Concept-Based Retrieval using Controlled Natural Language (1997)
BibTeX
@MISC{Zaïane97concept-basedretrieval,
author = {Osmar R. Zaïane and Andrew Fall and Stephen Rochefort and Veronica Dahl and Paul Tarau},
title = {Concept-Based Retrieval using Controlled Natural Language},
year = {1997}
}
Bookmark
 |
 |
 |
 |
 |
 |
OpenURL
Abstract
We present a method for retrieving concepts from web search queries and from candidate documents on the web, to help determine which of these documents are semantically (rather than simply key-word wise) related to the query. Our method combines hypothetical reasoning, which we use both for natural language analysis and for concept extraction, and domain-oriented taxonomies of concepts to guide the system's reasoning. 1 Introduction Realistic natural language analysis, whether for web or traditional applications, cannot make abstraction of semantics and pragmatics, any more than programming languages can fully make abstraction of their run-time environments. Computer-based discourse understanding (as its human counterpart) is basically a form of model-building. It involves constant constraint-solving to keep, at a given time, only a manageable subset of (intended) models. The task is harder, but similar to that of compilers for programming languages. The experience of being drowned wi...
