File Information

File: 05-lr/acl_arc_1_sum/cleansed_text/xml_by_section/abstr/98/p98-2178_abstr.xml

Size: 4,260 bytes

Last Modified: 2025-10-06 13:49:21

<?xml version="1.0" standalone="yes"?>
<Paper uid="P98-2178">
  <Title>JaBot: a multilingual Java-based intelligent agent for Web sites</Title>
  <Section position="1" start_page="0" end_page="1086" type="abstr">
    <SectionTitle>
Abstract
</SectionTitle>
    <Paragraph position="0"> This paper presents a novel type of intelligent agent with a multilingual natural language interface, which retrieves information from within a Web site. This agent, named JaBot after the fact that it is a bot which has been programmed in Java, has been designed and developed by the authors in an attempt to solve common Web site problems related to information retrieval. JaBot runs quickly and efficiently, and rather than running directly on the Web site pages, it is connected to a lexical semantic map. This map is based upon the contents of the Web site in question together with other associated linguistic knowledge.</Paragraph>
    <Paragraph position="1"> Introduction Java was launched by Sun Microsystems in the early '90s as a simple, robust, dynamic, multithreaded, general-purpose, object-oriented, platform independent programming language! Its strengths can be split into four key issues, namely, portability, security, robustness and ease of usage, and distributed operation across the Web (Read et al., 1997). These benefits make Java an ideal programming language for constructing Web-based computational linguistic applications and agents (Ritchey, 1995; Sommers, 1997). Some applications of this type are beginning to appear on the Web, such as the English learning tools developed in Java by the authors as part of the UNED - Profesor Virtual (UPV) research project 1 (Read &amp; B~ircena, in prep.).</Paragraph>
    <Paragraph position="2"> l Although JaBot and the rest of the modules that make up the UPV are fully functional and have been operational for some time now locally on our departmental Web pages, they cannot be accessed yet on the Internet because our Web site is in the f'mal stages of construction.</Paragraph>
    <Paragraph position="3"> Access to the vast amounts of information contained on the Web still highlights some problems, such as that of cataloguing or indexing all that information. The sheer size of the Web and the ever changing nature of its contents means that the process of charting it is closer to mapping a large cavern with only the aid of a small torch than to the construction of a library catalogue.</Paragraph>
    <Paragraph position="4"> Bot or agent technology is playing an increasingly important role in this mapping process, as will be seen next.</Paragraph>
    <Paragraph position="5"> 1 Bots and the Web Bots are distinguished from other commonly used programs in that they act as if they have some degree of intelligence and independence (Thompson, 1998). Born in the '60s, nowadays bots should be viewed as part of the wider move towards distributed object-based systems (Weber, 1997). Instead of having massive programs, the tendency is to use networked computer systems made of a large number of co-operating task-specific components. Some of these components will act when told to; others, bots, will be more autonomous, making the on-line experience more pleasant and productive.</Paragraph>
    <Paragraph position="6"> Internet search engines have a reputation of being unfriendly and unhelpful, despite the fact that some of them offer basic natural language interaction. The problem arises exactly at the point when the user connects to a specific Web site in search of some information that s/he believes to be contained there. If the site is large and there is no search engine, finding a particular item can be very difficult and time consuming, especially over a slow connection. Even if a search engine does exist, the current basis of search technology on the use of 'wild card'-based literal strings means that, unless the user knows a keyword which will be part of the entry s/he wants, the results of the search may well be zero links or a large list of  marginally related references in which the desired link is embedded.</Paragraph>
    <Paragraph position="7"> In order to overcome these problems, the authors have designed and developed a bot which functions within a Web site.</Paragraph>
  </Section>
class="xml-element"></Paper>
Download Original XML