Automatic text skimming using lexical chains
View Patent ↗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.
1. A method for filtering adjectives from a lexical chain, the method comprising:
receiving, at a processor, the lexical chain comprising an adjective, the lexical chain being a component of an input document;
calculating a non-characteristic-ness score based on the adjective's usage within the input document according to linguistic tests, the non-characteristic-ness score being a function of at least a frequency of the adjective's usage in the input document and a gradability non-characteristic-ness score for the adjective;
testing, by the processor, the adjective to determine if the adjective is at least one of the following: a characteristic adjective and a non-characteristic adjective, wherein testing the adjective comprises comparing the non-characteristic-ness score to a threshold score;
removing, by the processor, the adjective from the lexical chain when the non-characteristic-ness score is above the threshold score; and
leaving, by the processor, the adjective in the lexical chain when the non-characteristic-ness score is below the threshold score.
2. The method of claim 1 , wherein testing the adjective comprises determining if the adjective is a non-characteristic adjective, wherein a non-characteristic adjective can be removed from a collocation without changing the meaning of the collocation.
3. The method of claim 1 , wherein determining if the adjective is at least one of the following: the characteristic adjective and non-characteristic adjective comprises determining a gradability property.
4. The method of claim 1 , wherein determining if the adjective is at least one of the following: the characteristic adjective and non-characteristic adjective comprises determining a nominalization property.
5. The method of claim 1 , wherein the lexical chain comprises a collocation.
6. The method of claim 5 , further comprising determining, by the processor, if the collocation is a technical term.
7. The method of claim 1 , further comprising transmitting the at least one lexical chain to a remote computing device.
8. The method of claim 1 , further comprising broadcasting the at least one lexical chain via a speech synthesizer.
9. The method of claim 1 , wherein testing the adjective occurs without using a stop-list.
10. The method of claim 1 , wherein calculating the non-characteristic-ness score according to linguistic tests comprises:
assigning a point value based on each of the linguistic tests; and
summing the point values for each of the linguistic tests.
11. The method of claim 1 , wherein receiving the adjective comprises receiving multiple documents, each document containing at least one adjective.
12. A method for filtering adjectives before or during formation of a lexical chain, the method comprising:
receiving, at a processor, an adjective;
calculating, by the processor, a non-characteristic-ness score for the adjective, wherein calculating the non-characteristic-ness score comprises assigning a point value to the adjective based on linguistic tests and the adjective's usage within at least one input document, the non-characteristic-ness score being a function of a predication non-characteristic-ness score and a gradability non-characteristic-ness score for the adjective;
testing, by the processor, the adjective to determine if the adjective is at least one of the following: a characteristic adjective and a non-characteristic adjective, wherein testing the adjective comprises comparing the non-characteristic-ness score to a threshold score;
when the adjective is a non-characteristic adjective, forming, by the processor, the lexical chain without using the adjective;
when the adjective is a characteristic adjective, forming, by the processor, the lexical chain, wherein the lexical chain comprises the adjective.
13. The method of claim 12 , wherein testing the adjective occurs without using a stop-list.
14. A method for filtering adjectives from a lexical chain, the method comprising:
receiving, at a processor, the lexical chain comprising an adjective, the lexical chain being a component of an input document;
calculating a non-characteristic-ness score based on the adjective's usage within the input document according to linguistic tests, the non-characteristic-ness score being a function of at least a frequency of the adjective's usage in the input document and a predication non-characteristic-ness score for the adjective;
testing, by the processor, the adjective to determine if the adjective is at least one of the following: a characteristic adjective and a non-characteristic adjective, wherein testing the adjective comprises comparing the non-characteristic-ness score to a threshold score;
removing, by the processor, the adjective from the lexical chain when the non-characteristic-ness score is above the threshold score; and
leaving, by the processor, the adjective in the lexical chain when the non-characteristic-ness score is below the threshold score.
15. The method of claim 14 , wherein the non-characteristic-ness score is further a function of a gradability non-characteristic-ness score for the adjective.