File Information
File: 05-lr/acl_arc_1_sum/cleansed_text/xml_by_section/intro/06/w06-1806_intro.xml
Size: 2,076 bytes
Last Modified: 2025-10-06 14:04:06
<?xml version="1.0" standalone="yes"?> <Paper uid="W06-1806"> <Title>Natural Language Understanding using Temporal Action Logic</Title> <Section position="2" start_page="0" end_page="0" type="intro"> <SectionTitle> 1 Introduction </SectionTitle> <Paragraph position="0"> A complex and poorly understood area in computational linguistics is the integration and use of background knowledge to aid parsing, interpretation and understanding of natural language. There is general agreement that background knowledge is needed, e.g. to select between ambiguous interpretations or to provide answers to questions, and that without at least a partial understanding of the world a system can never hope to approach full natural language understanding. As artificial intelligence research moves closer to applications there is an increasing risk that too many natural language projects concentrate on the robust performance that is required in real-world applications and that they, while realizing that background knowledge is important, tend to make its role peripheral instead of a solid base on which to build upon.</Paragraph> <Paragraph position="1"> We describe a natural language understanding system based on a logicist knowledge representation foundation that serves as a research platform for experimentation with the interchange between computational linguistics and knowledge representation and reasoning. The focus is the representational and inferential adequacy of the underlying techniques, which have been selected for generality and extensibility, rather than on immediate applicability or the similarity with human dialogue characteristics. The techniques are brought together in a simple and clear architecture that holds great potential for development and experimentation. A novel integration of natural language technology, knowledge representation technology, and automated reasoning technology in a proof-of-concept question answering system, with the working title NL1, has been implemented and is available as open source1.</Paragraph> </Section> class="xml-element"></Paper>