combining acoustic and pragmatic features to predict recognition performance in spoken dialogue systems

Báo cáo khoa học: "Combining Acoustic and Pragmatic Features to Predict Recognition Performance in Spoken Dialogue Systems" pdf

Báo cáo khoa học: "Combining Acoustic and Pragmatic Features to Predict Recognition Performance in Spoken Dialogue Systems" pdf

Ngày tải lên : 08/03/2014, 04:22
... be interesting to investigate the im- pact of different dialogue and task features for clas- sification and to introduce a distinction between “generic” features that are domain independent and “application-specific” ... used by a dialogue manager to decide appro- priate system reactions. The approach is novel in combining machine learning with n-best processing for spoken dialogue systems using the Information State ... Langkilde. 2000. Using Natural Language Processing and Discourse Features to Identify Understanding Er- rors in a Spoken Dialogue System. In Proceed- ings of ICML-2000. 7 Results and Evaluation The...
  • 8
  • 314
  • 0
Báo cáo khoa học: "Combining Linguistic and Gaze Features to Resolve Second-Person References in Dialogue" docx

Báo cáo khoa học: "Combining Linguistic and Gaze Features to Resolve Second-Person References in Dialogue" docx

Ngày tải lên : 17/03/2014, 22:20
... Boakye, ¨ Ozg ¨ ur C¸ etin, Adam Janin, Matthew Magimai-Doss, Chuck Wooters, and Jing Zheng. 2008. The icsi-sri spring 2007 meeting and lecture recognition system. In Proceedings of CLEAR 2007 and RT2007. Springer Lecture ... Strube and Christoph M ¨ uller. 2003. A ma- chine learning approach to pronoun resolution in spoken dialogue. In Proceedings of ACL’03, pages 168–175. Yoshinao Takemae, Kazuhiro Otsuka, and Naoki Mukawa. ... 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. ...
  • 9
  • 242
  • 0
Báo cáo khoa học: "An Architecture for Dialogue Management, Context Tracking, and Pragmatic Adaptation in Spoken Dialogue Systems" pot

Báo cáo khoa học: "An Architecture for Dialogue Management, Context Tracking, and Pragmatic Adaptation in Spoken Dialogue Systems" pot

Ngày tải lên : 17/03/2014, 07:20
... for interrupting user speech for permitting interruption by the user, when to initiate repair dialogues, and how often to back- channel. 1.2 Context Tracking The Context Tracker maintains ... if-then heuristics to determine whether to send through the command or to intercept the utterance and notify the Dia- logue Manager to initiate a repair dialogue with the user. The Pragmatic Adapter ... the Dialogue Manager, Context Tracker, and Pragmatic Adapter need greater functionality, to handle both linguistic and non-linguistic events in both directions. 3.2.2 Computer-Mediated Dialogue...
  • 8
  • 408
  • 0
Báo cáo khoa học: "Learning to Adapt to Unknown Users: Referring Expression Generation in Spoken Dialogue Systems" ppt

Báo cáo khoa học: "Learning to Adapt to Unknown Users: Referring Expression Generation in Spoken Dialogue Systems" ppt

Ngày tải lên : 16/03/2014, 23:20
... types. In addition to the three users - Novice, Expert and Int2, from the train- ing simulations, two other intermediate users (Int1 and Int3) were added to examine how well each policy handles ... de- sign in meaning and reference. In J. F. LeNy and W. Kintsch, editors, Language and comprehension. Amsterdam: North-Holland. H. Cuayahuitl. 2009. Hierarchical Reinforcement Learning for Spoken Dialogue ... referring to (R i ) and its type (T i ) are used. However, the above model simulates the process of interpreting and resolving the expression and identifying the domain entity of interest in the in- struction....
  • 10
  • 293
  • 0
Báo cáo khoa học: "Learning to Generate Naturalistic Utterances Using Reviews in Spoken Dialogue Systems" ppt

Báo cáo khoa học: "Learning to Generate Naturalistic Utterances Using Reviews in Spoken Dialogue Systems" ppt

Ngày tải lên : 23/03/2014, 18:20
... Hirschberg and Diane. J. Litm an. 1987. Now let’ s ta lk about NOW: Identifying cue phrases intonationally. In Proc. 25th ACL, pages 163–171. Minqing Hu and Bing Liu. 2005. Mining and summarizing customer ... domain ontology, and the automat- ically constructed domain ontology from the re- view webpages may not cover all of the domain. In some review domains, the attributes that get individual ratings ... filtering is to identify U that realize the distinguished attributes and to guarantee high precision for the learned mappings. Recall is less important since systems need to convey requested information...
  • 8
  • 293
  • 0
Báo cáo khoa học: "User Simulations for context-sensitive speech recognition in Spoken Dialogue Systems" potx

Báo cáo khoa học: "User Simulations for context-sensitive speech recognition in Spoken Dialogue Systems" potx

Ngày tải lên : 31/03/2014, 20:20
... and pragmatic features to predict recogni- tion performance in spoken dialogue systems. In Proceedings of ACL-04, pages 344–351. Malte Gabsdil. 2003. Classifying Recognition Results for Spoken Dialogue ... is novel in combining User Simulations, machine learning, and n-best processing for spoken dialogue sys- tems. We employed a User Simulation model, trained on real dialogue data, to predict the ... Identify Understanding Errors in a Spoken Dialogue System. In Proceedings of ICML-2000. Jason Williams and Steve Young. 2003. Using wizard- of-oz simulations to bootstrap reinforcement- learning-based...
  • 9
  • 277
  • 0
Classification and regression tree (CART) model to predict pulmonary tuberculosis in hospitalized patients docx

Classification and regression tree (CART) model to predict pulmonary tuberculosis in hospitalized patients docx

Ngày tải lên : 15/03/2014, 03:20
... are increased due to the need for installing and maintaining IR [15-17]. IR are still scarce and infec- tion control measures in health care facilities are at an early stage of development in ... they had any re- spiratory symptom and were also isolated. Clinical data regarding demographic characteristics, respiratory and constitutional symptoms, potential predictive factors for TB diagnosis, ... (spontaneous or induced sputum and bronchoalveolar lavage), by findings of granulomatous inflammation with caseous ne crosis in respiratory tissue biopsy samples or by improvement of respiratory symptoms...
  • 8
  • 630
  • 0
Báo cáo hóa học: "Epigenetic change in E-Cardherin and COX-2 to predict chronic periodontitis" pptx

Báo cáo hóa học: "Epigenetic change in E-Cardherin and COX-2 to predict chronic periodontitis" pptx

Ngày tải lên : 18/06/2014, 16:20
... in cancer initiation [34]. Although the effect of IL-6 to cancer is s till unknown, this cytokine may provide a link from bacterial infection to inflammation and cancer. Changes and damages in cells ... of E-Cadherin and cytokeratin 19 and net proliferative rate of gingival keratinocytes in oral epithelium in periodontal health and disease. J Periodontol 2007, 78:2197-202. 10. Irwin C, Mullally ... was added into the tube and the sample tissue was continu- ally homogenized with grinding. 20 μlofProteinaseK (10 mg/ml) was added to the sample mixture and mixed byvortexing.Thesamplewaslysedbyincubationat 60°C...
  • 6
  • 422
  • 0
Báo cáo y học: " Non-invasive stroke volume measurement and passive leg raising predict volume responsiveness in medical ICU patients: an observational cohort study"

Báo cáo y học: " Non-invasive stroke volume measurement and passive leg raising predict volume responsiveness in medical ICU patients: an observational cohort study"

Ngày tải lên : 25/10/2012, 10:06
... the ventilator as well as changes in car- diac index during PLR were examined. An increase in cardiac index of 10% or more during PLR predicted an increase in car- diac index following VE of 15% ... arterial lines in place who were not necessarily fully accommodated to the ventilator [32]. Changes in arterial pulse pressure and pulse contour-derived cardiac index during end- expiratory occlusion ... CO readings obtained by the USCOM ® and the PAC [28]. The resulting bias between the two meth- ods was 0.18 L/min with limits of agreement of -1.43 L/min to 1.78 L/min. Finally, Dey and Sprivulis...
  • 9
  • 741
  • 0

Xem thêm