2008 | OriginalPaper | Chapter
Language Model Based Temporal Information Indexing
Author : Andrzej Bassara
Published in: Business Information Systems
Publisher: Springer Berlin Heidelberg
Activate our intelligent search to find suitable subject content or patents.
Select sections of text to find matching patents with Artificial Intelligence. powered by
Select sections of text to find additional relevant content using AI-assisted search. powered by
Temporal information indexing is a specialization of general information indexing, which aims at creation of: clear, concise, correct and comprehensive representations of document important features, with respect to possible information needs. In case of temporal indexing, temporal features represent so called, time horizon or valid time of information, i.e. time period, to which information presented in a document relates.
Approaches to temporal information indexing are based mainly on temporal expressions extracted from document contents. This method, although satisfactory for many applications, is very limited. Temporal expressions are only one of many means of relating information to time used in written language.
In this paper, the possibility of temporal information indexing based on other, more broad and frequent document temporal feature is evaluated. Soundness and effectiveness of temporal indexing based on document syntactic features is presented.