Enhanced web document summarization using hyperlinks

Text Summarization Techniques: A Brief Survey

“…Then they analyze the candidate pages and select the best sentences containing links to the web page heuristically. Delort et al [54] extended and improved this approach by using an algorithm trying to select a sentence about the same topic that covers as many aspects of the web page as possible.…”

Automatic Summarization

“…This text often provides a descriptive summary of a web page (e.g., "Access to papers published within the last year by members of the NLP group"). Proponents of using context to provide summary sentences argue that a web site includes multimedia, may cover diverse topics, and it may be hard for a summarizer to distinguish good summary content from bad [47]. The earliest work on this approach was carried out to provide snippets for each result from a search engine [2].…”

“…To determine a summary, their system issued a search for a URL, selected all sentences containing a link to that URL and the best sentence was identified using heuristics. Delort et al [47] use a very similar procedure to select context sentences. They extend the older approach through an algorithm that allows selection of a sentence that covers as many aspects of the web page as possible and that is on the same topic.…”

Critical Issues in Content Repurposing for Small Devices

“…Distinctiveness can be measured by classic measure of TF-IDF, which is where K is the number of occurrences of the word in the "document" or text to be summarized, N is a sample of documents, and n is the number of those documents in that sample having the word at least once. Other useful input for text summarization are the headings of pages linked to (Delort, Bouchon-Meunier, & Rifqi, 2003) since neighbor pages provide content clues. Content can also be classified into semantic units by aggregating clues or even by "parsing" the page display.…”