System, method, and program for processing text using object coreference technology

1. A computer-implemented method for processing text, comprising:

acquiring text to be processed;

extracting subject words and entity words corresponding to the subject words from the text;

establishing, by a computer, a subject relationship network according to a concerned object, to group the subject words into different subject word groups;

identifying at least two of the extracted entity words that reference a same concerned object based on the different subject word groups; and

generating amendment suggestions according to occurrence positions of the identified entity words that reference the same concerned object in order to insert embedded advertisement to the text.

2. A method according to claim 1 , wherein identifying the entity words comprises:

identifying a group of entity words corresponding to a same subject word group; and

determining whether each entity word in the group of entity words references the same concerned object.

3. A method according to claim 2 , wherein identifying the group of entity words comprises:

identifying an entity word corresponding to each subject word that belongs to the same subject word group.

4. A method according to claim 2 , further comprising:

performing noun extension on the concerned object, and

wherein determining whether each entity word in the group of entity words references the same concerned object comprises:

determining whether each entity word in the group of entity words matches with the extended concerned object.

5. A method according to claim 1 , wherein identifying the entity words comprises:

extracting a comparative conjunctions from the text; and

identifying different entity words that reference different concerned objects according to the comparative conjunctions in the text.

6. A method according to claim 1 , wherein generating amendment suggestions for the identified entity words comprises:

generating amendment suggestions according to occurrence positions of the identified entity words in the text.

7. A method according to claim 1 , wherein generating amendment suggestions for the identified entity words comprises:

generating amendment suggestions according to an emotion analysis result of the identified entity words that reference the same concerned object.

8. A method according to claim 1 , wherein the amendment suggestions comprise at least one of the following:

substituting another word for at least one of the identified entity words;

inserting a same icon for the identified entity words; and

adding a same link for the identified entity words.

9. A method according to claim 1 , further comprising:

receiving a concerned object list containing at least one concerned object therein.

10. A method according to claim 1 , further comprising:

determining at least one concerned object according to an analysis of a grammatical structure of the text.

11. A method according to claim 1 , further comprising:

identifying an associated entity word of the identified entity words; and

processing the associated entity word.

12. A method according to claim 1 , further comprising:

extracting a sentence or a phrase where at least one of the identified entity words resides.

13. A method according to claim 12 , further comprising:

performing an emotion classification on the extracted sentence or phrase.

14. A text processing system, comprising:

a text acquiring means configured to acquire text to be processed;

a word extracting means configured to extract subject words and entity words corresponding to the subject words from the text;

a subject word grouping means configured according to a subject relationship network based on a concerned object, to group the subject words into different subject word groups;

an entity word determining means configured to identify at least two of the extracted entity words that references a same concerned object based on the different subject word groups; and

a processing policy generating means configured to generate amendment suggestions according to occurrence positions of the identified entity words that reference the same concerned object in order to insert embedded advertisement to the text.

15. A system according to claim 14 , wherein the entity word determining means is further configured to:

identify a group of entity words corresponding to a same subject word group;

determine whether each entity word in the group of entity words references the same concerned object;

extract a comparative conjunctions from the text; and

identify different entity words that reference a different concerned object according to the comparative conjunctions in the text.

16. A system according to claim 15 , further comprising:

an extending means configured to perform noun extension on the concerned object.

17. A system according to claim 14 , wherein the processing policy generating means is further configured to:

extract a sentence or a phrase where at least one of the identified entity words resides.

18. An article of manufacture tangibly embodying computer readable instructions which, when implemented, cause a computer to carry out the steps of a text processing method, comprising:

acquiring text to be processed;

extracting subject words and entity words corresponding to the subject words from the text;

establishing a subject relationship network according to a concerned object, to group the subject words into different subject word groups;

identifying at least two of the extracted entity words that reference a same concerned object based on the different subject word groups; and

generating amendment suggestions according to occurrence positions of the identified entity words that reference the same concerned object in order to insert embedded advertisement to the text.