NLP-based systems and methods for providing quotations

• US 10,331,783 B2
• Filed: 10/14/2016
• Issued: 06/25/2019
• Est. Priority Date: 03/30/2010
• Status: Active Grant

• Current Assignee: Fiver LLC
• Original Assignee: Fiver LLC
• Inventors: Liang, Jisheng, Dhillon, Navdeep S., Koperski, Krzysztof
• Primary Examiner(s): Vo, Huyen X
• Application Number:
  US15/294,627
• Publication Number:
  US 20170103060A1
• Time in Patent Office: 984 Days
• Field of Search: 704 1- 10, 704230-257, 704270-275
• CPC Class Codes: G06F 16/3344 using natural language analysis
• CPC Class Codes: G06F 16/93 Document management systems
• CPC Class Codes: G06F 40/205 Parsing
• CPC Class Codes: G06F 40/253 Grammatical analysis; Style critique
• CPC Class Codes: G06F 40/289 Phrasal analysis, e.g. finite state techniques or chunking
• CPC Class Codes: G06F 40/295 Named entity recognition
• CPC Class Codes: G06F 40/40 Processing or translation of natural language natural language analysis G06F40/20; semantic analysis G06F40/30

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.

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.

2. The method of claim 1 wherein extracting the quotation includes determining grammatical roles including subjects, verbs and objects of sentences of the text document.

3. The method of claim 1 wherein extracting the quotation includes detecting a quotation verb by determining whether a verb in a sentence of the text document is one of a predetermined list of quotation verbs.

4. The method of claim 1 wherein the one or more attributes include a type or a facet of each of the one or more entities.

5. The method of claim 1 wherein identifying one or more entities includes recognizing and disambiguating a document reference to an entity, such that the reference is linked to a representation of the entity stored in an entity repository.

6. The method of claim 1 wherein identifying one of the entities as the speaker includes identifying a subject of a sentence in the text document.

7. The method of claim 1 wherein extracting the quotation includes identifying a verb for the quotation by identifying a verb of a sentence.

8. The method of claim 1, comprising 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 are stored as a triple in an inverted index.

9. The method of claim 8 wherein the triple includes at least one of:

a reference to a subject entity;

a facet associated with a subject entity;

subject modifiers;

an action;

an action modifier; and

/or one or more references to object entities and/or facts that are referenced within the quote.

10. The method of claim 1 wherein providing the quotation includes presenting at least one of:

text of the quotation;

an attribution;

a context including text surrounding the quotation;

or document metadata associated with the quotation including title, publication date, and/or author.

11. The method of claim 1 wherein providing the quotation includes ranking the quotation based on one or more factors including:

publication date, number of documents including the quotation, and/or credibility of quotation source.

12. The method of claim 1, wherein the determining of the relationship between the speaker and the remaining one or more entities that are referenced by the quotation includes identifying one or more verbs that relate the speaker to the remaining one or more entities.

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.

14. The computing system of claim 13 wherein the quotation extractor is part of a content recommendation system.

15. The computing system of claim 13, wherein the instructions upon execution by the computer processor cause the computer processor to store 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 as a triple in an inverted index.

16. The computing system of claim 13, wherein the instructions upon execution by the computer processor cause the computer processor to rank the quotation based on one or more factors including:

publication date, number of documents including the quotation, and/or credibility of quotation source.

17. The computing system of claim 13, the instructions upon execution by the computer processor cause the computer processor to determine the relationship between the speaker and the remaining one or more entities by identifying one or more verbs that relate the speaker to the remaining one or more entities.

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.

19. The computer-readable medium of claim 18, wherein the method comprises 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 are stored as a triple in an inverted index.

20. The computer-readable medium of claim 18, wherein the method comprises ranking the quotation based on one or more factors including:

publication date, number of documents including the quotation, and/or credibility of quotation source.

21. The computer-readable medium of claim 18, wherein providing the quotation includes presenting at least one of:

text of the quotation;

an attribution;

a context including text surrounding the quotation;

or document metadata associated with the quotation including title, publication date, and/or author.

22. The computer-readable medium of claim 18, wherein determining the relationship between the speaker and the remaining one or more entities comprises identifying one or more verbs that relate the speaker to the remaining one or more entities.