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 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: 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 for augmenting training data include accessing training data comprising a plurality of training examples comprising a first training example comprising a first natural language utterance and a first logical form for the first natural language utterance. A second natural language utterance is generated by adding or replacing one or more values in the first natural language utterance. A logical form for the second natural language utterance is generated. A second training example is generated, comprising the second natural language utterance and the logical form for the second natural language utterance. The training data is augmented by adding the second training example to the plurality of training examples to generate an augmented training data set. A machine learning model is trained to generate logical forms for utterances using the augmented training data set.

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 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: 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: Techniques are disclosed herein for improving model robustness on operators and triggering keywords in natural language to a meaning representation language system. The techniques include augmenting an original set of training data for a target robustness bucket by leveraging a combination of two training data generation techniques: (1) modification of existing training examples and (2) synthetic template-based example generation. The resulting set of augmented data examples from the two training data generation techniques are appended to the original set of training data to generate an augmented training data set and the augmented training data set is used to train a machine learning model to generate logical forms for utterances.

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: 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 for augmenting training data include accessing training data comprising a plurality of training examples comprising a first training example comprising a first natural language utterance and a first logical form for the first natural language utterance. A second natural language utterance is generated by adding or replacing one or more values in the first natural language utterance. A logical form for the second natural language utterance is generated. A second training example is generated, comprising the second natural language utterance and the logical form for the second natural language utterance. The training data is augmented by adding the second training example to the plurality of training examples to generate an augmented training data set. A machine learning model is trained to generate logical forms for utterances using the augmented training data set.

Abstract: Techniques are disclosed herein for improving model robustness on operators and triggering keywords in natural language to a meaning representation language system. The techniques include augmenting an original set of training data for a target robustness bucket by leveraging a combination of two training data generation techniques: (1) modification of existing training examples and (2) synthetic template-based example generation. The resulting set of augmented data examples from the two training data generation techniques are appended to the original set of training data to generate an augmented training data set and the augmented training data set is used to train a machine learning model to generate logical forms for utterances.

Abstract: Techniques are disclosed for automatically generating Subjective, Objective, Assessment and Plan (SOAP) notes. Particularly, techniques are disclosed for training data collection and evaluation for automatic SOAP note generation. Training data is accessed, and evaluation process is performed on the training data to result in evaluated training data. A fine-tuned machine-learning model is generated using the evaluated training data. The fine-tuned machine-learning model can be used to perform a task associated with generating a SOAP note.

Abstract: Techniques are disclosed for automatically evaluating SOAP notes. A method comprises accessing a Subjective, Objective, Assessment and Plan (SOAP) note and a checklist that includes checklist facts; using a first machine-learning model prompt to extract SOAP note facts from the SOAP note; using one or more second machine-learning model prompts to generate feedback for the SOAP note, the feedback indicating whether individual checklist facts are supported by at least one of the SOAP note facts, and whether individual SOAP note facts are supported by at least one of the checklist facts; and generating a score for the SOAP note based on the feedback.

Abstract: Techniques are disclosed for automatically generating Subjective, Objective, Assessment and Plan (SOAP) notes. Particularly, techniques are disclosed for automatic SOAP note generation using task decomposition. A text transcript is accessed and segmented into portions. The text transcript can correspond to an interaction between a first entity and a second entity. Machine-learning model prompts are used to extract entities and facts for the respective portions and generate SOAP note sections based at least in-part on the facts. A SOAP note is generated by combining the SOAP note sections. The SOAP note can be stored in a database in association with at least one of the first entity and the second entity.

Abstract: Techniques are disclosed for automatically generating Subjective, Objective, Assessment and Plan (SOAP) notes. Particularly, techniques are disclosed for identifying entities for automatic SOAP note generation. A text transcript is accessed and segmented into portions. The text transcript can correspond to an interaction between a first entity and a second entity. Entities for the respective portions are identified using machine-learning models. A SOAP note is generated using the one or more machine-learning models and facts are derived from the text transcript based at least in-part on the entities. The SOAP note can be stored in a database in association with at least one of the first entity and the second entity.

Abstract: Techniques are disclosed for automatically generating prompts. A method comprises accessing first prompts, wherein each of the first prompts is a prompt for generating a portion of a SOAP note using a machine-learning model. For each respective first prompt of the first prompts: (i) using the respective first prompt to obtain a first result from a first machine-learning model, (ii) using the respective first prompt and the first result to obtain a second result from a second machine-learning model, the second result including an assessment of the first result, (iii) using the second result to obtain a third result from a third machine-learning model, the third result including a second prompt, (iv) setting the second prompt as the respective first prompt, (v) repeating steps (i)-(iv) a number of times to obtain a production prompt, (vi) adding the production prompt to a collection of prompts; and storing the collection of prompts.

Abstract: Techniques are disclosed for automatically generating Subjective, Objective, Assessment and Plan (SOAP) notes. Particularly, techniques are disclosed for identifying entities for automatic SOAP note generation. A text transcript is accessed and segmented into portions. The text transcript can correspond to an interaction between a first entity and a second entity. One or more entities for the respective portions are identified using one or more machine-learning models. Facts are from the respective portions using the one or more machine-learning models based at least in-part on the context of the respective portions. A SOAP note is generated using the one or more machine-learning models and based at least in-part on the facts. The SOAP note can be stored in a database in association with at least one of the first entity and the second entity.

Abstract: Techniques are disclosed herein for transforming natural language conversations into a visual output. In one aspect, a computer-implement method includes generating an input string by concatenating a natural language utterance with a schema representation comprising a set of entities for visualization actions, generating, by a first encoder of a machine learning model, one or more embeddings of the input string, encoding, by a second encoder of the machine learning model, relations between elements in the schema representation and words in the natural language utterance based on the one or more embeddings, generating, by a grammar-based decoder of the machine learning model and based on the encoded relations and the one or more embeddings, an intermediate logical form that represents at least the query, the one or more visualization actions, or the combination thereof, and generating, based on the intermediate logical form, a command for a computing system.