Google Inc.

Jonathan T Betz

Andrew William Hogue

Shubin Zhao

Farhan Shamsi

Jeffrey C Reynar

Krzysztof Czuba

Robert Joseph Siemborski

Vivek Menezes

Tom Ritchford

Systems and methods for normalizing entities via name normalization are disclosed. In some implementations, a computer-implemented method of identifying duplicate objects in a plurality of objects is provided. Each object in the plurality of objects is associated with one or more facts, and each of the one or more facts having a value. The method includes: using a computer processor to perform: associating facts extracted from web documents with a plurality of objects; and for each of the plurality of objects, normalizing the value of a name fact, the name fact being among one or more facts associated with the object; processing the plurality of objects in accordance with the normalized value of the name facts of the plurality of objects. In some implementations, normalizing the value of the name fact is optionally carried out by applying a group of normalization rules to the value of the name fact.

Entity normalization via name normalization

A system may receive a search query. The system may further provide a list of first documents relating to the search query in a first area of a user interface and provide additional information that has been retrieved from the first documents in a second, different area of the user interface. The additional information includes an attribute name and an associated attribute value.

Supplementing search results with information of interest

A system and method for extracting facts from documents. A fact is extracted from a first document. The attribute and value of the fact extracted from the first document are used as a seed attribute-value pair. A second document containing the seed attribute-value pair is analyzed to determine a contextual pattern used in the second document. The contextual pattern is used to extract other attribute-value pairs from the second document. The extracted attributes and values are stored as facts.

Unsupervised extraction of facts

A system and method for corroborating a set of facts. If the anchor text of the references to a document matches the name of a set of facts, the referenced document is used to corroborate the set of facts. By analyzing the anchor text of the references to the document, the system is capable of determining if a document is relevant to the set of facts. These documents can then be used to corroborate or refute the facts, thereby improving their overall quality.

Anchor text summarization for corroboration

Systems and methods for automatic object reference identification and linking in a browseable fact repository database are provided. In some implementations, a method includes, identifying a set of values from a plurality of facts associated with an entity. The plurality of facts are stored in a fact repository, and a respective fact includes: an attribute and a corresponding value. The method further includes, responsive to a search for a first value included in a first fact in the plurality of facts: identifying a second fact associated with the entity; and causing to be displayed to a user: a link associated with the second fact, and information representing a confidence value associated with the second fact. The link, when selected, invokes a search of the fact repository in accordance with one or more search parameters, which include a value corresponding to an attribute included in the second fact.

Automatic object reference identification and linking in a browseable fact repository

Methods and systems for maintaining the internal consistency of a fact repository are described. Accessed objects are checked for attribute-value pairs that have links to other objects. For any link to an object, the name of the linked-to object is inserted into the attribute-value pair having the link. The accessed objects are filtered to remove attribute-value pairs meeting predefined criteria, possibly resulting in null objects. Links to null objects are identified and removed.

System for ensuring the internal consistency of a fact repository

A system may receive a search query. The system may further provide a list of first documents relating to the search query in a first area of a user interface and provide additional information that has been retrieved from one or more of the first documents in a second area of the user interface.

A repository contains objects representing entities. The objects also include facts about the represented entities. The facts are derived from source documents. A synonymous name of an object is determined by identifying a source document from which one or more facts of the entity represented by the object were derived, identifying a plurality of linking documents that link to the source document through hyperlinks, each hyperlink having an anchor text, processing the anchor texts in the plurality of linking documents to generate a collection of synonym candidates for the entity represented by the object, and selecting a synonymous name for the entity represented by the object from the collection of synonym candidates.

Learning synonymous object names from anchor texts

A method and system for identifying a subject of a document and facts included within are described. A source document that includes facts and linking documents that include hyperlinks to the source document are identified. The anchor texts of the hyperlinks are identified and candidate labels are generated based on the anchor texts. One of the candidate labels is selected as the unifying subject of the facts. An information set, distinct from the source document, is stored in a facts database, wherein the stored information set includes the unifying subject, and source document information associating the source document with the information set.

Identifying the unifying subject of a set of facts

A system and method identifying duplicate objects from a plurality of objects. The system and method normalizes name values of objects, groups objects into buckets based at least in part on the normalized name values, matches objects within the same bucket based on a selected matcher, and identifies the matching objects as duplicate objects.

Links between facts associated with objects are automatically created and maintained in a fact repository. Names of objects are automatically identified in the facts, and collected into a list of names. The facts are then processed to identifying such names in the facts. Identified names are used as anchor text for search links. A search link includes a search query for a service engine which search the fact repository for facts associated with objects having the same name.

A method and system for corroborating facts extracted as attribute-value pairs from multiple sources. Facts associated with a common subject are identified and extracted from multiple sources. From the extracted facts, attributes satisfying a first corroboration requirement are identified. Attribute-value pairs satisfying a second corroboration requirement and having any of the identified attributes that satisfy the first corroboration requirement are identified. Predefined actions may be performed with respect to the identified attribute-value pairs and/or with respect to their status in a fact database.

Growing community of inventors

Summit, NJ, United States of America

Jonathan T Betz