
... requires joint
expertise in natural language processing and
speech recognition, and best practices in
language engineering for every new domain.
On the other hand, a statistical learning
approach ... directly porting the model
to HCRFs, and finally introduce the CRFs and
882
the features that obtain the best SLU result on
ATIS test data. We compare the CRF and
perce...
... con-
textual information and integrate them into the
feature space. They obtain relatively good results
but are hindered by drawbacks of limited feature
space and excessive feature engineering. Kernel
based ... usage of
patterns and rules, and (iii) usage of flat features
to train machine learning (ML) classifiers. These
approaches have been studied for a long period
and have thei...
... evolution. In C. Huang
and W. Lenders, editors, Computational Linguistics
and Beyond, pages 65–108. Institute of Linguistics,
Academia Sinica, Taipei.
C. Yang. 2001. Internal and external forces in lan-
guage ... coupled. In
Model 1 there is no coupling (ˆα
t
and
ˆ
β
t
learned
independently), in Models 2–3 coupling takes the
form of a hard constraint corresponding to Ross’
g...
... gain in F-value for the combined
model on the training set is appended to the list.
The algorithm terminates when F-value cannot be
improved by any of the remaining candidates. A
finer distinction ... designating the dependent in left -to- right or-
der (e.g. 0 for
in
, 1 for
on
in example (5)), and a
number designating the head in left -to- right (e.g.
0 for
saw
, 1 for
man
, 2...
... string
representing a dubious area, and
in-
form at and on
are words. In this
838
case, the unknown word and its sur-
rounding known words are combined
together, resulting in
" ;in/ ormatjon" ... capture some use-
ful features in discriminating candidate words.
A feature-based approach using Winnow algo-
rithm is then applied to correct the remaining
erro...