Trainable Information Agents for the Web
نویسندگان
چکیده
Software agents are intended to perform certain tasks on behalf of their users. In many cases, however, the agent’s competence is not sufficient to produce the desired outcome. This chapter presents an approach to cooperative problem solving in which an information agent and its user try to support each other in achieving a particular goal. As a side effect the user can extend the agent’s capabilities in a programming-by-example dialogue, thus enabling it to perform similar tasks autonomously in the future.
منابع مشابه
طبقهبندی کاربردی کارکردهای عوامل نرمافزاری هوشمند و تطبیق آنها با ویژگیهای وبسایتهای کتابخانههای دیجیتال
Purpose: Web services are presently considered as technologies with highest number of applications for the purpose of providing the automatic, high-quality, and fast information interactions. The aim of this paper is therefore to provide a comprehensive framework for a collection of significant services offered by Farsi websites in libraries to be used in future designs. It also aims to classif...
متن کاملLearning to Extract Information for the Semantic Web
The goal of information extraction (IE) is to find desired pieces of information in natural language texts and store them in a form that is suitable for automatic querying and processing; the Semantic Web provides formats and standards for storing and processing such data. Hence IE-based automatic or semi-automatic approaches are a promising approach for building the Semantic Web. My Ph.D. thes...
متن کاملTools and techniques for rapid porting
Charlie Dolan, from Hughes Research Laboratories, discussed some of the difficulties in using trainable components in an information extraction system. The UMass/Hughes system used six different trainable components in their MUC5 system ; portability between the EJV and EME domains was achieved partl y through retraining these components. One of these components, the Trainable Template Generato...
متن کاملTrainable Sofware Agents
Software agents usually take a passive approach to learning, acquiring information about a task from watching passively what the user does. Examples are the only information that the user and the learner exchange. The induction task left to the agent is only possible with pre-defined learning biases. Determining a priori the language needed to represent the necessary criteria for performing a t...
متن کاملPresenting a method for extracting structured domain-dependent information from Farsi Web pages
Extracting structured information about entities from web texts is an important task in web mining, natural language processing, and information extraction. Information extraction is useful in many applications including search engines, question-answering systems, recommender systems, machine translation, etc. An information extraction system aims to identify the entities from the text and extr...
متن کامل