System and methods for quantitative assessment of information in natural language contents

1. A method for quantitatively assessing information in natural language contents, comprising:

receiving an object name by a computer processing system;

receiving, by the computer processing system, a document containing text in a natural language;

identifying a sentence in the document by the computer processing system;

dividing the sentence into a subject and a predicate by the computer processing system, wherein the predicate is defined as the portion of a sentence other than the subject;

retrieving an object-specific data set related to the object name from a computer storage system, wherein the object-specific data set includes a plurality of property names and association-strength values, each property name being associated with an association-strength value;

identifying a first property name in the plurality of property names that matches the subject;

assigning a first association-strength value associated with the first property name to the subject;

identifying a second property name in the plurality of property names that matches the predicate;

assigning a second association-strength value associated with the second property name to the predicate; and

multiplying the first association-strength value and the second association-strength value by the computer processing system to produce a sentence information index as a quantitative measure for the amount of information contained in the sentence about the object name.

2. The method of claim 1 , further comprising:

computing a document information index using the sentence information index, wherein the document information index is a quantitative measure for the amount of information contained in the document about the object name.

3. The method of claim 2 , wherein the step of computing the document information index comprises:

computing sentence information indices of a plurality of sentences in the document, wherein the sentence information indices are specific to the object name; and

computing the document information index as a function of the sentence information indices.

4. The method of claim 3 , wherein the step of computing the document information index comprises:

summing up the sentence information indices to produce the document information index.

5. The method of claim 2 , further comprising:

receiving a query related to the object name by the computer processing system; computing document information indices for a plurality of documents, wherein the document information indices each is a quantitative measure for the amount of information contained in the document about the object name; and

ranking the plurality of documents by their respective document information indices to produce a search result in response to a query.

6. The method of claim 2 , further comprising:

receiving an object name to classify documents by the computer processing system; computing document information indices for a plurality of documents, wherein the document information indices each is a quantitative measure for the amount of information contained in the document about the object name;

determining a threshold value for a document category related to the object name;

selecting one or more documents from the plurality of documents by comparing their respective document information indices to the threshold value; and

assigning the one or more documents to the document category.

7. The method of claim 6 , further comprising:

determining a threshold value for a document category related to the object name;

selecting one or more documents from the plurality of documents if the document information indices of the one or more documents are above or equal to the threshold value;

assigning the one or more documents to the document category.

8. The method of claim 1 , further comprising:

assigning a zero value to the sentence information index if a property name matching the subject or the predicate is not identified in the plurality of property names in the object-specific data set.

9. The method of claim 1 , wherein the subject or the predicate in the sentence comprises a single word, a string of words, a phrase, or an embedded clause.

10. The method of claim 1 , wherein the subject and the predicate in the sentence are determined by the computer processing system using a syntactic parser.

11. The method of claim 1 , wherein the object name includes a word, a list of words, a phrase, a character string, a query, a sub-component of a query, a topic, or the name of a document category.

12. The method of claim 1 , wherein the step of identifying a sentence in the document comprises:

identifying a complex sentence in the document by the computer processing system;

decomposing the complex sentence into one or more simple sentences, wherein a subject and a predicate are identified in each of the simple sentences by the computer processing system;

calculating sentence information indices for the one or more simple sentences; and

computing a sentence information index for the complex sentence using the sentence information indices for the one or more simple sentences.

13. A method for finding text documents relevant to a search query, comprising:

receiving a search query related to an object name by a computer processing system;

receiving, by the computer processing system, a plurality of documents each containing text in a natural language;

retrieving an object-specific data set related to the object name from a computer storage system, wherein the object-specific data set includes a plurality of property names and association-strength values, each property name being associated with an association-strength value;

computing a document information index for each of the plurality of documents, wherein the document information index is a quantitative measure for the amount of information contained in the document about the object name; and

ranking the plurality of documents by their respective document information indices to produce a search result in response to the search query,

wherein the step of computing a document information index comprises:

identifying a sentence in the document by the computer processing system;

dividing the sentence into a subject and a predicate by the computer processing system, wherein the predicate is defined as the portion of a sentence other than the subject;

identifying a first property name in the plurality of property names in the object-specific data set that matches the subject;

assigning a first association-strength value associated with the first property name to the subject;

identifying a second property name in the plurality of property names in the object-specific data set that matches the predicate;

assigning a second association-strength value associated with the second property name to the predicate;

multiplying the first association-strength value and the second association-strength value to produce a sentence information index; and

calculating the document information index using the sentence information index.

14. The method of claim 13 , wherein the document information index is calculated by summing up sentence information indices calculated for sentences identified in the document.

15. A method for classifying text documents in a natural language, comprising:

receiving, by the computer processing system, an object name for document classification;

receiving, by the computer processing system, a plurality of documents each containing text in a natural language;

retrieving an object-specific data set related to the object name from a computer storage system, wherein the object-specific data set includes a plurality of property names and association-strength values, each property name being associated with an association-strength value;

computing a document information index for each of the plurality of documents, wherein the document information index is a quantitative measure for the amount of information contained in the document about the object name;

selecting one or more documents relevant to the object name from the plurality of documents using their respective document information indices; and

assigning the one or more documents to a document category related to the object name,

wherein the step of computing a document information index comprises:

identifying a sentence in the document by the computer processing system;

dividing the sentence into a subject and a predicate by the computer processing system, wherein the predicate is defined as the portion of a sentence other than the subject;

identifying a first property name in the plurality of property names in the object-specific data set that matches the subject;

assigning a first association-strength value associated with the first property name to the subject;

identifying a second property name in the plurality of property names in the object-specific data set that matches the predicate;

assigning a second association-strength value associated with the second property name to the predicate;

multiplying the first association-strength value and the second association-strength value to produce a sentence information index; and

calculating the document information index using the sentence information index.

16. The method of claim 15 , further comprising:

determining a threshold value for a document category related to the object name;

selecting one or more documents from the plurality of documents if the document information indices of the one or more documents are above or equal to the threshold value;

assigning the one or more documents to the document category.

17. A method for quantitatively assessing information in a text content about an object name, comprising:

receiving an object name by a computer processing system;

retrieving an object-specific data set related to the object name from a computer storage system, wherein the object-specific data set includes a plurality of property names and association-strength values, each property name being associated with an association-strength value;

receiving, by the computer processing system, a text content in a natural language;

identifying a sentence in the text content;

identifying a plurality of component strings in the sentence by the computer processing system;

searching for a property name in the plurality of property names that matches at least one of the component strings;

assigning an association-strength value associated with the property name to the one of the component strings;

averaging, by the computer processing system, the association-strength values assigned to the component strings in the sentence to produce a sentence information index; and

calculating an information index for the text content using the sentence information index, wherein the information index is a quantitative measure for the amount of information contained in the text content about the object name.

18. A system for quantitatively assessing information in natural language contents, comprising:

a computer processing system configured to receive an object name and a document containing text in a natural language; and

a computer storage system in communication with the computer processing system and configured to store an object-specific data set related to the object name from wherein the object-specific data set includes a plurality of property names and association-strength values, each property name being associated with an association-strength value,

wherein the computer processing system is configured to identify a sentence in the document, divide the sentence into a subject and a predicate, wherein the predicate is defined as the portion of a sentence other than the subject, identify a first property name in the plurality of property names that matches the subject, assign a first association-strength value associated with the first property name to the subject, identify a second property name in the plurality of property names that matches the predicate, assign a second association-strength value associated with the second property name to the predicate; and multiply the first association-strength value and the second association-strength value to produce a sentence information index as a quantitative measure for the amount of information contained in the sentence about the object name.

19. The system of claim 18 , wherein the computer processing system is further configured to compute a document information index using the sentence information index, wherein the document information index is a quantitative measure for the amount of information contained in the document about the object name.

20. The system of claim 19 , wherein the computer processing system is further configured to sum up the sentence information indices computed for sentences in the document to produce the document information index.