NLP-based systems and methods for providing quotations
First Claim
1. A method in a content recommendation system in a computer system having a computer processor for automatically generating indexed article websites with procedurally generated headlines, the method comprising:
- extracting, by the computer processor, a quotation from a text document indexed by the computer system for access by a search engine and hosted by a web server;
identifying, by the computer processor, one or more entities that are referenced by the quotation, wherein identifying the one or more entities includes assigning one or more attributes to each of the one or more entities, and disambiguating and identifying one of the entities as a speaker of the quotation;
indexing, by the computer processor, the quotation within the search engine based on each of the one or more entities, wherein indexing the quotation includes;
determining, by the computer processor, a relationship between the speaker and the remaining one or more entities that are referenced by the quotation; and
storing the one or more attributes of the speaker, the relationship between the speaker and the remaining one or more entities, and the one or more attributes of each of the remaining one or more entities in an index data structure; and
providing, by the computer processor, the quotation via a hyperlink responsive to a search request upon determining that an input parameter included in the search quest matches an attribute of the speaker, the relationship, or an attribute of any of the remaining one or more entities of the quotation stored in the index data structure, wherein the hyperlink is constructed based on information about the speaker.
3 Assignments
0 Petitions
Accused Products
Abstract
Techniques for providing quotations obtained from text documents using natural language processing techniques are described. Some embodiments provide a content recommendation system (“CRS”) configured to provide quotations by extracting quotations from a corpus text documents, and providing access to the extracted quotations in response to search requests received from users. The CRS may extract quotations by using natural language processing-based techniques to identify one or more entities, such as people, places, objects, concepts, or the like, that are referenced by the extracted quotations. The CRS may then store the extracted quotations along with identified entities, such as quotation speakers and subjects, for later access via search requests.
-
Citations
22 Claims
-
1. A method in a content recommendation system in a computer system having a computer processor for automatically generating indexed article websites with procedurally generated headlines, the method comprising:
-
extracting, by the computer processor, a quotation from a text document indexed by the computer system for access by a search engine and hosted by a web server; identifying, by the computer processor, one or more entities that are referenced by the quotation, wherein identifying the one or more entities includes assigning one or more attributes to each of the one or more entities, and disambiguating and identifying one of the entities as a speaker of the quotation; indexing, by the computer processor, the quotation within the search engine based on each of the one or more entities, wherein indexing the quotation includes; determining, by the computer processor, a relationship between the speaker and the remaining one or more entities that are referenced by the quotation; and storing the one or more attributes of the speaker, the relationship between the speaker and the remaining one or more entities, and the one or more attributes of each of the remaining one or more entities in an index data structure; and providing, by the computer processor, the quotation via a hyperlink responsive to a search request upon determining that an input parameter included in the search quest matches an attribute of the speaker, the relationship, or an attribute of any of the remaining one or more entities of the quotation stored in the index data structure, wherein the hyperlink is constructed based on information about the speaker. - View Dependent Claims (2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12)
-
-
13. A computing system configured to recommend content for automatically generating indexed article websites with procedurally generated headlines, comprising:
-
a memory having instructions stored thereon; and a computer processor; the instructions upon execution by the computer processor causing the computer processor to; extract a quotation from a text document for access by a search engine and hosted by a web server; identify one or more entities that are referenced by the quotation, wherein identifying the one or more entities includes assigning one or more attributes to each of the one or more entities, and disambiguating and identifying one of the entities as a speaker of the quotation; index the quotation within the search engine based on each of the one or more entities by; determining a relationship between the speaker and the remaining one or more entities that are referenced by the quotations; and storing the one or more attributes of the speaker, the relationship, and the one or more attributes of each of the remaining one or more entities in an index data structure; and provide the quotation via a hyperlink in response to a search request upon determining that an input parameter included in the search request matches an attribute of the speaker or an attribute of any of the remaining one or more entities of the quotation stored in the index data structure, wherein the hyperlink is constructed based on information about the speaker. - View Dependent Claims (14, 15, 16, 17)
-
-
18. A non-transitory computer-readable medium storing instructions that, when executed by a computer processor, cause a computing system to automatically recommend content for automatically generating indexed article websites with procedurally generated headlines, by performing a method comprising:
-
extracting a quotation from a text document for access by a search engine and hosted by a web server; identifying one or more entities that are referenced by the quotation, wherein identifying the one or more entities includes assigning one or more attributes to each of the one or more entities, and disambiguating and identifying one of the entities as a speaker of the quotation; indexing the quotation within the search engine based on each of the one or more entities, wherein indexing the quotation includes; determining a relationship between the speaker and the remaining one or more entities that are referenced by the quotation; and storing the one or more attributes of the speaker, the relationship, and the one or more attributes of each of the remaining one or more entities in an index data structure; and providing the quotation in response a search request upon determining that an input parameter included in the search quest matches an attribute of the speaker or an attribute of any of the remaining one or more entities of the quotation stored in the index data structure, wherein the hyperlink is constructed based on information about the speaker. - View Dependent Claims (19, 20, 21, 22)
-
Specification