Natural language dialogue for personalized interaction
Wlodek Zadrozny, Margo Budzikowska, Joyce Yue Chai, Nandakishore Kambhatla, Sylvie Lévesque, Nicolas Nicolov · Communications of the ACM · 2000
The article focuses on cognitive modeling for games and animation Biblioteca de Ciencias y Tecnología Normal Biblioteca de Ciencias y Tecnología 2 73 2006-05-25T23:44:00Z 2006-05-25T23:44:00Z 1 167 922 UCLA 7 2 1087 11.6568 Clean Clean 21 false false false MicrosoftInternetExplorer4 /* Style Definitions */ table.MsoNormalTable {mso-style-name:"Tabla normal"; mso-tstyle-rowband-size:0; mso-tstyle-colband-size:0; mso-style-noshow:yes; mso-style-parent:""; mso-padding-alt:0cm 5.4pt 0cm 5.4pt; mso-para-margin:0cm; mso-para-margin-bottom:.0001pt; mso-pagination:widow-orphan; font-size:10.0pt; font-family:"Times New Roman"; mso-ansi-language:#0400; mso-fareast-language:#0400; mso-bidi-language:#0400;} The article evaluates the use of natural language (NL) as a compelling enabling technology for personalized interaction. Use of NL offers that each individual can interact with the system in exactly his or her own words, rather than the use of small numbers of preset words and ways to interact. Such behavior requires personalization, as personal contextual data is a condition for smooth interaction. NL understanding is a spectrum of technologies, starting from keyword searches to fully contextualized understanding of intentions. The dialogue system employing NL concept works on six steps, which have been discussed in the article. Engineering a dialogue model consists of selecting an appropriate domain, and relevant set of parameters for all steps. NL understanding does not imply customizing the dialogue to a specific user. It essentially implies customizing to a style or modality of interaction, to a group of users, or to a channel of interaction. Use of NL is restricted in some domains; like in general investment advice which involves large number of conceptual entities.