Document retrieval using a substring index

Open Access
Publisher Website
Google Scholar
Abstract
Recent research has suggested the indexing of documents by the substrings that are present in some content rich piece of text from the document; in particular, articles have reported on the analysis of titles. A method is suggested here, based on keywords, that reduces considerably the processing required for substring analysis, that generates some word truncation to group grammatical variants, that avoids the bias created by spaces and noncontent words, and that also maintains acceptable levels of dictionary size and retrieval precision.

This publication has 0 references indexed in Scilit: