a spoken dialogue interface
Tài liệu Báo cáo khoa học: "Semantic Information and Derivation Rules for Robust Dialogue Act Detection in a Spoken Dialogue System" pptx
Ngày tải lên :
20/02/2014, 05:20
... utterance, H
t
is the dialogue
historical information, and Ω = {A
1
, . . . , A
q
} is the
set of DAs. Using the maximum approximation for
summation, (1) can be written as
A
∗
t
= arg max
A Ω
W
P ... under-
standing (SLU) module converts W
t
to an abstract
representation of the user’s dialogue act (DA). The
dialogue management (DM) module determines the
user’s dialogue act A
∗
t
and accordingly ... infor-
mation data set harvested from the databases avail-
able on the web, e.g., Wikipedia and Google Map.
A- data consists of 1, 603 sentences with 317 word
types. The second type of data, called...
- 6
- 555
- 0
Tài liệu Báo cáo khoa học: "The Utility of a Graphical Representation of Discourse Structure in Spoken Dialogue Systems" ppt
Ngày tải lên :
20/02/2014, 12:20
...
tutoring task. In addition, the SIH is not always
available and users have to activate it manually.
Other visual improvements for dialogue- based
computer tutors have been explored in the past
(e.g. ... Uncertainty in
Spoken Tutorial Dialogue Systems. International
Journal of Artificial Intelligence in Education, 16.
C. Rich and C. L. Sidner. 1998. COLLAGEN: A Col-
laboration Manager for Software ... Tuto
r
5
362
that naïve users can reliably annotate the informa-
tion needed for the NM (Passonneau and Litman,
1993). Our NM design choices should also have an
equivalent in a new domain (e.g. displaying...
- 8
- 515
- 0
Tài liệu Báo cáo khoa học: "A Shallow Model of Backchannel Continuers in Spoken Dialogue" potx
Ngày tải lên :
22/02/2014, 02:20
... Sydney,
Australia. Australian Speech Science and Technology As-
sociation (ASSTA).
J. Carletta, A. Isard, S. Isard, J. Kowtko, G. Doherty-
Sneddon, and A. Anderson. 1997. The reliability of a di-
alogue ... indicated by con-
junctive and case/adverbial particles and adverbial
verb forms, coupled with the FO contours flat-fall
and rise-fall.
Ward & Tsukahara (2000) modeled the location of
backchannel ... difficulty with evaluating a model such as
ours is that human speakers differ markedly in their
own backchanneling behaviour. As Ward and Tsuka-
hara (2000) remark, " ;a rule can predict opportunities,
but...
- 8
- 651
- 0
Tài liệu Báo cáo khoa học: "Using Automatically Transcribed Dialogs to Learn User Models in a Spoken Dialog System" doc
Ngày tải lên :
20/02/2014, 09:20
... 08540, USA
usyed@cs.princeton.edu
Jason D. Williams
Shannon Laboratory
AT&T Labs — Research
Florham Park, NJ 07932, USA
jdw@research.att.com
Abstract
We use an EM algorithm to learn user ... expectation and its
maximization are easy to compute. This is because
our dialog model has a chain-like structure that
closely resembles an Hidden Markov Model, so a
forward-backward procedure can ... θ be the maximum likelihood
estimate using automatically transcribed data,
i.e., θ
asu
=
e
K
D
as
P
a
e
K
D
as
. This approach ignores
transcription errors and assumes that user be-
havior depends...
- 4
- 470
- 0
Tài liệu Báo cáo khoa học: "Co-training for Predicting Emotions with Spoken Dialogue Data" pdf
Ngày tải lên :
20/02/2014, 16:20
...
instances. We compare the learning curve from
Co-training with a baseline of majority class and
an upper-bound, in which the classifiers are trained
on human-annotated data. Post-hoc analyses ... promising
approach for predicting emotions with spoken
dialogue data. We have given an algorithm that
increased the size of the training set producing
even better accuracy than the manually labeled ... (where an utterance is a
student’s turn in a dialogue) . Unfortunately, high
dimensionality, i.e. large amount of input features,
may lead to a large variance of estimates, noise,
overfitting, and...
- 4
- 381
- 0
Tài liệu Báo cáo khoa học: "Dialog Navigator : A Spoken Dialog Q-A System based on Large Text Knowledge Base" docx
Ngày tải lên :
20/02/2014, 16:20
... Knowledge Base
Yoji Kiyota, Sadao Kurohashi (The University of Tokyo)
kiyota,kuro @kc.t.u-tokyo.ac.jp
Teruhisa Misu, Kazunori Komatani, Tatsuya Kawahara (Kyoto University)
misu,komatani,kawahara @kuis.kyoto-u.ac.jp
Fuyuko ... typical vague user question. If a user
question matches it, the dialog manager asks the
back question after
SYS , showing choices be-
Dialog Navigator : A Spoken Dialog Q -A System
based on Large ... solutions have problems: it is diffi-
cult for beginners to retrieve a proper item in large
manuals; experts are not always near us; and call
centers are not always available. Furthermore, op-
eration...
- 4
- 509
- 0
Tài liệu Báo cáo khoa học: "Context Management with Topics for Spoken Dialogue Systems" pptx
Ngày tải lên :
20/02/2014, 18:20
... management for spoken dialogue systems.
Finally, statistical modelling is prone to sparse data
problems, and we need to consider ways to overcome
inaccuracies in calculating mutual information. ... test utterances), and used the
other 70 dialogues for training in each test cycle.
The average accuracy rate, 78.68 % is a satisfactory
result. We also did another set of cross-validation
tests ... Focus of attention:
Constraining what can be said next. In C. L.
Paris, W. R. Swartout, and W. C. Moore, ed-
itors, Natural Language Generation in Artificial
Intelligence and Computational Linguistics,...
- 7
- 362
- 0
Tài liệu Báo cáo khoa học: "Information Presentation in Spoken Dialogue Systems" potx
Ngày tải lên :
22/02/2014, 02:20
... efficient and natural access to applica-
tions and services, such as email and calendars,
travel and entertainment booking, and product rec-
ommendation. In evaluating nine SDS in the
DARPA Communicator ... designed
manually, as this system is implemented for an-
other domain. The order of the dialogues in a pair
was randomized. The dialogues were provided as
transcripts.
After reading each dialogue transcript, ... in-
formation is given about the cluster. All positive
homogeneous attributes are mentioned and con-
trasted against all average or negative attributes.
An attribute that was used for identification...
- 8
- 357
- 0
Báo cáo khoa học: " a Movie Dialogue Corpus for Research and Development" potx
Ngày tải lên :
07/03/2014, 18:20
... Seve-
ral factors, such as the availability of more power-
ful computers, an almost unlimited storage ca-
pacity, the availability of large volumes of data in
digital format, as well as the ... data-driven methodolo-
gy for dialogue management and natural language
generation. Springer.
Stallard D (2000) Talk’n’travel: a conversational system
for air travel planning. In Proceedings of ... in
which human-human dialogue applications already
exists, data collection is generally straight forward,
while in some other cases, data design and collec-
tion can constitute a complex problem...
- 5
- 424
- 0
Báo cáo khoa học: "High Frequency Word Entrainment in Spoken Dialogue" ppt
Ngày tải lên :
08/03/2014, 01:20
... exchanges
characterized by overlaps are reliably associated
with entrainment in usage of affirmative cue word,
filled pauses and game-specific most frequent
words. Long latency is negatively associated ... Word Entrainment in Spoken Dialogue
Ani Nenkova
Dept. of Computer and Information Science
University of Pennsylvania
Philadelphia, PA 19104, USA
nenkova@seas.upenn.edu
Agust
´
ın Gravano
Dept. ... corpus), and its as-
sociation with dialogue naturalness and flow,
as well as with task success. Our results show
that such entrainment is predictive of the per-
ceived naturalness of dialogues and...
- 4
- 306
- 0