Automatic Text Skimming Using Lexical Chains

Abstract

Automatic text skimming using lexical chains may be provided. First, at least one lexical chain may be created from an electronic document. Next, a list of positions within the electronic document may be created. The positions may include where at least one concept represented by one of the at least one lexical chain is mentioned. In addition, a list of the position where the at least one concept is mentioned may be assembled. A selection of at least one concept may be received from the list.

The following is claimed: 
     
         1 . A method for constructing a search index, the method comprising:
 receiving at least one characteristic multiword expression from at least one document to be indexed;   storing a location of at least one sentence in the document that references the at least one characteristic multiword expression;   computing a contribution score of the at least one characteristic multiword expression to a representation of the document, wherein a characteristic multiword expression representing a key concept in the document receives a higher contribution score than a characteristic multiword expression representing a minor point in the document; and   creating a characteristic multiword expression list of the at least one characteristic multiword expression.   
     
     
         2 . The method of  claim 1 , further comprising recording at least one word used in the at least one characteristic multiword expression in a word list. 
     
     
         3 . The method of  claim 2 , further comprising computing a contribution score for at least one word to the at least one characteristic multiword expression, wherein a word representing a key concept in the characteristic multiword expression receives a higher contribution score than the word representing a minor point in the characteristic multiword expression. 
     
     
         4 . The method of  claim 3 , wherein the characteristic multiword expression list comprises the contribution score for at least one word to the at least one characteristic multiword expression. 
     
     
         5 . The method of  claim 3 , further comprising creating a document index, the document index comprises a list of all words used in the at least one characteristic multiword expression for the at least one document in the index. 
     
     
         6 . The method of  claim 1 , wherein a characteristic multiword expression representing a key concept in the document receives a higher contribution score than a characteristic multiword expression representing a minor point in the document comprises determining a frequency of the characteristic multiword expression in the document. 
     
     
         7 . The method of  claim 1 , wherein a characteristic multiword expression representing a key concept in the document receives a higher contribution score than a characteristic multiword expression representing a minor point in the document comprises determining whether the characteristic multiword expression is contained in a lexical chain in the document. 
     
     
         8 . The method of  claim 1 , wherein the characteristic multiword expression list comprises at least one of the following:
 a location list of the location of at least one sentence in the document that references the at least one characteristic multiword expression, denoted by at least one of the following: a sentence number and a page number,   a page list of all page numbers in the document that correspond to pages containing the at least one sentence in the document that references the at least one characteristic multiword expression, and   the contribution score of the at least one characteristic multiword expression to a representation of the document.   
     
     
         9 . The method of  claim 1 , further comprising computing a contribution score of the at least one characteristic multiword expression to a sentence, wherein a characteristic multiword expression representing a key concept in the sentence receives a higher contribution score than a characteristic multiword expression representing a minor point in the sentence. 
     
     
         10 . The method of  claim 9 , wherein a characteristic multiword expression representing a key concept in the sentence receives a higher contribution score than a characteristic multiword expression representing a minor point in the sentence comprises determining whether the characteristic multiword expression is contained in a lexical chain in the sentence. 
     
     
         11 . The method of  claim 1 , further comprising transmitting the at least one characteristic multiword expression to a remote computing device. 
     
     
         12 . The method of  claim 1 , further comprising broadcasting the at least one characteristic multiword expression via a speech synthesizer.