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 method of a server device is provided. The method of a server device includes retrieving a prediction input and a prediction setting, replacing at least one non-linear activation channel in a neural network with at least one replacement channel based on the received prediction setting, generating a prediction based on the received prediction input based on the neural network with the at least one replacement channel, and outputting the generated prediction.

Abstract: A machine learning method using a trained machine learning model residing on an electronic device includes receiving an inference request by the electronic device. The method also includes determining, using the trained machine learning model, an inference result for the inference request using a selected inference path in the trained machine learning model. The selected inference path is selected based on a highest probability for each layer of the trained machine learning model. A size of the trained machine learning model is reduced corresponding to constraints imposed by the electronic device. The method further includes executing an action in response to the inference result.

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 method includes applying, by at least one processor, a natural language understanding (NLU) model to an input utterance in order to obtain initial slot probability distributions. The method also includes performing, by the at least one processor, a confidence calibration by applying a calibration probability distribution to the initial slot probability distributions in order to generate calibrated slot probability distributions. The calibration probability distribution has a higher number of dimensions than the initial slot probability distributions. The method further includes identifying, by the at least one processor, uncertainties associated with words in the input utterance based on the calibrated slot probability distributions. In addition, the method includes identifying, by the at least one processor, a new concept contained in the input utterance that is not recognized by the NLU model based on the identified uncertainties.

Abstract: A method includes training, using at least one processor, a specialized teacher model to perform visual object instance segmentation in order to segment and classify objects in first training images. The first training images contain foreground objects without backgrounds. The method also includes training, using the at least one processor, a student model to perform visual object instance segmentation in order to segment and classify objects in second training images. The second training images contain the foreground objects and the backgrounds. Training the student model includes using selected outputs of the specialized teacher model. The method further includes deploying the trained student model to perform visual object instance segmentation in an external device.

Abstract: A continual learning method includes obtaining an input data including a trained model, continual learning (CL) Information, and training data by an electronic device. The method also includes re-training, using the electronic device, the model for a task based on the training data. The method also includes updating, using the electronic device, the CL Information based on the model and the training data. The method further includes selecting a first set of exemplars from the training data based on data associated with the CL Information. The CL Information includes a first group of variables associated with the model and a second group of variables associated with the model that changes to the first group of variables have stronger impact to the model's performance of the task than changes to the second group of variables.

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: A method includes obtaining, using at least one processor of an electronic device, an image-query understanding model. The method also includes obtaining, using the at least one processor, an image and a user query associated with the image, where the image includes a target image area and the user query includes a target phrase. The method further includes retraining, using the at least one processor, the image-query understanding model using a correlation between the target image area and the target phrase to obtain a retrained image-query understanding model.

Abstract: Systems and methods are described for adding new attributes to entities of a knowledge base. A plurality of correlations may be identified between the new attribute and existing attributes of the entities using a rule-based model, such that attribute rules may be associated with each identified correlation exceeding a predetermined confidence threshold. An unstructured data model may then be applied to the knowledge base to identify unstructured data associated with each entity of the plurality of entities correlated to presence of the new attribute. Then a meta learner model may be applied to identify weights for each attribute rule and the identified unstructured data. After the weights have been set for the meta learner model, the meta learner model may then be applied to each entity in the knowledge base to accurately identify entities having the new attribute.

Abstract: A system, method, and computer program product to renewably prevent traitors in a broadcast encryption system from re-using compromised keys. A license agency assigns individual receivers a set of Sequence Keys preferably at manufacture, and assigns Sequence Key Blocks (SKBs) to protected content files to be distributed. The files may be distributed on prerecorded media and typically include several file modifications. The particular modifications in a pirated version of a file can help identify which traitors contributed to its theft. SKBs assigned to new files distributed after traitors have been identified cannot be usefully processed using the compromised keys employed in previous content piracy. Innocent receivers that happen to have compromised key(s) in common with traitors can use a replacement uncompromised Sequence Key from the set to usefully decrypt content. Traitors will however step through all their Sequence Keys without reaching one that will work.

Abstract: A data processing method receives a set of time-series user data and also receives a privacy requirement of the time-series user data. Next, the time-series user data is transformed using the privacy requirement such that the transforming satisfies differential privacy.

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 for learning a task includes capturing first information associated with at least one application executed by an electronic device. A sequence of user interface interactions for the at least one application is recorded. Second information are extracted from the sequence of user interface interactions. Events, action or a combination thereof are filtered from the second information using the first information. Recognition is performed on each element from the first information to generate a semantic ontology. An executable sequential event task bytecode is generated from each element of the semantic ontology and the filtered second information.

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 method, an electronic device and computer readable medium for entity-relationship embeddings using automatically generated entity graphs instead of a traditional knowledge graph are provided. The method includes receiving, by a processor, an input text. The method also includes identifying a primary entity, a secondary entity and a context from the input text, wherein the context comprises a relationship between the primary entity and the secondary entity. The method additionally includes generating, by the processor, an entity context graph based on the primary entity, the secondary entity, and the context by: extracting, from the context, one or more text segments comprising a plurality of words describing one or more additional relationships between the primary entity and the secondary entity, and generating a plurality of context triples from the one or more text segments, each of the plurality of context triples defining a respective relationship between primary entity and the secondary entity.

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: An inpainting method includes retrieving image information at an electronic device, where the image information identifies an area within an image. The method also includes retrieving, using the electronic device, semantic information including a plurality of semantic classes and a semantic class distribution for each semantic class of the plurality of semantic classes. The method further includes generating semantic codes associated with different portions of the image based on the image information and the semantic information. In addition, the method includes constructing the area within the image by generating image content based on the semantic information.

Abstract: A first device specifies a privacy specification. The privacy specification includes at least a safe zone and a precision parameter may also be specified. A second device, such as an untrusted server, uses the privacy specification to provide guidance to the first device on how to perturb sensitive data. The first device then uses the guidance to transform sensitive data and provides it to the second device. The data transformation permits the first device to share sensitive data in a manner that preserves the privacy of the first user but permits statistics on aggregated data to be generated by an untrusted server.

Abstract: A method for intelligent assistance includes identifying one or more insertion points within an input comprising text for providing additional information. A follow-up expression that includes at least a portion of the input and the additional information at the one or more insertion points is generated for clarifying or supplementing meaning of the input.