spoken dialogue agent for email

Ngày tải lên: 17/03/2014, 07:20

Ngày tải lên: 31/03/2014, 03:20

... June 19-24, 2011. c 2011 Association for Computational Linguistics Semantic Information and Derivation Rules for Robust Dialogue Act Detection in a Spoken Dialogue System Wei-Bin Liang 1 Chung-Hsien ... method of dialogue act de- tection for robust spoken dialogue system, we adopt the commonly-used Wizard-of-Oz approach (Fraser and Gilbert, 1991) to harvest the Tainan-city tour- guiding dialogue ... computed. Figure 2: An example of a dialogue management mod- ule using n-gram model for dialogue act sequence in the domain of historic spot. 3 ASR Score and History Score For the ASR score, we use the...

Ngày tải lên: 20/02/2014, 05:20

... performance end end average_performance and keep average_performance end B = best average_performance bestFeatures  B ∪ bestFeatures end Figure 2. Implemented algorithm for forward ... Wrappers for Feature Subset Selection. Artificial Intelligence, Volume 97, Issue 1-2. D. J. Litman and K. Forbes-Riley, 2004. Annotating Student Emotional States in Spoken Tutoring Dialogues. ... Interest Group on Discourse and Dialogue Workshop on Discourse and Dialogue (SIGdial). D. J. Litman and S. Silliman, 2004. ITSPOKE: An Intelligent Tutoring Spoken Dialogue System. Companion Proceedings...

Ngày tải lên: 20/02/2014, 16:20

... point. For the pruned topic types, we reserved 10 ran- domly picked dialogues for testing (each test file con- tained about 400-500 test utterances), and used the other 70 dialogues for training ... fact that the information content of the utterances is ignored. Consistency of the information exchanged in (task- oriented) conversations is one of the main sources for dialogue coherence, ... shifts of attention, we seek a formalisation of the information structure of utterances in terms of the new information that is exchanged in the course of the dialogue. The purpose of our...

Ngày tải lên: 20/02/2014, 18:20

... Introduction Building a robust spoken dialogue system for a new task currently requires considerable effort, includ- ing extensive data collection, grammar develop- ment, and building a dialogue manager that ... 85–88, Ann Arbor, June 2005. c 2005 Association for Computational Linguistics Two diverse systems built using generic components for spoken dialogue (Recent Progress on TRIPS) James Allen, George ... framework for man- aging the dialogue. The collaboration manager queries a domain-specific task component in order to make decisions about interpretations and re- sponses. 4 TRIPS Spoken Dialogue...

Ngày tải lên: 08/03/2014, 04:22

... the No Help con- 152 Targeted Help for Spoken Dialogue Systems: intelligent feedback improves naive users' performance Beth Ann Hockey Research Institute for Advanced Computer Science (RIACS), NASA ... experience with spoken dialogue systems. The structure of the interaction with the system was the same for both groups. They were given minimal written instruction on how to use the system before the ... ex- periments on a spoken dialogue system for command and control of a simulated robotic helicopter. 1 Introduction Targeted Help makes use of user utterances that are out-of-coverage of the main dialogue...

Ngày tải lên: 08/03/2014, 21:20

... generation for spoken dialogue: an experiment. In In Proc. of IC- SLP. Amanda Stent, Rashmi Prasad, and Marilyn Walker. 2004. Trainable sentence planning for complex in- formation presentation in spoken ... 2006. Infor- mation presentation in spoken dialogue systems. In Proceedings of EACL. James Henderson, Oliver Lemon, and Kallirroi Georgila. 2008. Hybrid reinforcement / supervised learning of dialogue ... simulation User simulations are commonly used to train strategies for Dialogue Management, see for ex- ample (Young et al., 2007). A user simulation for NLG is very similar, in that it is a predictive model of...

Ngày tải lên: 08/03/2014, 21:20

Ngày tải lên: 17/03/2014, 00:20

Ngày tải lên: 17/03/2014, 07:20

Ngày tải lên: 17/03/2014, 23:20

Ngày tải lên: 23/03/2014, 16:20

Ngày tải lên: 23/03/2014, 19:20

Ngày tải lên: 23/03/2014, 20:21

Ngày tải lên: 31/03/2014, 20:20

Ngày tải lên: 22/06/2014, 23:20

... ./usr/local/ilagent/bin/ilagentd To stop Endpoint Security Agent: ° Type the following command to stop Endpoint Security Agent: [root@localhost root] # ./usr/local/ilagent/bin/ilagentd shutdown ... section. Endpoint Security Agent for Linux 25 [root@localhost root] # ./usr/local/ilagent/bin/ilagentd shutdown -c <config_file> [root@localhost root] # ./usr/local/ilagent/bin/ilagentd -c <config_file> Using ... by other U.S. Patents, foreign Endpoint Security Agent for Linux 7 Endpoint Security Agent for Linux 7 To manage Linux computer groups: 1. Create a user catalog and group for Linux computers....

Ngày tải lên: 23/10/2013, 12:15

... for Software Interface Agents. User Modeling and User-Adapted Interaction, 8(3-4). M. Rotaru and D. Litman. 2006. Exploiting Discourse Structure for Spoken Dialogue Performance Analy- sis. In ... has inspired several generic dialogue man- agers for spoken dialogue systems (e.g. (Rich and Sidner, 1998)). The NM requires that we have the discourse structure information at runtime. To do ... present, it is easier for users to integrate the current question to the discussion so far (Q10, trend). For Q10, there is no difference for F users but a sig- nificant one for S users. We hypothesize...

Ngày tải lên: 20/02/2014, 12:20

... context of informing work on spoken dialogue systems, is somewhat at odds with previous think- ing about turn-taking. Although turn-taking behaviour is cul- turally dependent , human dialogue is ... (2002) describe work on building spoken dialogue systems for convers- ing with mobile robots, and this is a setting where com- plex instructions naturally arise. For example, in one scenario, 1 ... based on human dia- logue data, for predicting where to place backchannel feedback. The model deliberately requires only simple processing on information that spoken dialogue sys- tems already keep...

Ngày tải lên: 22/02/2014, 02:20

... Information Presentation in Spoken Dialogue Systems Vera Demberg Institute for Natural Language Processing (IMS) University of Stuttgart D-70174 ... lead to a more informed choice and de- crease the risk that the user does not find the opti- mal option. 4 Implementation Our approach was implemented within a spoken dialogue system for flight booking. ... relevant criteria for later in the dialogue. Thus, the branching criterion for the first level of the tree is the attribute that has the highest weight according to the user model. For example, Figure...

Ngày tải lên: 22/02/2014, 02:20