Abstract:
Methods and apparatus are disclosed for resolving multiple interpretations of an ambiguous temporal term of a resource to a subset of the multiple interpretations. In some implementations, a group of one or more messages is identified, an ambiguous temporal term of the messages determined, additional content of the messages determined, and multiple interpretations of the ambiguous temporal term resolved to a subset based on the additional content.
Abstract:
Methods and apparatus for populating a contact entry of a user based on information obtained from one or more sources that are external to the contact entry. Some implementations are directed generally to analyzing text of a document associated with the user to identify contact information in the document. In some versions of those implementations, an affinity measure associated with the document may be determined that is indicative of an amount of interest of the user in the document and a contact entry may be populated with one or more aspects of the contact information based on the affinity measure satisfying a threshold.
Abstract:
Systems and methods for annotating electronic messages are disclosed. In some implementations, a method includes, at a computing device, analyzing content of a first electronic message against a set of annotation rules; and in accordance with the analyzing: identifying a search term not included in the content of the first electronic message as associated with the first electronic message. In some implementations, the first set of annotation rules includes one of: a content based annotation, a syntax based annotation rule, and a hybrid annotation rule. In some implementations, the content of the electronic message includes one of: a text item, an audio item, an image item, and a video item.
Abstract:
Methods, systems, and computer-readable media are provided for identifying social connections. In some implementations, the occurrence of a first reference to a first person and a second reference to a second person is identified in unstructured data. A relationship metric is calculated between the first reference and the second reference, wherein the relationship metric is based at least in part on the co-occurrence of the first reference and the second reference. The existence of a potential connection between the first reference and the second reference is determined based at least in part on the relationship metric. A recommendation is provided to at least one of the first person and the second person to acknowledge the potential connection as an actual connection. Input is received from at least one of the first person and the second person confirming the potential connection as an actual connection.
Abstract:
Methods and apparatus are disclosed for resolving multiple interpretations of an ambiguous temporal term of a resource to a subset of the multiple interpretations. In some implementations, a group of one or more messages is identified, an ambiguous temporal term of the messages determined, additional content of the messages determined, and multiple interpretations of the ambiguous temporal term resolved to a subset based on the additional content.
Abstract:
Methods, apparatus and computer-readable media (transitory and non-transitory) are disclosed for analyzing a communication to or from a user to identify an event assumption and/or determine a likelihood that the communication is event-related. In various implementations, an accuracy of the event assumption, as well as an accuracy of the determined likelihood, may be assessed based on one or more scheduling signals, such as user-creation of a corresponding calendar entry. In various implementations, a machine learning classifier may be trained based at least in part on one or both accuracies.
Abstract:
Computer-implemented techniques for automatic identification and use of alternate user contact information can include identifying, at a server having one or more processors, a set of patterns from training electronic messages, each pattern indicating a pattern of contact information context. The techniques can include storing and utilizing, at the server, the set of patterns to obtain a set of alternate contact information for a target user. In response to a use of a specific alternate contact information for the target user by a source user at a computing device, the techniques can include providing, from the server to the computing device, a suggestion for the source user. Examples of the suggestion may include a virtual address for an electronic message or at a social network, a physical address for navigation, and a telephone number for calling or incoming caller identification.
Abstract:
Methods and apparatus for populating a contact entry of a user based on information obtained from one or more sources that are external to the contact entry. Some implementations are directed generally to analyzing text of a document associated with the user to identify contact information in the document. In some versions of those implementations, an affinity measure associated with the document may be determined that is indicative of an amount of interest of the user in the document and a contact entry may be populated with one or more aspects of the contact information based on the affinity measure satisfying a threshold.
Abstract:
Methods and apparatus for populating a contact entry of a user based on information obtained from one or more sources that are external to the contact entry. Some implementations are directed generally to analyzing text of a document associated with the user to identify contact information in the document. In some versions of those implementations, an affinity measure associated with the document may be determined that is indicative of an amount of interest of the user in the document and a contact entry may be populated with one or more aspects of the contact information based on the affinity measure satisfying a threshold.
Abstract:
Computer-implemented techniques for automatic identification and use of alternate user contact information can include identifying, at a server having one or more processors, a set of patterns from training electronic messages, each pattern indicating a pattern of contact information context. The techniques can include storing and utilizing, at the server, the set of patterns to obtain a set of alternate contact information for a target user. In response to a use of a specific alternate contact information for the target user by a source user at a computing device, the techniques can include providing, from the server to the computing device, a suggestion for the source user. Examples of the suggestion may include a virtual address for an electronic message or at a social network, a physical address for navigation, and a telephone number for calling or incoming caller identification.