Automatic text skimming using lexical chains

• US 10,146,767 B2
• Filed: 01/28/2014
• Issued: 12/04/2018
• Est. Priority Date: 08/16/2007
• Status: Active Grant

• Current Assignee: Skimcast Holdings, LLC
• Original Assignee: Skimcast Holdings, LLC
• Inventors: Hollingsworth, William A.
• Primary Examiner(s): Saint Cyr, Leonard
• Application Number:
  US14/165,717
• Publication Number:
  US 20140236576A1
• Time in Patent Office: 1,771 Days
• Field of Search: 704 7- 10
• CPC Class Codes: G06F 16/31 Indexing; Data structures therefor; Storage structures
• CPC Class Codes: G06F 40/284 Lexical analysis, e.g. tokenisation or collocates
• CPC Class Codes: G06F 40/30 Semantic analysis

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.

Claims

1. A method for generating characteristic lexical chain, and for synthesizing the update of a lexical chain, the method comprising:

receiving a string of text;

generating at least one lexical chain from the string of text, wherein the at least one lexical chain comprises at least one noun and at least one adjective;

generating at least one of the following;

a gradability score and a predication score for the at least one adjective;

determining whether the at least one adjective is one of the following;

characteristic and non-characteristic, based on, at least in part, at least one of the following;

the gradability score and the predication score;

updating the at least one lexical chain by removing a non-characteristic adjective from the at least one lexical chain when the non-characteristic adjective appears before at least one of;

a characteristic adjective and a noun; and

providing the updated at least one lexical chain via a computing device capable of at least one of the following;

audibly broadcasting synthesized speech associated with the updated at least one lexical chain, and transmitting over a network data to a user device for at least one of the following;

audible broadcast of the synthesized speech and the visual display of text.

2. The method of claim 1, wherein removing the non-characteristic adjective from the lexical chain comprises determining whether the adjective can be removed from a collocation without adding ambiguity to the collocation.

3. The method of claim 1, wherein removing the non-characteristic adjective from the lexical chain comprises determining a conjunction property for each adjective conjunction.

4. The method of claim 1, wherein removing the non-characteristic adjective from the lexical chain comprises determining a nominalization property.

5. The method of claim 1, further comprising leaving the non-characteristic adjective in the at least one lexical chain when the non-characteristic adjective appears after a characteristic adjective.

6. The method of claim 1, wherein the at least one lexical chain comprises a multi-word expression.

7. The method of claim 6, further comprising determining if the multi-word expression is a technical term.

8. The method of claim 1, further comprising transmitting the at least one lexical chain to a remote computing device.

9. The method of claim 1, further comprising broadcasting the at least one lexical chain via a speech synthesizer.

10. A method for generating characteristic multiword expressions and for synthesizing the update of a multiword expression the method comprising:

receiving a string of text;

generating a multiword expression from the string of text, wherein the multiword expression comprises at least one noun and at least one adjective;

determining whether the at least one adjective wherein the determining includes calculating a measure of non-characteristic-ness;

generating a gradability score and a predication score for the at least one adjective;

determining the at least one adjective'"'"'s initial non-characteristic-ness based on at least a combination of the gradability score and the predication test score;

performing a conjunction test based on at least a combination of the gradability score and the predication test score for the at least one adjective;

determining the at least one adjective'"'"'s final non-characteristic-ness based on, at least in part, the at least one adjective'"'"'s initial non-characteristic-ness and the results of the conjunction test;

updating the multiword expression by removing the at least one adjective determined finally to be non-characteristic when the at least one adjective appears before at least one of;

a characteristic adjective, and a noun; and

providing the updated multiword expression via a computing device capable of at least one of the following;

audibly broadcasting synthesized speech associated with the updated multiword expression, and transmitting over a network data to a user device for at least one of the following;

audible broadcast of the synthesized speech and the visual display of text.