Abstract: A method includes executing a Optical Character Recognition (OCR) preprocessor on training images to obtain OCR preprocessor output, executing an OCR engine on the OCR preprocessor output to obtain OCR engine output, and executing an approximator on the OCR preprocessor output to obtain approximator output. The method further includes iteratively adjusting the approximator to simulate the OCR engine using the OCR engine output and the approximator output, and generating OCR preprocessor losses using the approximator output and target labels. The method further includes iteratively adjusting the OCR preprocessor using the OCR preprocessor losses to obtain a customized OCR preprocessor.

Abstract: Systems and methods for training a machine learning model are disclosed. A system may be configured to obtain a plurality of training samples. The system includes a machine learning model to generate predictions and generate a confidence score for each generated prediction. In this manner, the system is configured to, for each training sample of the plurality of training samples, generate a prediction by a machine learning model based on the training sample and generating a confidence score associated with the prediction by the machine learning model. The system is also configured to train the machine learning model based on the plurality of predictions and associated confidence scores. For example, one or more training samples may be excluded from use in training the machine learning model based on the associated one or more confidence scores (such as the confidence score being less than a threshold).

Abstract: Systems and methods for forecasting cashflows across one or more accounts of a user disclosed. One example method may include retrieving a data set for each of a plurality of accounts from a database, constructing a graph including a plurality of nodes linked together by a multitude of edges, wherein each node identifies a time series value corresponding to one of the accounts, and each edge indicates a time series value of a corresponding set of transactions occurring between a corresponding pair of accounts, determining a plurality of constraints, determining a specified loss function based on the plurality of constraints, back-propagating a derivative of the specified loss function into a deep neural network (DNN) to determine a set of neural network parameters, forecasting, using the DNN, a time sequence for one or more of the nodes and one or more of the edges, and providing the forecasted time sequences to the user.

Abstract: A method may include extracting, from a document, a first key-value pair including a key and a first value and corresponding to a first confidence score, extracting a second key-value pair including the key and a second value corresponding to a second confidence score, classifying a first match probability for the first key-value pair and a second match probability for the second key-value pair, generating a first calibrated confidence score for the first confidence score and a second calibrated confidence score for the second confidence score by transforming, using precision lookup tables constructed from training records, the first match probability to the first calibrated confidence score and the second match probability to second calibrated confidence score, selecting, using the first and second calibrated confidence scores, one of the first key-value pair and the second key-value pair, and presenting, in a graphical user interface (GUI), the selected key-value pair.

Abstract: Certain aspects of the present disclosure provide techniques for node matching with accuracy by combining statistical methods with a knowledge graph to assist in responding (e.g., providing content) to a user query in a user support system. In order to provide content, a keyword matching algorithm, statistical method (e.g., a trained BERT model), and data retrieval are each implemented to identify node(s) in a knowledge graph with encoded content relevant to the user's query. The implementation of the keyword matching algorithm, statistical method, and data retrieval results in a matching metric score, semantic score, and graph metric data, respectively. Each score associated with a node is combined to generate an overall score that can be used to rank nodes. Once the nodes are ranked, the top ranking nodes are displayed to the user for selection. Based on the selection, content encoded in the node is displayed to the user.

Abstract: Systems and methods for forecasting cashflows across one or more accounts of a user disclosed. One example method may include retrieving a data set for each of a plurality of accounts from a database, constructing a graph including a plurality of nodes linked together by a multitude of edges, wherein each node identifies a time series value corresponding to one of the accounts, and each edge indicates a time series value of a corresponding set of transactions occurring between a corresponding pair of accounts, determining a plurality of constraints, determining a specified loss function based on the plurality of constraints, back-propagating a derivative of the specified loss function into a deep neural network (DNN) to determine a set of neural network parameters, forecasting, using the DNN, a time sequence for one or more of the nodes and one or more of the edges, and providing the forecasted time sequences to the user.

Abstract: This disclosure relates to predictions based on a Bernoulli uncertainty characterization used in selecting between different prediction models. An example system is configured to perform operations including determining a prediction by a first prediction model. The first prediction model is associated with a loss function. The system is also configured to determine whether the prediction is associated with the first prediction model or a second prediction model based on a joint loss function. The second prediction model is associated with a likelihood function, and the joint loss function is based on the loss function and the likelihood function. The system is further configured to indicate the prediction to the user in response to determining that the prediction is associated with the first prediction model. If the prediction is associated with the second prediction model, the system may prevent indicating the prediction to the user.

Abstract: This disclosure relates to predictions based on a Bernoulli uncertainty characterization used in selecting between different prediction models. An example system is configured to perform operations including determining a prediction by a first prediction model. The first prediction model is associated with a loss function. The system is also configured to determine whether the prediction is associated with the first prediction model or a second prediction model based on a joint loss function. The second prediction model is associated with a likelihood function, and the joint loss function is based on the loss function and the likelihood function. The system is further configured to indicate the prediction to the user in response to determining that the prediction is associated with the first prediction model. If the prediction is associated with the second prediction model, the system may prevent indicating the prediction to the user.

Abstract: One embodiment provides a system that facilitates efficient collection of training data. During operation, the system obtains, by a recording device, a first image of a physical object in a scene which is associated with a three-dimensional (3D) world coordinate frame. The system marks, on the first image, a plurality of vertices associated with the physical object, wherein a vertex has 3D coordinates based on the 3D world coordinate frame. The system obtains a plurality of second images of the physical object in the scene while changing one or more characteristics of the scene. The system projects the marked vertices on to a respective second image to indicate a two-dimensional (2D) bounding area associated with the physical object.

Abstract: Certain aspects of the present disclosure provide techniques for mapping natural language to stored information. The method generally includes receiving a long-tail query comprising a natural language utterance from a user of an application associated with a set of topics and providing the natural language utterance to a natural language model configured to identify nodes of a knowledge graph. The method further includes, based on output of the natural language model, identifying a node of a knowledge graph associated with the natural language utterance, wherein the output of the natural language model includes a node identifier for the node of the knowledge graph and providing the node identifier to the knowledge engine. The method further includes receiving a response associated with the node of the knowledge graph from the knowledge engine and transmitting the response to the user in response to the long-tail query.

Abstract: One embodiment provides a system that facilitates efficient collection of training data. During operation, the system obtains, by a recording device, a first image of a physical object in a scene which is associated with a three-dimensional (3D) world coordinate frame. The system marks, on the first image, a plurality of vertices associated with the physical object, wherein a vertex has 3D coordinates based on the 3D world coordinate frame. The system obtains a plurality of second images of the physical object in the scene while changing one or more characteristics of the scene. The system projects the marked vertices on to a respective second image to indicate a two-dimensional (2D) bounding area associated with the physical object.

Abstract: Certain aspects of the present disclosure provide techniques for mapping natural language to stored information. The method generally includes receiving a long-tail query comprising a natural language utterance from a user of an application associated with a set of topics and providing the natural language utterance to a natural language model configured to identify nodes of a knowledge graph. The method further includes, based on output of the natural language model, identifying a node of a knowledge graph associated with the natural language utterance, wherein the output of the natural language model includes a node identifier for the node of the knowledge graph and providing the node identifier to the knowledge engine. The method further includes receiving a response associated with the node of the knowledge graph from the knowledge engine and transmitting the response to the user in response to the long-tail query.

Abstract: Certain aspects of the present disclosure provide techniques for processing natural language utterances in a knowledge graph. An example method generally includes receiving a long-tail query comprising a natural language utterance from a user of an application. Operands and operators are extracted from the natural language utterance using a natural language model. Operands may be mapped to nodes in a knowledge graph, the nodes representing values calculated from data input into the application, and operators may be mapped to operations to be performed on data extracted from the knowledge graph. The functions associated with the operators are executed using data extracted from the nodes in the knowledge graph associated with the operands to generate a query result. The query result is returned as a response to the received long-tail query.

Abstract: Certain aspects of the present disclosure provide techniques for optimizing results generated by functions executed using a rule-based knowledge graph. The method generally includes generating a neural network based on a knowledge graph and inputs for performing a function using the knowledge graph. Inputs for the function are received and used to generate a result of the function. A request to optimize the generated result of the function is received. A loss function is generated for the neural network. Generally, the loss function identifies a desired optimization for the function. Values of parameters in the neural network are adjusted to optimize the generated result based on the generated loss function, and the adjusted values of the parameters in the neural network are output in response to the request to optimize the generated result of the function.

Abstract: Certain aspects of the present disclosure provide techniques for node matching with accuracy by combining statistical methods with a knowledge graph to assist in responding (e.g., providing content) to a user query in a user support system. In order to provide content, a keyword matching algorithm, statistical method (e.g., a trained BERT model), and data retrieval are each implemented to identify node(s) in a knowledge graph with encoded content relevant to the user's query. The implementation of the keyword matching algorithm, statistical method, and data retrieval results in a matching metric score, semantic score, and graph metric data, respectively. Each score associated with a node is combined to generate an overall score that can be used to rank nodes. Once the nodes are ranked, the top ranking nodes are displayed to the user for selection. Based on the selection, content encoded in the node is displayed to the user.

Abstract: A method for generating a synthetic dataset involves generating discretized synthetic data based on driving a model of a cumulative distribution function (CDF) with random numbers. The CDF is based on a source dataset. The method further includes generating the synthetic dataset from the discretized synthetic data by selecting, for inclusion into the synthetic dataset, values from a multitude of entries of the source dataset, based on the discretized synthetic data, and providing the synthetic dataset to a downstream application that is configured to operate on the source dataset.

Abstract: Aspects of the present disclosure provide techniques for intent matching. Embodiments include receiving input of text by a user via a user interface. Embodiments include determining weights for portions of the text based on a plurality of keywords. Embodiment include generating an embedding of the text. Embodiments include determining an intent of the text by weighting, based on the weights, word mover's distances from the embedding of the text to a known embedding of known text associated with the intent in order to determine a similarity measure between the text and the known text. Embodiments include providing content to the user via the user interface based on the intent.

Abstract: Systems and methods for forecasting cashflows across one or more accounts of a user disclosed. One example method may include retrieving a data set for each of a plurality of accounts from a database, constructing a graph including a plurality of nodes linked together by a multitude of edges, wherein each node identifies a time series value corresponding to one of the accounts, and each edge indicates a time series value of a corresponding set of transactions occurring between a corresponding pair of accounts, determining a plurality of constraints, determining a specified loss function based on the plurality of constraints, back-propagating a derivative of the specified loss function into a deep neural network (DNN) to determine a set of neural network parameters, forecasting, using the DNN, a time sequence for one or more of the nodes and one or more of the edges, and providing the forecasted time sequences to the user.

Abstract: Certain aspects of the present disclosure provide techniques for mapping natural language to stored information. The method generally includes receiving a long-tail query comprising a natural language utterance from a user of an application associated with a set of topics and providing the natural language utterance to a natural language model configured to identify nodes of a knowledge graph. The method further includes, based on output of the natural language model, identifying a node of a knowledge graph associated with the natural language utterance, wherein the output of the natural language model includes a node identifier for the node of the knowledge graph and providing the node identifier to the knowledge engine. The method further includes receiving a response associated with the node of the knowledge graph from the knowledge engine and transmitting the response to the user in response to the long-tail query.

Abstract: One embodiment can provide a system for detecting outlines of objects in images. During operation, the system receives an image that includes at least one object, generates a random noise signal, and provides the received image and the random noise signal to a shape-regressor module, which applies a shape-regression model to predict a shape outline of an object within the received image.