Quick Summary - Archive ouverte HAL Access content directly
Preprints, Working Papers, ... Year :

Quick Summary

(1)
1
Robert Wahlstedt
  • Function : Author
  • PersonId : 924421

Abstract

Quick Summary is an innovate implementation of an automatic document summarizer that inputs a document in the English language and evaluates each sentence. The scanner or evaluator determines criteria based on its grammatical structure and place in the paragraph. The program then asks the user to specify the number of sentences the person wishes to highlight. For example should the user ask to have three of the most important sentences, it would highlight the first and most important sentence in green. Commonly this is the sentence containing the conclusion. Then Quick Summary finds the second most important sentence usually called a satellite and highlights it in yellow. This is usually the topic sentence. Then the program finds the third most important sentence and highlights it in red. The implementations of this technology are useful in a society of information overload when a person typically receives 42 emails a day (Microsoft). Another implication is meeting summary information from video for peace officer records and sports broadcasters. The paper also is a candid look at difficulty that machine learning has in textural translating. However, it speaks on how to overcome the obstacles that historically prevented progress. This research is different from other research attempts because it takes into account heuristics in the paragraph and treats the document instead of having a list of disjointed sentences it also each sentence contributing meaning to other sentences until it achieves a pivotal point in document. Previous methods of a document summary generator included reducing redundant words or junction words until it develops a nuclear core. This paper proposes mathematical meta-data criteria that justify the place of importance of a sentence. Just as tools for the study of relational symmetry in bio-informatics, this tool seeks to classify words with greater clarity. "Survey Finds Workers Average Only Three Productive Days per Week." Microsoft News Center. Microsoft. Web. 31 Mar. 2012.
Fichier principal
Vignette du fichier
QuickSummary.pdf (137.57 Ko) Télécharger le fichier
Origin : Files produced by the author(s)
Loading...

Dates and versions

hal-00691651 , version 1 (26-04-2012)
hal-00691651 , version 2 (06-06-2012)

Identifiers

  • HAL Id : hal-00691651 , version 2

Cite

Robert Wahlstedt. Quick Summary. 2012. ⟨hal-00691651v2⟩

Collections

TICE TDS-MACS
344 View
418 Download

Share

Gmail Facebook Twitter LinkedIn More