Abstract: Aspects of the present disclosure provide techniques for machine learning and rules integration. Embodiments include receiving input values corresponding to a subset of a set of input variables associated with an automated determination. Embodiments include generating a directed acyclic graph (DAG) representing a set of constraints corresponding to the set of input variables. The set of constraints relate to one or more machine learning models and one or more rules. Embodiments include receiving one or more outputs from the one or more machine learning models based on one or more of the input values. Embodiments include determining outcomes for the one or more rules based on at least one of the input values. Embodiments include populating the DAG based on the input values, the one or more outputs, and the outcomes. Embodiments include making the automated determination based on logic represented by the DAG.

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: A method of blank detection involves receiving a document from a user, where the document includes derived text; applying a trained blank detection model to the document to make a first prediction, where the first prediction indicates whether at least one field in the document is blank; comparing the first prediction with a second prediction, where the second prediction is made by an extraction model; and extracting the at least one field using the extraction model.

Abstract: Systems and methods for recognizing domain specific named entities are disclosed. An example method may be performed by one or more processors of a text incorporation system and include extracting a number of terms from a text under consideration, identifying, among the number of terms, a set of unmatched terms that do not match any of a plurality of known terms, passing each respective unmatched term to a vectorization module, embedding a vectorized version of each respective unmatched term in a vector space, comparing each vectorized version to known term vectors, passing, to a machine learning model, candidate terms corresponding to known term vectors closest to the vectorized versions, identifying, using the machine learning model, a best candidate term for each respective unmatched term, mapping the best candidate terms to unmatched terms in the text under consideration, and incorporating the text under consideration into the system based on the mappings.

Abstract: Aspects of the present disclosure provide techniques for machine learning and rules integration. Embodiments include receiving input values corresponding to a subset of a set of input variables associated with an automated determination. Embodiments include generating a directed acyclic graph (DAG) representing a set of constraints corresponding to the set of input variables. The set of constraints relate to one or more machine learning models and one or more rules. Embodiments include receiving one or more outputs from the one or more machine learning models based on one or more of the input values. Embodiments include determining outcomes for the one or more rules based on at least one of the input values. Embodiments include populating the DAG based on the input values, the one or more outputs, and the outcomes. Embodiments include making the automated determination based on logic represented by the DAG.

Abstract: Certain aspects of the present disclosure provide techniques for extracting information, including receiving a document comprising a plurality of tokens, wherein each token is associated with position coordinates; determining a classification for at least one token; generating a plurality of key-value pairs based on the positional coordinates; analyzing each respective key-value pair of the plurality of key-value pairs based on whether a token of the two tokens of each respective key-value pair matches a type associated with the respective key-value pair; determining a correct key-value pair of the plurality of key-value pairs based on the correct key-value pair comprising a matched token that matches the type associated with the correct key-value pair; and providing the classification and the correct key-value pair to a component of an application associated with the document.

Abstract: Certain aspects of the present disclosure provide techniques for generating a compliance graph based on a compliance rule to implement in a software program product for determining user compliance. To generate a compliance graph, an encoder receives a compliance rule in a source language and generates a set of corresponding vectors. The decoder, which has been trained using verified training pairs and synthetic data, generates a sequence of operations based on the vectors from the encoder. The sequence of operations is the used to build a graph in which each operation is a node in the graph and each node is connected to at least one other node in the same graph or a separate graph.

Abstract: Systems and methods that may be used to determine that input form field data is accurate or not, and associate a level of confidence with that determination. The systems and methods may use a multi part confidence model that uses inter-field correlation to tie the correctness of a particular field to the pattern of values seen in other fields of the document the field data is input from.

Abstract: Systems and methods for recognizing domain specific named entities are disclosed. An example method may be performed by one or more processors of a text incorporation system and include extracting a number of terms from a text under consideration, identifying, among the number of terms, a set of unmatched terms that do not match any of a plurality of known terms, passing each respective unmatched term to a vectorization module, embedding a vectorized version of each respective unmatched term in a vector space, comparing each vectorized version to known term vectors, passing, to a machine learning model, candidate terms corresponding to known term vectors closest to the vectorized versions, identifying, using the machine learning model, a best candidate term for each respective unmatched term, mapping the best candidate terms to unmatched terms in the text under consideration, and incorporating the text under consideration into the system based on the mappings.

Abstract: A natural language processing method and system utilizes a combination of rules-based processes, vector-based processes, and machine learning-based processes to identify the meaning of terms extracted from data management system related text. Once the meaning of the terms has been identified, the method and system can automatically incorporate new forms and text into a data management system.

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 generating a compliance graph based on a compliance rule to implement in a software program product for determining user compliance. To generate a compliance graph, an encoder receives a compliance rule in a source language and generates a set of corresponding vectors. The decoder, which has been trained using verified training pairs and synthetic data, generates a sequence of operations based on the vectors from the encoder. The sequence of operations is the used to build a graph in which each operation is a node in the graph and each node is connected to at least one other node in the same graph or a separate graph.