Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media, for generating responses using task-independent conversational systems are provided. In one example method, a response to a user text input is generated by updating a state of the conversation based on the user text input, generating a conversational (task-independent) output, and determining whether to provide a conversational response based on the conversational output, or to additionally generate a task-specific output.

Abstract: Exemplary embodiments relate to methods, mediums, and systems for managing a conversation. In an embodiment, a computer-implemented input interface is provided to receive an input comprising information in natural language. A dialog manager is configured to determine an intent of the input, determine information to fulfill the intent, and identify one or both of information available to the dialog manager or information that is unavailable to the dialog manager. A conversational understanding document documents the intent and the identified information. An output interface forwards the conversational understanding document towards a task completion handler separate and distinct from the dialog manager. Other embodiments are described and claimed.

Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media, for secure data transmission using natural language. One of the methods includes: obtaining sensitive information for a user; obtaining a natural language key for the user, wherein the natural language key for the user includes one or more natural language tokens; generating decoding data for the sensitive information for the user, wherein generating the decoding data comprises: for each place in the sensitive information for the user: assigning a respective one of the natural language tokens in the natural language key for the user to the value at the place, and generating one or more respective dummy natural language tokens for each value of the respective set of possible values for the place other than the value at the place; and providing the decoding data for use in decoding the natural language key into the sensitive information.

Abstract: This application addresses techniques for personalizing natural language generation by conversational agents. These solutions allow for human-like, large scale opinion expression using a consistent style or personality. Training sentences may be retrieved and a vocabulary may be built based on an analysis of the training sentences. The sentences may be analyzed to determine: (1) whether they express an opinion; (2) whether the opinion is positive or negative; (3) whether the sentence fits in the context of the currently communication; and (4) whether the sentence came from a person with first-hand experience of the topic. Further classifications may be made based on characteristics such as the age or gender of the person expressing the opinion. These opinions may be entered into a repository and used for opinion expression, for example by using the statements directly in a conversation or by training a language generation model with the opinions.

Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media, for secure data transmission using natural language. One of the methods includes: obtaining sensitive information for a user; obtaining a natural language key for the user, wherein the natural language key for the user includes one or more natural language tokens; generating decoding data for the sensitive information for the user, wherein generating the decoding data comprises: for each place in the sensitive information for the user: assigning a respective one of the natural language tokens in the natural language key for the user to the value at the place, and generating one or more respective dummy natural language tokens for each value of the respective set of possible values for the place other than the value at the place; and providing the decoding data for use in decoding the natural language key into the sensitive information.

Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media, for generating additional training data for a natural language understanding engine. One of the methods includes: obtaining data identifying (i) a first input conversational turn and (ii) a first annotation, determining that the first annotation accurately characterized the first input conversational turn, determining that the natural language understanding engine is likely to generate inaccurate annotations of other conversational turns that are similar to the first input conversational turn, in response to the determining, obtaining one or more first paraphrases of the first input conversational turn; and generating, for each of the one or more first paraphrases, a respective first training example that identifies the first annotation as the correct annotation for the first paraphrase; and training the natural language understanding engine on at least the first training examples.

Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media, for generating responses using task-independent conversational systems.

Abstract: A method determines user intent associated with a post from a user on a social networking service, based at least in part on content of the post. The method generates a first notification of the user intent associated with the post and selects a plurality of users of the social networking service to receive the first notification. The method provides the first notification to the users. After providing the first notification to the plurality of users, the method: (i) receives one or more responses to the first notification from one or more users of the plurality of users, the responses including information responsive to the first notification; (ii) generates a second notification, including indications of determined respective intent associated with the one or more received responses based, at least in part, on content of the one or more received responses; and (iii) provides the second notification to the user.

Abstract: A method of providing notifications to users of a social networking service includes determining a user intent associated with a post from a user on the social networking service, based at least in part on content of the post. The method further includes generating a first notification of the user intent associated with the post and selecting a plurality of users of the social networking service to receive the first notification. The method further includes providing the first notification to the plurality of users, and after providing the first notification to the plurality of users: (1) receiving one or more responses to the first notification from one or more users of the plurality of users, the one or more responses including information responsive to the first notification, and (2) providing the information responsive to the first notification to the user.

Abstract: This application addresses techniques for personalizing natural language generation by conversational agents. These solutions allow for human-like, large scale opinion expression using a consistent style or personality. Training sentences may be retrieved and a vocabulary may be built based on an analysis of the training sentences. The sentences may be analyzed to determine: (1) whether they express an opinion; (2) whether the opinion is positive or negative; (3) whether the sentence fits in the context of the currently communication; and (4) whether the sentence came from a person with first-hand experience of the topic. Further classifications may be made based on characteristics such as the age or gender of the person expressing the opinion. These opinions may be entered into a repository and used for opinion expression, for example by using the statements directly in a conversation or by training a language generation model with the opinions.

Abstract: This application addresses techniques for personalizing natural language generation by conversational agents. These solutions allow for human-like, large scale opinion expression using a consistent style or personality. Opinion statements may be retrieved and categorized. These opinion statements may be entered into a database and used directly for opinion expression. A model, such as an artificial neural network, may be generated or parameterized based on these opinions. Within the model structure, a personality embedding space may be defined. The embedding space may be used when generating new sentences, or to classify newly-generated or existing sentences. Thus, the model may be used to find further examples of opinions in the same style, or to generate entirely new opinion sentences in a given style.

Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media, for generating responses using task-independent conversational systems.

Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media, for secure data transmission using natural language. One of the methods includes: obtaining sensitive information for a user; obtaining a natural language key for the user, wherein the natural language key for the user includes one or more natural language tokens; generating decoding data for the sensitive information for the user, wherein generating the decoding data comprises: for each place in the sensitive information for the user: assigning a respective one of the natural language tokens in the natural language key for the user to the value at the place, and generating one or more respective dummy natural language tokens for each value of the respective set of possible values for the place other than the value at the place; and providing the decoding data for use in decoding the natural language key into the sensitive information.

Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media, for generating additional training data for a natural language understanding engine. One of the methods includes: obtaining data identifying (i) a first input conversational turn and (ii) a first annotation, determining that the first annotation accurately characterized the first input conversational turn, determining that the natural language understanding engine is likely to generate inaccurate annotations of other conversational turns that are similar to the first input conversational turn, in response to the determining, obtaining one or more first paraphrases of the first input conversational turn; and generating, for each of the one or more first paraphrases, a respective first training example that identifies the first annotation as the correct annotation for the first paraphrase; and training the natural language understanding engine on at least the first training examples.

Abstract: A method of providing notifications to users of a social networking service includes determining a user intent associated with a post from a user on the social networking service, based at least in part on content of the post. The method further includes generating a first notification of the user intent associated with the post and selecting a plurality of users of the social networking service to receive the first notification. The method further includes providing the first notification to the plurality of users, and after providing the first notification to the plurality of users: (1) receiving one or more responses to the first notification from one or more users of the plurality of users, the one or more responses including information responsive to the first notification, and (2) providing the information responsive to the first notification to the user.

Abstract: Exemplary embodiments relate to methods, mediums, and systems for managing a conversation. In an embodiment, a computer-implemented input interface is provided to receive an input comprising information in natural language. A dialog manager is configured to determine an intent of the input, determine information to fulfill the intent, and identify one or both of information available to the dialog manager or information that is unavailable to the dialog manager. A conversational understanding document documents the intent and the identified information. An output interface forwards the conversational understanding document towards a task completion handler separate and distinct from the dialog manager. Other embodiments are described and claimed.

Abstract: One or more embodiments of techniques or systems for modeling familiarity for a traveler are provided herein. Familiarity evidence can be received, indicative of how familiar a traveler is with an area or road segment, and based on a number of visits the traveler has made to that area. The familiarity evidence can be used to generate one or more familiarity models indicative of a predicted familiarity of locations around the area. Familiarity models can be based on kernels, graph distances, Markov random fields (MRFs), etc. When route directions are generated from an origin location to a destination location, one or more of the directions can be provided based on one or more of the familiarity models. For example, if a familiarity model indicates that a traveler is familiar with a route, driving directions of the route can be adapted to be more succinct.

Abstract: A method and system for multimodal human-vehicle interaction including receiving input from an occupant in a vehicle via more than one mode and performing multimodal recognition of the input. The method also includes augmenting at least one recognition hypothesis based on at least one visual point of interest and determining a belief state of the occupant's intent based on the recognition hypothesis. The method further includes selecting an action to take based on the determined belief state.

Abstract: An utterance is received from a user specifying a location attribute and a landmark. A set of candidate locations is identified based on the specified location attribute, and a confidence score can be determined for each candidate location. A set of landmarks is identified based on the specified landmark, and confidence scores can be determined for the landmarks. An associated kernel model is generated for each landmark. Each kernel model is centered at the location of the associated landmark on a map, and the amplitude of the kernel model can be based on landmark attributes, landmark confidence scores, characteristics of the user, and the like. The candidate locations are ranked based on the amplitudes of overlapping kernel models at the candidate locations, and can also be ranked based on confidence scores associated with the candidate locations. A candidate location is selected and presented to the user based on the candidate location ranking.

Abstract: A powertrain of a hybrid electric vehicle (HEV) is controlled. A first value ?1 and a second value ?2 are determined. ?1 represents a proportion of an instantaneous power requirement (Preq) supplied by an engine of the HEV. ?2 controls a recharging rate of a battery of the HEV. A determination is performed, based on ?1 and ?2, regarding how much engine power to use (Peng) and how much battery power to use (Pbatt). Peng and Pbatt are sent to the powertrain.