Abstract: Techniques are disclosed herein for improving the performance of an end-to-end (E2E) Automatic Speech Recognition (ASR) model in a target domain. A set of test examples are generated. The set of test examples comprise multiple subsets of test examples and each subset of test examples corresponds to a particular test category. A machine language model is then used to convert audio samples of the subset of test examples to text transcripts. A word error rate is determined for the subset of test examples. A test category is then selected based on the word error rates and a set of training examples is generated for training the ASR model in a particular target domain from a selected subset of test examples The training examples are used to fine-tune the model in the target domain. The trained model is then deployed in a cloud infrastructure of a cloud service provider.

Abstract: A drain detection system for a vehicle includes: a sensor configured to detect parameters of a low-voltage battery of the vehicle and collect battery data including the parameters when the vehicle is OFF; a telematics module; and a control module configured to i) receive the battery data from the sensor when the vehicle is ON, ii) transmit via the telematics module the battery data to a network device, which is remotely located from the vehicle, iii) receive an alert message from the network device indicative of a parasitic drain on the low-voltage battery, and iv) perform a first countermeasure in response to the alert message.

Abstract: The present disclosure is related to techniques for converting a natural language utterance to a logical form query and deriving a natural language interpretation of the logical form query. The techniques include accessing a Meaning Resource Language (MRL) query and converting the MRL query into a MRL structure including logical form statements. The converting includes extracting operations and associated attributes from the MRL query and generating the logical form statements from the operations and associated attributes. The techniques further include translating each of the logical form statements into a natural language expression based on a grammar data structure that includes a set of rules for translating logical form statements into corresponding natural language expressions, combining the natural language expressions into a single natural language expression, and providing the single natural language expression as an interpretation of the natural language utterance.

Abstract: The present disclosure is related to techniques for converting a natural language utterance to a logical form query and deriving a natural language interpretation of the logical form query. The techniques include accessing a Meaning Resource Language (MRL) query and converting the MRL query into a MRL structure including logical form statements. The converting includes extracting operations and associated attributes from the MRL query and generating the logical form statements from the operations and associated attributes. The techniques further include translating each of the logical form statements into a natural language expression based on a grammar data structure that includes a set of rules for translating logical form statements into corresponding natural language expressions, combining the natural language expressions into a single natural language expression, and providing the single natural language expression as an interpretation of the natural language utterance.

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: 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 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: A system comprises a production well having an inlet in fluid communication with an underground reservoir, wherein the reservoir is at a first temperature and contains a native aqueous solution, a working fluid withdrawn from the reservoir into the inlet and through the production well. The working fluid comprises a non-water component and an aqueous component comprising a portion of the aqueous solution. The system further comprises a separation apparatus in communication with the production well configured to separate the aqueous component from the working fluid to provide a dewatered working fluid, wherein the aqueous component is from more than 0 wt. % to no more than a specified threshold of the dewatered working fluid. The system also includes an energy recovery system that comprises an expansion device through which the dewatered working fluid passes and produces work energy and a generator that converts the work energy to electricity.

Abstract: Techniques are disclosed herein for synthesizing synthetic training data to facilitate training a natural language to logical form model. In one aspect, training data can be synthesized from original under a framework based on templates and a synchronous context-free grammar. In one aspect, training data can be synthesized under a framework based on a probabilistic context-free grammar and a translator. In one aspect, training data can be synthesized under a framework based on tree-to-string translation. In one aspect, the synthetic training data can be combined with original training data in order to train a machine learning model to translate an utterance to a logical form.

Abstract: Techniques for preprocessing data assets to be used in a natural language to logical form model based on scalable search and content-based schema linking. In one particular aspect, a method includes accessing an utterance, classifying named entities within the utterance into predefined classes, searching value lists within the database schema using tokens from the utterance to identify and output value matches including: (i) any value within the value lists that matches a token from the utterance and (ii) any attribute associated with a matching value, generating a data structure by organizing and storing: (i) each of the named entities and an assigned class for each of the named entities, (ii) each of the value matches and the token matching each of the value matches, and (iii) the utterance, in a predefined format for the data structure, and outputting the data structure.

Abstract: Techniques are disclosed herein for synthesizing synthetic training data to facilitate training a natural language to logical form model. In one aspect, training data can be synthesized from original under a framework based on templates and a synchronous context-free grammar. In one aspect, training data can be synthesized under a framework based on a probabilistic context-free grammar and a translator. In one aspect, training data can be synthesized under a framework based on tree-to-string translation. In one aspect, the synthetic training data can be combined with original training data in order to train a machine learning model to translate an utterance to a logical form.

Abstract: Techniques are disclosed herein for synthesizing synthetic training data to facilitate training a natural language to logical form model. In one aspect, training data can be synthesized from original under a framework based on templates and a synchronous context-free grammar. In one aspect, training data can be synthesized under a framework based on a probabilistic context-free grammar and a translator. In one aspect, training data can be synthesized under a framework based on tree-to-string translation. In one aspect, the synthetic training data can be combined with original training data in order to train a machine learning model to translate an utterance to a logical form.

Abstract: A system comprises a production well having an inlet in fluid communication with an underground reservoir, wherein the reservoir is at a first temperature and contains a native aqueous solution, a working fluid withdrawn from the reservoir into the inlet and through the production well. The working fluid comprises a non-water component and an aqueous component comprising a portion of the aqueous solution. The system further comprises a separation apparatus in communication with the production well configured to separate the aqueous component from the working fluid to provide a dewatered working fluid, wherein the aqueous component is from more than 0 wt. % to no more than a specified threshold of the dewatered working fluid. The system also includes an energy recovery system that comprises an expansion device through which the dewatered working fluid passes and produces work energy and a generator that converts the work energy to electricity.

Abstract: A system comprising a non-water working fluid feed stream, a compressor configured to compress the non-water based working fluid, to provide a compressed non-water based working fluid; and an energy recovery system configured to recover energy from the compressed non-water based working fluid, to provide a de-energized compressed non-water based working fluid, wherein the energy recovery system captures at least a portion of excess energy from the compressed non-water based working fluid and converts the captured excess energy to electricity, heat energy, or both electricity and heat energy.

Abstract: Provided are antibody-drug conjugates (ADCs) that bind to, and kill MET expressing tumor cells, and that are effective in treating MET expressing cancers. Also provided are novel compounds and methods of conjugating MET antibodies to generate such ADCs.

Abstract: Provided are antibody-drug conjugates (ADCs) that bind to, and kill MET expressing tumor cells, and that are effective in treating MET expressing cancers. Also provided are novel compounds and methods of conjugating MET antibodies to generate such ADCs.

Abstract: The present invention provides the following compounds, or pharmaceutically acceptable salts thereof, and pharmaceutical compositions containing said compounds useful as a Notch pathway signaling inhibitor for the treatment of named cancers, sensorineural hearing loss caused by auditory hair cell loss, and inducing auditory hair cell generation.

Abstract: A compressive brace for intraarticular needle procedures that provides constant radial compression. One embodiment comprises a non-pneumatic releasable compressive planar device or tubular sleeve, a method to apply tension to the device or sleeve comprising a non-stretchable material or stretchable elastomeric material with fasteners or external compression straps or both resulting in fluid displacement and increased intraarticular fluid pressure, a design that displaces fluid within the joint to low pressure areas to be readily accessible by needle or catheter via specific anatomic portals so that the joint can be completely aspirated, tension and pressure can be released so that fluid can be easily removed or injected into the joint, and integration of the device into arthrocentesis, surgical, diagnostic, and joint therapy kits. Some embodiments define a window or aperture to allow pooling of fluid and to introduce needles and catheters.

Abstract: Percutaneous musculoskeletal lavage devices, and procedures for simultaneous therapeutic and diagnostic purposes, performed with a needle or catheter and various combinations of a syringe, reciprocating syringe, stop-cock, check valves, depth indicator, compressive sleeve or brace, and specialty catheters, provided individually or in a kit. The lavage fluid can be analyzed for factors of medical interest and used to determine personalized treatment, and has intrinsic medical benefit by virtue of clearing the tissues of noxious substances in an enhanced fashion.

Abstract: The present invention provides the following compounds, or pharmaceutically acceptable salts thereof, and pharmaceutical compositions containing said compounds useful as a Notch pathway signaling inhibitor for the treatment of named cancers, sensorineural hearing loss caused by auditory hair cell loss, and inducing auditory hair cell generation.