IDENTIFICATION OF SEMANTIC RELATIONSHIPS WITHIN REPORTED SPEECH

• US 20090063426A1
• Filed: 08/29/2008
• Published: 03/05/2009
• Est. Priority Date: 08/31/2007
• Status: Active Grant

• Current Assignee: Zhigu Holdings Limited
• Original Assignee: Powerset (Microsoft Corporation)
• Inventors: VAN DEN BERG, MARTIN HENK, GUREVICH, OLGA, POLANYI, LIVIA, PREVOST, SCOTT A., PELL, BARNEY D., AHN, DAVID, CROUCH, RICHARD S., THIONE, GIOVANNI LORENZO
• Granted Patent: US 8,868,562 B2
• Time in Patent Office: Days
• US Class Current: 1/1
• CPC Class Codes: G06F 16/313 Selection or weighting of terms for indexing
• CPC Class Codes: G06F 16/316 Indexing structures
• CPC Class Codes: G06F 16/3344 using natural language analysis
• CPC Class Codes: G06F 16/35 Clustering; Classification
• CPC Class Codes: G06F 16/93 Document management systems

Abstract

Methods and computer-readable media for associating words or groups of words distilled from content, such as reported speech or an attitude report, of a document to form semantic relationships collectively used to generate a semantic representation of the content are provided. Semantic representations may include elements identified or parsed from a text portion of the content, the elements of which may be associated with other elements that share a semantic relationship, such as an agent, location, or topic relationship. Relationships may also be developed by associating one element that is in relation to, or is about, another element, thereby allowing for rapid and effective comparison of associations found in a semantic representation with associations derived from queries. The semantic relationships may be determined based on semantic information, such as potential meanings and grammatical functions of each element within the text portion of the content.

Claims

1. A computer-implemented method for developing semantic relationships between elements distilled from content of a document to generate a semantic representation of the content, the method comprising:

identifying a text portion of the document;

determining semantic information for a plurality of elements identified in the text portion, the semantic information including one or more of meanings of the identified elements or grammatical functions of the identified elements;

identifying at least one of the identified elements as a reporting act corresponding to a speech report or an attitude report;

based on the determined semantic information for the identified elements, associating the identified elements so that each association of identified elements represents a certain semantic relationship; and

generating a semantic representation that includes the associations of the identified elements.

2. The method of claim 1, wherein the text portion comprises at least one of one or more sentences, a table, a template, or a plurality of data.

3. The method of claim 1, further comprising:

accessing a data store to retrieve at least a portion of the content from the document.

4. The method of claim 1, further comprising:

parsing the text portion of the document to identify the plurality of elements to be included in the semantic representation.

5. The method of claim 1, further comprising:

recognizing one or more entities within the text portion, wherein the one or more entities are recognized by searching a predefined list of words stored in a data store.

6. The method of claim 1, further comprising:

associating with each of the identified elements a plurality of words having a similar meaning.

7. The method of claim 1, wherein associating the identified elements comprises identifying one or more levels of association within the text portion, each of the one or more levels of association including one or more of the identified elements.

8. The method of claim 7, further comprising:

identifying a reporting act for at least one of the one or more levels of association; and

associating a first reporting act with each of a first set of identified elements, wherein the first reporting act is associated with a first level of association.

9. The method of claim 8, further comprising:

associating a second reporting act with each of a second set of identified elements, wherein the second reporting act is associated with a second level of association.

10. The method of claim 8, wherein the first reporting act and each of the first set of identified elements are associated by way of a relational element that describes the association.

11. The method of claim 10, further comprising:

indexing the semantic representation, wherein the semantic representation, including the identified elements and the relational elements, is stored in an index for retrieval, and wherein the index is searchable.

12. The method of claim 11, wherein the index includes pointers from the semantic representation to its associated text portion that is stored in a data store.

13. A computer-implemented method for, in response to receiving a query, creating associations between various terms distilled from the query to generate a proposition, the proposition being used to interrogate semantic representations of content from documents stored in a semantic index to provide relevant search results, the method comprising:

determining semantic information for one or more search terms;

identifying a first reporting act within the query;

based on the determined semantic information for the one or more search terms, determining a semantic relationship between the first reporting act and at least one of the one or more search terms, thereby creating an association by way of a relational element that describes the semantic relationship; and

generating the proposition, the proposition including the association between the first reporting act and the at least one of the one or more search terms.

14. The method of claim 13, further comprising:

parsing the query to determine the one or more search terms therein.

15. The method of claim 13, wherein the semantic information includes one or more of meanings of the identified elements or grammatical functions of the identified elements.

16. The method of claim 13, further comprising:

associating with each of the one or more search terms a plurality of words having a similar meaning to the at least one of the one or more search terms.

17. The method of claim 13, wherein the proposition is a logical representation of a meaning of the query that is used to interrogate semantic relationships contained within semantic representations of content from the documents.

18. The method of claim 13, further comprising:

identifying a second reporting act within the query; and

based on the determined semantic information for the one or more search terms, determining a semantic relationship between the second reporting act and the at least one of the one or more search terms, thereby creating an association by way of a relational element that describes the semantic relationship.

19. The method of claim 13, further comprising:

comparing the proposition against one or more of the semantic representations stored in the semantic index to determine one or more matching pairs.

20. One or more computer-readable media having computer-useable instructions embodied thereon for performing a method of developing semantic relationships between elements distilled from content of a document to generate a semantic representation of the content, further allowing for indexing of the content, the method comprising:

identifying at least a portion of the document to be indexed, the at least a portion of the document being a text portion;

parsing the text portion of the document to identify elements that are to be semantically represented;

accessing a data store to determine potential meanings and grammatical functions of the identified elements;

determining one or more levels of association within the text portion;

identifying a reporting act within the text portion for each of the one or more determined levels of association;

associating a first reporting act with a first set of identified elements, wherein the first reporting act is associated with a first level of association;

associating a second reporting act with a second set of identified elements, wherein the second reporting act is associated with a second level of association; and

generating a semantic representation that includes associations, by way of a relational element that describes the associations, between the first set of identified elements to the first reporting act and the second set of identified elements to the second reporting act.