Abstract: One embodiment provides a method comprising receiving general private data identifying at least one type of privacy-sensitive data to protect, collecting at least one type of real-time data, and determining an inference privacy risk level associated with transmitting the at least one type of real-time data to a second device. The inference privacy risk level indicates a degree of risk of inferring the general private data from transmitting the at least one type of real-time data. The method further comprises distorting at least a portion of the at least one type of real-time data based on the inference privacy risk level before transmitting the at least one type of real-time data to the second device.

Abstract: A system receives a phrase that includes at least one tagged object and generates instantiated phrases by instantiations of each tagged object in the phrase. The system generates lists of natural language phrases by corresponding paraphrases of each of the instantiated phrases. The system generates ordered lists of natural language phrases by ordering natural language phrases in each list of natural language phrases based on occurrences of each natural language phrase. The system generates annotated natural language phrases by using each tagged object in the phrase to annotate the ordered lists of natural language phrases or an enhanced set of natural language phrases that is based on the ordered lists of natural language phrases.

Abstract: A method includes obtaining, using at least one processor of an electronic device, a base natural language understanding (NLU) model that includes a word embedding layer, where the word embedding layer is associated with at least one training utterance. The method also includes calculating, using the at least one processor, a regularization loss value for use in a determination of an intent detection loss, where the regularization loss value reveals an effect of word embeddings on intent determination of the training utterance. The method further includes retraining, using the at least one processor, the word embedding layer of the base NLU model using the intent detection loss to obtain a retrained NLU model.

Abstract: A system determines intent values based on an object in a received phrase, and detail values based on the object in the received phrase. The system determines intent state values based on the intent values and the detail values, and detail state values and an intent detail value based on the intent values and the detail values. The system determines other intent values based on the intent values and another object in the received phrase, and other detail values based on the detail values and the other object in the received phrase. The system determines a general intent value based on the other intent values, the other detail values, and the intent state values, and another intent detail value based on the other intent values, the other detail values, and the detail state values.

Abstract: A method includes obtaining, using at least one processor of an electronic device, a base model trained to perform natural language understanding. The method also includes generating, using the at least one processor, a first model expansion based on knowledge from the base model. The method further includes training, using the at least one processor, the first model expansion based on first utterances without modifying parameters of the base model. The method also includes receiving, using the at least one processor, an additional utterance from a user. In addition, the method includes determining, using the at least one processor, a meaning of the additional utterance using the base model and the first model expansion.

Abstract: A method includes receiving, from an electronic device, information defining a user utterance associated with a skill to be performed, where the skill is not recognized by a natural language understanding (NLU) engine. The method also includes receiving, from the electronic device, information defining one or more actions for performing the skill. The method further includes identifying, using at least one processor, one or more known skills having one or more slots that map to at least one word or phrase in the user utterance. The method also includes creating, using the at least one processor, a plurality of additional utterances based on the one or more mapped slots. In addition, the method includes training, using the at least one processor, the NLU engine using the plurality of additional utterances.

Abstract: An electronic device for complex task machine learning includes at least one memory and at least one processor coupled to the at least one memory. The at least one processor is configured to receive an unknown command for performing a task and generate a prompt regarding the unknown command. The at least one processor is also configured to receive one or more instructions in response to the prompt, where each of the one or more instructions provides information on performing at least a portion of the task. The at least one processor is further configured to determine at least one action for each one of the one or more instructions. In addition, the at least one processor is configured to create a complex action for performing the task based on the at least one action for each one of the one or more instructions.

Abstract: Described is a system for providing improved exploration for an interactive recommendation system by leveraging intuitive user feedback. The recommendation system may provide images of recommend items and receive user feedback preferences in the form of a natural language expression. Traditional techniques for interactive recommendation systems typically rely on restricted forms of user feedback such as binary relevance responses, or feedback based on a fixed set of relative attributes. In contrast, the recommendation system described herein introduces a new approach to interactive image recommendation (or image search) that enables users to provide feedback via natural language, allowing for a more natural and effective interaction. The recommendation system may be based on formulating the task of natural-language-based interactive image recommendation as a reinforcement learning problem, and reward the recommendation system for improving the rank of the target image during each iterative interaction.

Abstract: Intent determination based on one or more multi-model structures can include generating an output from each of a plurality of domain-specific models in response to a received input. The domain-specific models can comprise simultaneously trained machine learning models that are trained using a corresponding local loss metric for each domain-specific model and a global loss metric for the plurality of domain-specific models. The presence or absence of an intent corresponding to one or more domain-specific models can be determined by classifying the output of each domain-specific model.

Abstract: Systems and methods are described for converting input content. A first model may convert input content to an output content that exhibits one or more desired properties. A second model may determine if the conversion meets a desired quality of conversion using a discriminating function. The discriminating function may determine a difference between properties of the output content and properties of desired content, where the difference corresponds to the success of the conversion applying the desired properties. Updated control data may be generated by a third model using information from the second model, where the updated control data may be used by the first model to reduce the determined difference. After updated control data has been generated, the foregoing steps may be repeated based upon the updated control data. One of a plurality of different actions may be determined in response to the difference.

Abstract: An accurate distance between two devices can be determined in continuous and secure manner using modulated audible signals containing time-based information. This calculated distance can be used to lock and unlock one of the two devices such that if one of the devices, such as a smart phone or smart watch, is beyond a pre-configured distance from the other device, such as a laptop or tablet, the other device locks and may display a message to the user. The modulated messages contain time difference data of audible signal emission and receiving times which are used by each device to calculate an accurate estimate of the distance between the two devices.

Abstract: An electronic device including a deep memory model includes at least one memory and at least one processor coupled to the at least one memory. The at least one processor is configured to receive input data to the deep memory model. The at least one processor is also configured to extract a history state of an external memory coupled to the deep memory model based on the input data. The at least one processor is further configured to update the history state of the external memory based on the input data. In addition, the at least one processor is configured to output a prediction based on the extracted history state of the external memory.

Abstract: An electronic device for training a machine learning model includes at least one memory and at least one processor coupled to the at least one memory. The at least one processor is configured to train a classification layer of the model. To train the classification layer, the at least one processor is configured to receive, by the classification layer, one or more language contexts from an utterance encoder layer and to classify, by the classification layer, at least one portion of an utterance into an information type among a plurality of information types. The at least one processor may be further configured to jointly train a slot filling layer and an intent detection layer of the model.

Abstract: A method includes determining, by an electronic device, a skill from a first natural language (NL) input. Upon successful determination of the skill, the first NL input is transmitted to a custom skill parser for determination of a skill intent. The custom skill parser is trained based on data including at least a custom training data set. Upon unsuccessful determination of the skill, the first NL input is transmitted to a generic parser for determination of a general intent of the first NL input.

Abstract: A system receives a phrase that includes at least one tagged object and generates instantiated phrases by instantiations of each tagged object in the phrase. The system generates lists of natural language phrases by corresponding paraphrases of each of the instantiated phrases. The system generates ordered lists of natural language phrases by ordering natural language phrases in each list of natural language phrases based on occurrences of each natural language phrase. The system generates annotated natural language phrases by using each tagged object in the phrase to annotate the ordered lists of natural language phrases or an enhanced set of natural language phrases that is based on the ordered lists of natural language phrases.

Abstract: A system determines intent values based on an object in a received phrase, and detail values based on the object in the received phrase. The system determines intent state values based on the intent values and the detail values, and detail state values and an intent detail value based on the intent values and the detail values. The system determines other intent values based on the intent values and another object in the received phrase, and other detail values based on the detail values and the other object in the received phrase. The system determines a general intent value based on the other intent values, the other detail values, and the intent state values, and another intent detail value based on the other intent values, the other detail values, and the detail state values.

Abstract: An electronic device for active learning includes at least one memory and at least one processor coupled to the at least one memory. The at least one processor is configured to select one or more entries from a data set including unlabeled data based on a similarity between the one or more entries and labeled data. The at least one processor is further configured to cause the one or more entries to be labeled.

Abstract: A method includes retrieving, at an electronic device, a first natural language (NL) input. An intent of the first NL input is undetermined by both a generic parser and a personal parser. A paraphrase of the first NL input is retrieved at the electronic device. An intent of the paraphrase of the first NL input is determined using at least one of: the generic parser, the personal parser, or a combination thereof. A new personal intent for the first NL input is generated based on the determined intent. The personal parser is trained using existing personal intents and the new personal intent.

Abstract: An apparatus, method, and computer readable medium for management of infinite data streams. The apparatus includes a memory that stores streaming data with a data set and a processor operably connected to the memory. The processor transforms the data set to a second data set. To transform the data set, the processor determines whether a difference level exceeds a threshold, and transforms the data set by adding a noise when the difference level exceeds the threshold. When the difference level does not exceed the threshold, the processor determines whether a retroactive count is greater than a threshold, transforms the data set by adding a second noise when the retroactive count is greater than the threshold, and transforms the data set by adding a third noise when the retroactive count is not greater than the threshold. The processor transmits the second data set to a data processing system for further processing.

Abstract: A recognition method includes retrieving an input including data of a first window size. The method further includes classifying the input based on comparison of warping distance of the input with a pruning threshold.