Abstract: A conversation model is generated based on a conversation between a plurality of participants. Conversation text associated with the conversation is retrieved. A plurality of conversation model components are identified within the conversation text. A correlation score is determined for each pair of conversation model components representing a measure of relatedness between the pair of conversation model components. Extrapolated conversation model components are identified based on the plurality of conversation model components and the determined correlation scores. The conversation model components, the additional conversation model components, and the correlation scores are then stored as a conversation model.

Abstract: Contextual content is provided to a first conversation participant via a client device of the first conversation participant. Communication information associated with a conversation is received via the first client device interface. Context information associated with the conversation is retrieved from the received communication information. One or more concepts associated with the conversation are identified based on the context information. Content is selected for presenting on the client device based on the identified concepts. The selected content is then presented to the first conversation participant in a second client device interface.

Abstract: Data is asynchronously provided to a participant of a conversation. A temporal model is maintained for each of a plurality of client devices associated with the conversation. A temporal model describes a state of an associated client device. Data for sending to a client device is identified based on conversation context information describing a context of a conversation participant associated with the client device. A determination of whether to send the identified data to the client device is made based on the temporal model associated with the client device. The temporal model associated with the client device is updated based on the determination.

Abstract: A gesture-based search interface is provided on a client device. A concept interface is displayed within the search interface, the concept interface including a plurality of selected concept tabs. A content interface is also displayed within the search interface, the content interface configured to, in response to a selection of a concept tab, display content associated with a concept represented by the selected concept tab. A gesture input is received at the client device, for instance a touch input received at a touch-screen of the client device. A concept input mechanism is presented in response to the gesture input, and an additional concept tab is presented within the concept interface in response to receiving a concept via the concept input mechanism. The content interface displays content associated with the received concept when the additional concept tab is selected.

Abstract: Conversation information is provided to a conversation participant. Audio data is received a client device associated with a conversation participant. The client device maintains a buffer of received audio data, for instance audio data received in a previous interval of time. A recall request is received by the client device for information associated with the buffered audio data. The buffered audio data is analyzed responsive to the recall request to identify the requested information. The identified information is then presented at the client device.