METHOD, APPARATUS, AND COMPUTER-READABLE MEDIUM FOR GENERATING HEADLINES

• US 20140351266A1
• Filed: 05/21/2014
• Published: 11/27/2014
• Est. Priority Date: 05/21/2013
• Status: Abandoned Application

• Current Assignee: Callisto Publishing LLC
• Original Assignee: Temnos, Inc. (Zeta Interactive Corporation)
• Inventors: Musgrove, Timothy A.
• Application Number:
  US14/284,370
• Publication Number:
  US 20140351266A1
• Time in Patent Office: Days
• US Class Current: 707/748
• CPC Class Codes: G06F 16/24578 using ranking
• CPC Class Codes: G06F 16/345 Summarisation for human users

Abstract

An apparatus, computer-readable medium, and computer-implemented method for generating a headline includes identifying a content section of a document, selecting a sentence in the content section based at least in part on a determination that the sentence exhibits one or more characteristics correlated with headline performance, extracting a portion of the sentence based at least in part on a trigger attribute within the sentence, and generating the headline based at least in part on the portion of the sentence.

Claims

1. A method executed by one or more computing devices for generating a headline, the method comprising:

identifying, by at least one of the one or more computing devices, a content section of a document;

selecting, by at least one of the one or more computing devices, a sentence in the content section based at least in part on a determination that the sentence exhibits one or more characteristics correlated with headline performance;

extracting, by at least one of the one or more computing devices, a portion of the sentence based at least in part on a trigger attribute within the sentence; and

generating, by at least one of the one or more computing device, the headline based at least in part on the portion of the sentence.

2. The method of claim 1, wherein the one or more characteristics correlated with headline performance comprise at least one of semantic characteristics and grammatical characteristics.

3. The method of claim 1, wherein headline performance is measured by a performance indicator.

4. The method of claim 3, wherein the performance indicator comprises at least one of click-through rate, conversion to action, time spent on site, and download rate.

5. The method of claim 1, wherein selecting a sentence comprises:

scoring a plurality of sentences in the content section based at least in part on the one or more characteristics correlated with headline performance, wherein each sentence is scored based on the occurrence of the one or more characteristics within that sentence; and

selecting the sentence in the plurality of sentences based at least in part on the score of the sentence.

6. The method of claim 1, wherein extracting a portion of the sentence comprises:

identifying the trigger attribute within the sentence;

identifying at least one of a subject of the trigger attribute and an object of the trigger attribute; and

extracting the portion of the sentence based at least in part on the location of the trigger attribute and the location of at least one of the subject of the trigger attribute and the object of the trigger attribute.

7. The method of claim 6, wherein at least one of the subject of the trigger attribute and the object of the trigger attribute are identified based on rules relating to at least one of syntax, parts-of-speech, grammar, and punctuation.

8. The method of claim 6, wherein the trigger attribute comprises at least one of a verb and an adjective.

9. The method of claim 1, wherein generating the headline comprises:

removing one or more words from the portion of the sentence.

10. The method of claim 9, wherein the one or more words comprise at least one of an adjective, an adverb, and a prepositional phrase.

11. The method of claim 1, wherein generating the headline comprises:

converting a verb in the portion of the sentence into either an active tense or a gerund.

12. An apparatus for generating a headline comprising:

one or more processors; and

one or more memories operatively coupled to at least one of the one or more processors and having instructions stored thereon that, when executed by at least one of the one or more processors, cause at least one of the one or more processors to;

identify a content section of a document;

select a sentence in the content section based at least in part on a determination that the sentence exhibits one or more characteristics correlated with headline performance;

extract a portion of the sentence based at least in part on a trigger attribute within the sentence; and

generate the headline based at least in part on the portion of the sentence.

13. The apparatus of claim 12, wherein the one or more characteristics correlated with headline performance comprise at least one of semantic characteristics and grammatical characteristics.

14. The apparatus of claim 12, wherein headline performance is measured by a performance indicator.

15. The apparatus of claim 14, wherein the performance indicator comprises at least one of click-through rate, conversion to action, time spent on site, and download rate.

16. The apparatus of claim 12, wherein the instructions that, when executed by at least one of the one or more processors, cause at least one of the one or more processors to select a sentence further cause at least one of the one or more processors to:

score a plurality of sentences in the content section based at least in part on the one or more characteristics correlated with headline performance, wherein each sentence is scored based on the occurrence of the one or more characteristics within that sentence; and

select the sentence in the plurality of sentences based at least in part on the score of the sentence.

17. The apparatus of claim 12, wherein the instructions that, when executed by at least one of the one or more processors, cause at least one of the one or more processors to extract a portion of the sentence further cause at least one of the one or more processors to:

identify the trigger attribute within the sentence;

identify at least one of a subject of the trigger attribute and an object of the trigger attribute; and

extract the portion of the sentence based at least in part on the location of the trigger attribute and the location of at least one of the subject of the trigger attribute and the object of the trigger attribute.

18. The apparatus of claim 17, wherein at least one of the subject of the trigger attribute and the object of the trigger attribute are identified based on rules relating to at least one of syntax, parts-of-speech, grammar, and punctuation.

19. The apparatus of claim 17, wherein the trigger attribute comprises at least one of a verb and an adjective.

20. The apparatus of claim 12, wherein the instructions that, when executed by at least one of the one or more processors, cause at least one of the one or more processors to generate the headline further cause at least one of the one or more processors to remove one or more words from the portion of the sentence.

21. The apparatus of claim 20, wherein the one or more words comprise at least one of an adjective, an adverb, and a prepositional phrase.

22. The apparatus of claim 12, wherein the instructions that, when executed by at least one of the one or more processors, cause at least one of the one or more processors to generate the headline further cause at least one of the one or more processors to convert a verb in the portion of the sentence into either an active tense or a gerund.

23. At least one non-transitory computer-readable medium storing computer-readable instructions that, when executed by one or more computing devices, cause at least one of the one or more computing devices to:

identify a content section of a document;

select a sentence in the content section based at least in part on a determination that the sentence exhibits one or more characteristics correlated with headline performance;

extract a portion of the sentence based at least in part on a trigger attribute within the sentence; and

generate a headline based at least in part on the portion of the sentence.

24. The at least one non-transitory computer-readable medium of claim 23, wherein the one or more characteristics correlated with headline performance comprise at least one of semantic characteristics and grammatical characteristics.

25. The at least one non-transitory computer-readable medium of claim 23, wherein headline performance is measured by a performance indicator.

26. The at least one non-transitory computer-readable medium of claim 25, wherein the performance indicator comprises at least one of click-through rate, conversion to action, time spent on site, and download rate.

27. The at least one non-transitory computer-readable medium of claim 23, wherein the instructions that, when executed by at least one of the one or more computing devices, cause at least one of the one or more computing devices to select a sentence further cause at least one of the one or more computing devices to:

score a plurality of sentences in the content section based at least in part on the one or more characteristics correlated with headline performance, wherein each sentence is scored based on the occurrence of the one or more characteristics within that sentence; and

select the sentence in the plurality of sentences based at least in part on the score of the sentence.

28. The at least one non-transitory computer-readable medium of claim 23, wherein the instructions that, when executed by at least one of the one or more computing devices, cause at least one of the one or more computing devices to extract a portion of the sentence further cause at least one of the one or more computing devices to:

identify the trigger attribute within the sentence;

identify at least one of a subject of the trigger attribute and an object of the trigger attribute; and

extract the portion of the sentence based at least in part on the location of the trigger attribute and the location of at least one of the subject of the trigger attribute and the object of the trigger attribute.

29. The at least one non-transitory computer-readable medium of claim 28, wherein at least one of the subject of the trigger attribute and the object of the trigger attribute are identified based on rules relating to at least one of syntax, parts-of-speech, grammar, and punctuation.

30. The at least one non-transitory computer-readable medium of claim 28, wherein the trigger attribute comprises at least one of a verb and an adjective.

31. The at least one non-transitory computer-readable medium of claim 23, wherein the instructions that, when executed by at least one of the one or more computing devices, cause at least one of the one or more computing devices to generate the headline further cause at least one of the one or more computing devices to remove one or more words from the portion of the sentence.

32. The at least one non-transitory computer-readable medium of claim 31, wherein the one or more words comprise at least one of an adjective, an adverb, and a prepositional phrase.

33. The at least one non-transitory computer-readable medium of claim 23, wherein the instructions that, when executed by at least one of the one or more computing devices, cause at least one of the one or more computing devices to generate the headline further cause at least one of the one or more computing devices to convert a verb in the portion of the sentence into either an active tense or a gerund.