Notes:
A topic selection module can name a cluster automatically. The topic selection module decides the flow of conversation based on the selection probabilities of topics. The topic selection module may compose a summary. In a real-time application, a topic selection module that classifies the input of an NLU system would not be expected to have access to the parser annotations. A topic selection module may be designed to enhance the readability of topic names. A conversational system may be composed of topic selection module, conversation control module and utterance selection module. WordNet was used to enhance the topic selection module in MegaSAL.
See also:
Topic Selection of Web Documents Using Specific Domain Ontology H Kong, M Hwang, G Hwang, J Shim… – MICAI 2006: Advances in …, 2006 – Springer … This paper is organized as follows: Section 2 presents related works. In Section 3, we present the preprocessing tasks for supporting our approach. In Section 4, we present our approach, which consists of the mapping module, topic selection module, Page 2. 1048 H. Kong et al. … Cited by 10 – Related articles – BL Direct – All 2 versions
Using GHSOM to construct legal maps for Taiwan’s securities and futures markets [PDF] from ntu.edu.tw JY Shih, YJ Chang… – Expert Systems with Applications, 2008 – Elsevier … Meanwhile, an enhanced topic selection module and a web-based user interface are also proposed. … Hence, in this paper, we propose a topic selection module that names a cluster automatically. This is discussed in detail in Section 4. … Cited by 11 – Related articles – All 5 versions
Remote education based on robot edutainment A Yorita, T Hashimoto, H Kobayashi… – Progress in Robotics, 2009 – Springer … module. The topic selection module decides the global flow of conversation based on the selection probabilities of topics. The conversation with people controls the flow of utterances based on transition probabilities of utter- ances. … Cited by 3 – Related articles – All 3 versions
Topic-specific parser design in an air travel natural language understanding application [PDF] from cmu.edu CJK Ekanadham… – Eighth European Conference on …, 2003 – isca-speech.org … In a real-time application, a topic selection module that classifies the input of an NLU system would not be expected to have access to the parser annotations. The partition of the corpora into the conforming topics produced subsets of the size shown in figure 2 below: … Cited by 1 – Related articles – All 2 versions
[PDF] Rushes Redundancy Detection [PDF] from psu.edu R Ren, P Punitha… – Proceedings of the TRECVID BBC Rushes …, 2008 – Citeseer … The module of retaking identification computes the sequential similarity between these sub-sequences and therefore removes unnec- essary re-take instances. The later topic selection module chooses video clips with a high attention intensity and com- poses a summary. … Cited by 1 – Related articles – View as HTML – All 5 versions
Dynamic searching in the brain [HTML] from nih.gov E Mizraji, A Pomi… – Cognitive Neurodynamics, 2009 – Springer Page 1. RESEARCH ARTICLE Dynamic searching in the brain Eduardo Mizraji E Andrés Pomi E Juan C. Valle-Lisboa Received: 9 March 2009 / Revised: 27 April 2009 / Accepted: 27 April 2009 / Published online: 3 June 2009 Ó Springer Science+Business Media BV 2009 … Cited by 2 – Related articles – All 4 versions
Conversation system based on Boltzmann selection and Bayesian networks for a partner robot N Kubota… – … Communication, 2009. RO-MAN 2009. The …, 2009 – ieeexplore.ieee.org Page 1. Abstract-Human interaction based on conversation and gestures is very important to realize the natural communication. This paper proposes a conversation system composed of topic selection module, conversation control module and utterance selection module. … Related articles
[PDF] Integration of WordNet into a Topic Selection Routine [PDF] from uchicago.edu J Riehl – people.cs.uchicago.edu … Section 2 gives an overview of the MegaSAL design and implementation, comparing and contrasting MegaSAL with the bot it was modeled after, MegaHAL. Section 3 presents how WordNet was used to enhance the topic selection module in MegaSAL. … Related articles – View as HTML
Conversation system for robot partners based on informationally structured space N Kubota, T Mori… – Robotic Intelligence In …, 2011 – ieeexplore.ieee.org … The scenario conversation mode is performed by three interrelated module, topic selection modules, conversation control module, and utterance selection module. The topic selection module decides the global flow of conversation based on the selection probabilities of topics. … Related articles
Adaptive Engine Logic Used in Training Academic Proficiency L Cheng, B Kong, J Ng, S Lee… – US Patent App. 10/551,663, 2004 – Google Patents … [0047] In one exemplary embodiment of the present inven- tion, the server tier comprises a collection of server processes including a Knowledge Assessment Test module, a Topic Selection module, and a Question Selection module, (collec- tively also called “Engine …
Adaptive Engine Logic Used in Training Academic Proficiency L Cheng, B Kong, J Ng, S Lee… – US Patent App. 20,080/ …, 2004 – freepatentsonline.com … In one exemplary embodiment of the present invention, the server tier comprises a collection of server processes including a Knowledge Assessment Test module, a Topic Selection module, and a Question Selection module. (collectively also called “Engine”), discussed below. … Cached
System And Method For Triaging Of Information Feeds L Hong, G Covertino, B Suh… – US Patent App. 12/646,846, 2009 – Google Patents Page 1. <19) United States US 20llOl53646Al <12) Patent Application Publication <10) Pub. No.: US 2011/0153646 A1 Hong et al. (43) Pub. Date: Jun. 23, 2011 (54) SYSTEM AND METHOD FOR TRIAGING OF Publication Classi?cation … All 2 versions
An automated knowledge structure construction approach: Applying information retrieval and genetic algorithm to journal of Expert Systems with Applications DY Chiu, YC Pan… – Expert Systems With Applications, 2009 – Elsevier … securities and futures market. A topic selection module was designed to enhance the readability of topic names (Shih, Chang, & Chen, 2008). 20 labels were obtained for each cluster by the LabelSOM algorithm. The topic name … Related articles – All 5 versions
[PDF] Constructing Knowledge Maps of A Manager’s Managerial Logic by A Text Mining Approach [PDF] from atlantis-press.com JYSYJ Chang – atlantis-press.com … Because the label lists suggested by LabelSOM are not all suitable as topic names in this case, we designed a topic selection module to enhance the readability of topic names. We first obtained at most 20 labels for each cluster by the LabelSOM algorithm. … Related articles – View as HTML – All 2 versions
[HTML] ??????????????? [HTML] from airitilibrary.com ??? – ?????????????, 2005 – airitilibrary.com … We use GHSOM to present a content-based, highly readable, and easy-to-use map hierarchy for Chinese language legal documents in the securities and futures markets. We also propose a fully enhanced topic selection module and a web-based user interface. …