Abstract: Techniques are disclosed herein for resolving date/time expressions while transforming natural language to a logical form such as a meaning representation language. A class label for a token in a natural language utterance and a meaning representation for the natural language utterance can be predicted. The class label can be associated with a date/time expression. The meaning representation can include an operator and a value. When the value associated with the class label matches a predetermined value type or the operator matches a predetermined operator, the value and/or the operator can be modified, and an executable statement can be generated for the meaning representation. A query on a computing system can be executed using the executable statement.

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 herein for implementing digital assistants using generative artificial intelligence. An input prompt comprising a natural language utterance and candidate agents and associated actions can be constructed. An execution plan can be generated using a first generative artificial model based on the input prompt. The execution plan can be executed to perform actions included in the execution plan using agents indicated by the execution plan. A response to the natural language utterance can be generated by a second generative artificial intelligence model using one or more outputs from executing the execution plan.

Abstract: Techniques are disclosed herein for generating and using a knowledge base of information extracted from documents. The techniques include accessing a document comprising text and dividing the document into a plurality of chunks of text. The chunks are indexed by storing each chunk mapped to respective identifying metadata including a chunk index for each chunk. A query is received and a chunk relevant to the query is identified. A prompt is formulated including the query, the identified relevant chunk, and a subsequent chunk. The prompt is provided to a language model and output is received from the language model based on the prompt. An answer to the query is returned based on the received output.

Abstract: Techniques are disclosed herein for selecting document chunks that are most relevant to a query. The techniques include receiving a query and comparing a plurality of stored text passages to the query using a first similarity metric. Based on the comparison, a subset of the plurality of stored text passages that are most similar to the query are selected. A plurality of sentences from the subset of the plurality of stored text passages are identified. The identified sentences are ranked based on the query and a second similarity metric. A subset of the sentences are selected based on the ranking. The subset of the sentences or a derivative thereof are output in response to the query.

Abstract: Techniques are disclosed herein for contextual query rewriting. The techniques include inputting a first user utterance and a conversation history to a first language model. The first language model identifies an ambiguity in the first user utterance and one or more terms in the conversation history to resolve the ambiguity, modifies the first user utterance to include the one or more terms identified to resolve the ambiguity to generate a modified utterance, and outputs the modified utterance. The computing system provides the modified utterance as input to a second language model. The second language model performs a natural language processing task based on the input modified utterance and outputs a result. The computing system outputs a response to the first user utterance based on the result.

Abstract: Techniques are disclosed for returning references associated with an answer to a query. The techniques include accessing a text portion and identifying a plurality of sentences in the text portion. Each of the sentences is embedded to generate a respective plurality of text sentence embeddings. The text portion or a derivative thereof and a query are provided to a language model and a response to the query based on the text portion is received from the language model. A plurality of sentences are identified in the response. The plurality of sentences in the response is embedded to generate a plurality of response embeddings. The response embeddings are compared to the sentence embeddings to generate a similarity score for each sentence embedding-response embedding pair. Based on the similarity scores, an indication of a subset of the plurality of sentences is output with the response to the query.

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.

Abstract: A method includes receiving an indication of a first coverage value corresponding to a desired overlap between a dataset of natural language phrases and a training dataset for training a machine learning model; determining a second coverage value corresponding to a measured overlap between the dataset of natural language phrases and the training dataset; determining a coverage delta value based on a comparison between the first coverage value and the second coverage value; modifying, based on the coverage delta value, the dataset of natural language phrases; and processing, utilizing a machine learning model including the modified dataset of natural language phrases, an input dataset including a set of input features. The machine learning model processes the input dataset based at least in part on the dataset of natural language phrases to generate an output dataset.

Abstract: Techniques are disclosed for systems including techniques for multi-feature balancing for natural langue processors. In an embodiment, a method includes receiving a natural language query to be processed by a machine learning model, the machine learning model utilizing a dataset of natural language phrases for processing natural language queries, determining, based on the machine learning model and the natural language query, a feature dropout value, generating, and based on the natural language query, one or more contextual features and one or more expressional features that may be input to the machine learning model, modifying at least one or the one or more contextual features and the one or more expressional features based on the feature dropout value to generate a set of input features for the machine learning model, and processing the set of input features to cause generating an output dataset for corresponding to the natural language query.

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 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 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 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 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: Techniques for data augmentation for training chatbot systems in natural language processing. In one particular aspect, a method is provided that includes generating a list of values to cover for an entity, selecting utterances from a set of data that have context for the entity, converting the utterances into templates, where each template of the templates comprises a slot that maps to the list of values for the entity, selecting a template from the templates, selecting a value from the list of values based on the mapping between the slot within the selected template and the list of values for the entity; and creating an artificial utterance based on the selected template and the selected value, where the creating the artificial utterance comprises inserting the selected value into the slot of the selected template that maps to the list of values for the entity.

Abstract: Techniques for data augmentation for training chatbot systems in natural language processing. In one particular aspect, a method is provided that includes generating a list of values to cover for an entity, selecting utterances from a set of data that have context for the entity, converting the utterances into templates, where each template of the templates comprises a slot that maps to the list of values for the entity, selecting a template from the templates, selecting a value from the list of values based on the mapping between the slot within the selected template and the list of values for the entity; and creating an artificial utterance based on the selected template and the selected value, where the creating the artificial utterance comprises inserting the selected value into the slot of the selected template that maps to the list of values for the entity.

Abstract: Techniques are provided for augmenting training data using gazetteers and perturbations to facilitate training named entity recognition models. The training data can be augmented by generating additional utterances from original utterances in the training data and combining the generated additional utterances with the original utterances to form the augmented training data. The additional utterances can be generated by replacing the named entities in the original utterances with different named entities and/or perturbed versions of the named entities in the original utterances selected from a gazetteer. Gazetteers of named entities can be generated from the training data and expanded by searching a knowledge base and/or perturbing the named entities therein. The named entity recognition model can be trained using the augmented training data.