Abstract: A remote memory system includes a substrate of a multi-chip package, an integrated circuit chip connected to the substrate, and an electro-optical chip connected to the substrate. The integrated circuit chip includes a high-bandwidth memory interface. An electrical interface of the electro-optical chip is electrically connected to the high-bandwidth memory interface. A photonic interface of the electro-optical chip is configured to optically connect with an optical link. The electro-optical chip includes at least one optical macro that converts outgoing electrical data signals received through the electrical interface from the high-bandwidth interface into outgoing optical data signals. The optical macro transmits the outgoing optical data signals through the photonic interface to the optical link. The optical macro also converts incoming optical data signals received through the photonic interface into incoming electrical data signals.

Abstract: The present disclosure relates generally to determining intent based upon speech input using a dialog system. More particularly, techniques are described using matching-based machine learning techniques to identify an intent corresponding to speech input in a dialog system. These procedures do not require training when intents are added or removed from the set of possible intents.

Abstract: Techniques are disclosed herein for using named entity recognition to resolve entity expression while transforming natural language to a meaning representation language. In one aspect, a method includes accessing natural language text, predicting, by a first machine learning model, a class label for a token in the natural language text, predicting, by a second machine-learning model, operators for a meaning representation language and a value or value span for each attribute of the operators, in response to determining that the value or value span for a particular attribute matches the class label, converting a portion of the natural language text for the value or value span into a resolved format, and outputting syntax for the meaning representation language. The syntax comprises the operators with the portion of the natural language text for the value or value span in the resolved format.

Abstract: Techniques are disclosed for augmenting training data for training a machine learning model to generate database queries. Training data comprising a first training example comprising a first natural language utterance, a logical form for the first natural language utterance, and associated first metadata is obtained. From the first training example, a template utterance is generated. A second natural language utterance is generated by filling slots in the template utterance based on a database schema and database values. Updated metadata is produced based on the first metadata and the second natural language utterance. A second training example is generated, comprising the second natural language utterance, the logical form for the first natural language utterance, and the updated metadata. The training data is augmented by adding the second training example. A machine learning model is trained to generate a database query comprising the database operation using the augmented training data set.

Abstract: Techniques are disclosed herein for calibrating confidence scores of a machine learning model trained to translate natural language to a meaning representation language. The techniques include obtaining one or more raw beam scores generated from one or more beam levels of a decoder of a machine learning model trained to translate natural language to a logical form, where each of the one or more raw beam scores is a conditional probability of a sub-tree determined by a heuristic search algorithm of the decoder at one of the one or more beam levels, classifying, by a calibration model, a logical form output by the machine learning model as correct or incorrect based on the one or more raw beam scores, and providing the logical form with a confidence score that is determined based on the classifying of the logical form.

Abstract: Systems and methods identify whether an input utterance is suitable for providing to a machine learning model configured to generate a query for a database. Techniques include generating an input string by concatenating a natural language utterance with a database schema representation for a database; providing the input string to a first machine learning model; based on the input string, generating, by the first machine learning model, a score indicating whether the natural language utterance is translatable to a database query for the database and should be routed to a second machine learning model, the second machine learning model configured to generate a query for the database based on the natural language utterance; comparing the score to a threshold value; and responsive to determining that the score exceeds the threshold value, providing the natural language utterance or the input string to the second machine learning model.

Abstract: Techniques are disclosed herein for converting a natural language utterance to an intermediate database query representation. An input string is generated by concatenating a natural language utterance with a database schema representation for a database. Based on the input string, a first encoder generates one or more embeddings of the natural language utterance and the database schema representation. A second encoder encodes relations between elements in the database schema representation and words in the natural language utterance based on the one or more embeddings. A grammar-based decoder generates an intermediate database query representation based on the encoded relations and the one or more embeddings. Based on the intermediate database query representation and an interface specification, a database query is generated in a database query language.

Abstract: A server device, system, method, and for controlling access to project resources is disclosed. The disclosure includes a processor, and a communications module and a memory coupled to the processor. The memory, when executed by the processor, causes the processor to generate a plurality of zones for a project, each zone defining a set of access rights to: i) a database; and ii) at least one tool. The processor configures each set of access rights to allow a proxy service to access the zones, and receives, from a client device and via the proxy service, an access query to access at least one zone. The processor provides the client device access to, via the proxy service, the at least one dataset and at least one tool of the at least one zone.

Abstract: Techniques are disclosed herein for addressing catastrophic forgetting and over-generalization while training a model to transform natural language to a logical form such as a meaning representation language. The techniques include accessing training data comprising natural language examples, augmenting the training data to generate expanded training data, training a machine learning model on the expanded training data, and providing the trained machine learning model. The augmenting includes (i) generating contrastive examples by revising natural language of examples identified to have caused regression during training of a machine learning model with the training data, (ii) generating alternative examples by modifying operators of examples identified within the training data that belong to a concept that exhibits bias, or (iii) a combination of (i) and (ii).

Abstract: A bacterium of the class Clostridia comprising a heterologous nucleic acid molecule encoding at least one antigen, wherein the bacterium is capable of expressing the antigen in an intracellular compartment of the bacterium during anaerobic cell growth, and wherein at least one antigen is an infectious agent antigen or a tumour antigen.

Abstract: Systems and methods fine-tune a pretrained machine learning model. For a model having multiple layers, an initial set of configurations is identified, each configuration establishing layers to be frozen and layers to be fine-tuned. A configuration that is optimized with respect to one or more parameters is selected, establishing a set of fine-tuning layers and a set of frozen layers. An input for the model is provided to a remote system. An output of the set of frozen layers of the model, given the provided input, is received back and locally stored. The set of fine-tuning layers of the model is loaded from the remote system. The model is fine-tuned by retrieving the locally stored output of the set of frozen layers, and updating weights associated with the set of fine-tuning layers of the machine learning model.

Abstract: Disclosed herein are techniques for using a generative adversarial network (GAN) to train a semantic parser of a dialog system. A method described herein involves accessing seed data that includes seed tuples. Each seed tuple includes a respective seed utterance and a respective seed logical form corresponding to the respective seed utterance. The method further includes training a semantic parser and a discriminator in a GAN. The semantic parser learns to map utterances to logical forms based on output from the discriminator, and the discriminator learns to recognize authentic logical forms based on output from the semantic parser. The semantic parser may then be integrated into a dialog system.

Abstract: A method for tailoring a document for viewing on a mobile device includes obtaining residence information for an individual who is required to sign the document. The document is tailored to the residence of the individual. This includes hiding or condensing one or more portions of the document that pertain to laws in other jurisdictions. The document is permitted to be accessible by the mobile device.

Abstract: A method, system, and apparatus for monitoring a magnetic field related to magnetic stimulation may be provided. A system for monitoring a pulsing magnetic field related to magnetic stimulation therapy may include a magnetic stimulation component, a sensor, and a processor. The magnetic stimulation component may be configured to generate the pulsing magnetic field for the magnetic stimulation therapy. The sensor may be configured to generate a signal associated with the pulsing magnetic field. The processor may be configured to estimate a first characteristic associated with a first peak of the signal, estimate a second characteristic associated with a second peak of the signal, and determine a third characteristic of the signal based on the first characteristic and the second characteristic. The processor may be configured to determine whether a failure occurred based on the third characteristic of the signal.

Abstract: An inflatable penile prosthesis can include, a reservoir, an inflatable member and a pump assembly. The pump assembly can include at least one valve comprising an entry portion, a middle portion, an exit portion, and exit tube interface, and a valve member. The exit portion can include a first landing portion including an interior portion, the interior portion of the first landing portion being semicircular about a longitudinal exit axis, the longitudinal exit axis extending through a center of the exit portion parallel to a direction that an exit tube interface extends from the exit portion, and a first channel portion adjacent to the first landing portion and including an interior portion, the interior portion of the first channel portion being farther from the longitudinal exit axis than the interior portion of the first landing portion.

Abstract: A system includes a memory comprising a first preference profile and a second preference profile, a correlation module configured to determine a correlation value between the first preference profile and the second preference profile, and a module configured to take an action as a function of the correlation value. The action is changing a physical configuration of signage from a first physical configuration to a second physical configuration.

Abstract: An augmentation and feature caching subsystem is described for training AI/ML models. In one particular aspect, a method is provided that includes receiving data comprising training examples, one or more augmentation configuration hyperparameters and one or more feature extraction configuration hyperparameters; generating a first key based on one of the training examples and the one or more augmentation configuration hyperparameters; searching a first key-value storage based on the first key; obtaining one or more augmentations based on the search of the first key-value storage; applying the obtained one or more augmentations to the training examples to result in augmented training examples; generating a second key based on one of the augmented training examples and the one or more feature extraction configuration hyperparameters; searching a second key-value storage based on the second key; obtaining one or more features based on the search of the second key-value storage.

Abstract: An atomizer for applying a coating includes a nozzle plate, an actuator, and an acoustic focusing device. The nozzle plate defines at least one aperture. The actuator is configured to oscillate to form pressure waves within a fluid to eject the fluid from the nozzle plate. The acoustic focusing device focuses the pressure waves toward the apertures.

Abstract: A method of performing peritoneal dialysis (PD), the method comprising: delivering a PD fluid to the peritoneal cavity of a patient through a PD catheter; dwelling the PD fluid within the peritoneal cavity; and while dwelling the PD fluid, removing a biofilm from the PD catheter wall using a biofilm removing solution. The biofilm removing solution comprises: sodium citrate dihydrate; citric acid anhydrous; sodium lauryl sulfate; and water. In another aspect, a method for decontaminating a peritoneal dialysis (PD) catheter and removing a biofilm from the PD catheter and a transfer set, the method comprising: providing a biofilm removing solution; transferring the biofilm removing solution into a syringe; connecting the syringe to a transfer set of the PD catheter; and filling the transfer set and the PD catheter with the biofilm removing solution.

Abstract: The invention relates methods for diagnosing patients with multiple sclerosis by detecting cell free nucleosomes as biomarkers in body fluid samples.