Abstract: Techniques are disclosed herein for integrating document question answering in an artificial intelligence-based platform, such as a chatbot system. The techniques include receiving a query from a user, rewriting the query to include one or more specific descriptors, computing an embedding vector for the rewritten query, retrieving one or more textual passages from a document store utilizing the embedding vector for the rewritten query, determining one or more answers to the rewritten query within the one or more textual passages, and returning the one or more answers.

Abstract: Techniques for using logit values for classifying utterances and messages input to chatbot systems in natural language processing. A method can include a chatbot system receiving an utterance generated by a user interacting with the chatbot system. The chatbot system can input the utterance into a machine-learning model including a set of binary classifiers. Each binary classifier of the set of binary classifiers can be associated with a modified logit function. The method can also include the machine-learning model using the modified logit function to generate a set of distance-based logit values for the utterance. The method can also include the machine-learning model applying an enhanced activation function to the set of distance-based logit values to generate a predicted output. The method can also include the chatbot system classifying, based on the predicted output, the utterance as being associated with the particular class.

Abstract: Techniques for maintaining list-type text formatting when converting content from a source content format to a destination content format are disclosed. A system generates text content by applying text formatting tags to segments of characters obtained from a source electronic document. The system parses a static-display type source electronic document to obtain character data of the characters in the source document. The system analyzes the parsed data to identify text arranged in a list-type text format in the source document. The system generates text content in a destination content format different from the source format by applying tags to segments of the text content designating the segments items in a list.

Abstract: Techniques are disclosed herein for objective function optimization in target based hyperparameter tuning. In one aspect, a computer-implemented method is provided that includes initializing a machine learning algorithm with a set of hyperparameter values and obtaining a hyperparameter objective function that comprises a domain score for each domain that is calculated based on a number of instances within an evaluation dataset that are correctly or incorrectly predicted by the machine learning algorithm during a given trial. For each trial of a hyperparameter tuning process: training the machine learning algorithm to generate a machine learning model, running the machine learning model in different domains using the set of hyperparameter values, evaluating the machine learning model for each domain, and once the machine learning model has reached convergence, outputting at least one machine learning model.

Abstract: Techniques are provided for using context tags in named-entity recognition (NER) models. In one particular aspect, a method is provided that includes receiving an utterance, generating embeddings for words of the utterance, generating a regular expression and gazetteer feature vector for the utterance, generating a context tag distribution feature vector for the utterance, concatenating or interpolating the embeddings with the regular expression and gazetteer feature vector and the context tag distribution feature vector to generate a set of feature vectors, generating an encoded form of the utterance based on the set of feature vectors, generating log-probabilities based on the encoded form of the utterance, and identifying one or more constraints for the utterance.

Abstract: Techniques are disclosed herein for continuous hyperparameter tuning with automatic domain weight adjustment based on periodic performance checkpoints. In one aspect, a method is provided that includes initializing a machine learning algorithm with a set of hyperparameter values and obtaining a hyperparameter objective function that is defined at least in part on a plurality of domains of a search space that is associated with the machine learning algorithm. For each trial of a hyperparameter tuning process: running the machine learning algorithm in different domains using the set of hyperparameter values, periodically checking a performance of the machine learning algorithm in the different domains based on the hyperparameter objective function; and continuing hyperparameter tuning with a new set of hyperparameter values after automatically adjusting the domain weights according to a regression status of the different domains.

Abstract: Techniques for automatically switching between chatbot skills in the same domain. In one particular aspect, a method is provided that includes receiving an utterance from a user within a chatbot session, where a current skill context is a first skill and a current group context is a first group, inputting the utterance into a candidate skills model for the first group, obtaining, using the candidate skills model, a ranking of skills within the first group, determining, based on the ranking of skills, a second skill is a highest ranked skill, changing the current skill context of the chatbot session to the second skill, inputting the utterance into a candidate flows model for the second skill, obtaining, using the candidate flows model, a ranking of intents within the second skill that match the utterance, and determining, based on the ranking of intents, an intent that is a highest ranked intent.

Abstract: Techniques for generating text content arranged in a consistent read order from a source document including text corresponding to different read orders are disclosed. A system parses a binary file representing an electronic document to identify characters and metadata associated with the characters. The system pre-sorts a character order of characters in each line of the electronic document to generate an ordered list of characters arranged according to the right-to-left reading order. The system performs a layout-mirroring operation to change a position of characters within the modified document relative to a right edge of the document and a left edge of the document. Subsequent to performing layout-mirroring, the system identifies native left-to-right reading-order text in-line with the native right-to-left reading-order text.

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 for generating formatting tags for textual content obtained from a source electronic document are disclosed. A system parses a digital file to obtain information about characters in an electronic document. The system applies tags to text generated based on the textual content of the electronic document by creating segments of textually-consecutive characters and applying corresponding text formatting style tags to the segments. The system further identifies segments of text overlapping bounding boxes in the electronic document. The system generates textual content including a segment of text and a corresponding hyperlink associated with the segment of text. The system further generates textual content by selectively applying line breaks from the source electronic document in the textual content.

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 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 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 training and deploying a named entity recognition model. The techniques include implementing a nested labeling scheme for named entities within the training data and then training a machine learning model on the training data The techniques further include extracting an entity hierarchy for a predicted class based on a hierarchical template associated with a composite label, where the predicted class is representative of multiple named entity classes comprising at least a parent class and a child class associated with the composite label. The techniques further include increasing the volume of training data via data mining for sequence tags in a language corpus and then training a machine learning model on the training data.

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: Systems and methods fine-tune a pretrained machine learning model. For a model having multiple layers, an initial set of configurations is identified, each configuration establishing layers to be frozen and layers to be fine-tuned. A configuration that is optimized with respect to one or more parameters is selected, establishing a set of fine-tuning layers and a set of frozen layers. An input for the model is provided to a remote system. An output of the set of frozen layers of the model, given the provided input, is received back and locally stored. The set of fine-tuning layers of the model is loaded from the remote system. The model is fine-tuned by retrieving the locally stored output of the set of frozen layers, and updating weights associated with the set of fine-tuning layers of the machine learning model.

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 generating text content arranged in a consistent read order from a source document including text corresponding to different read orders are disclosed. A system parses a binary file representing an electronic document to identify characters and metadata associated with the characters. The system pre-sorts a character order of characters in each line of the electronic document to generate an ordered list of characters arranged according to the right-to-left reading order. The system performs a layout-mirroring operation to change a position of characters within the modified document relative to a right edge of the document and a left edge of the document. Subsequent to performing layout-mirroring, the system identifies native left-to-right reading-order text in-line with the native right-to-left reading-order text.

Abstract: Disclosed herein are techniques for using a generative adversarial network (GAN) to train a semantic parser of a dialog system. A method described herein involves accessing seed data that includes seed tuples. Each seed tuple includes a respective seed utterance and a respective seed logical form corresponding to the respective seed utterance. The method further includes training a semantic parser and a discriminator in a GAN. The semantic parser learns to map utterances to logical forms based on output from the discriminator, and the discriminator learns to recognize authentic logical forms based on output from the semantic parser. The semantic parser may then be integrated into a dialog system.

Abstract: An augmentation and feature caching subsystem is described for training AI/ML models. In one particular aspect, a method is provided that includes receiving data comprising training examples, one or more augmentation configuration hyperparameters and one or more feature extraction configuration hyperparameters; generating a first key based on one of the training examples and the one or more augmentation configuration hyperparameters; searching a first key-value storage based on the first key; obtaining one or more augmentations based on the search of the first key-value storage; applying the obtained one or more augmentations to the training examples to result in augmented training examples; generating a second key based on one of the augmented training examples and the one or more feature extraction configuration hyperparameters; searching a second key-value storage based on the second key; obtaining one or more features based on the search of the second key-value storage.