Oracle International Corporation

Voicebox Technologies Corporation

Mark Edward Johnson

Thanh Long Duong

Vishal Vishnoi

Elias Luqman Jalaluddin

Cong Duy Vu Hoang

Srinivasa Phani Kumar Gadde

Balakota Srinivas Vinnakota

Poorya Zaremoodi

Vladislav Blinov

Yu-Heng Hong

Tuyen Quang Pham

Ying Xu

Xu Zhong

Yakupitiyage Don Thanuja Samodhye Dharmasiri

Duy Vu

Aashna Devang Kanuga

Thanh Tien Vu

Manish Parekh

Crystal C Pan

Vishank Bhatia

Gautam Singaraju

Nitika Mathur

Gioacchino Tangari

Xin Xu

Shivashankar Subramanian

Budhaditya Saha

Philip Arthur

Serge Le Huitouze

Dai Hoang Tran

Steve Wai-Chun Siu

Sagar Gollamudi

Vu Cong Duy Hoang

Yuanxu Wu

Vladislavs Dovgalecs

Guy Bashkansky

Jason Eric Black

Ahmed Ataallah Ataallah Abobakr

Andrew David Bleeker

Michael R Kennewick, Sr

Shashi Prasad Suravarapu

King-Hwa Lee

Adam Pocock

Jae Min John

Katherine Silverstein

Omid Mohamad Nezami

Nagaraj N Bhat

Glen Pink

Varsha Kuppur Rajendra

Philip Cohen

Chang Xu

Christopher Kennewick

Syed Najam Abbas Zaidi

Zikai Li

Shaoke Xu

Hongtao Yang

Dominique Estival

Hadi Afshar

Long Duong

Umanga Bista

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.

Using a generative adversarial network to train a semantic parser of a dialog system

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.

Model robustness on operators and triggering keywords in natural language to a meaning representation language system

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.

Calibrating confidence scores of a machine learning model trained as a natural language interface

Techniques are disclosed for training a model, using multi-task learning, to transform natural language to a logical form. In one particular aspect, a method includes accessing a first set of utterances that have non-follow-up utterances and a second set of utterances that have initial utterances and associated one or more follow-up utterances and training a model for translating an utterance to a logical form. The training is a joint training process that includes calculating a first loss for a first semantic parsing task based on one or more non-follow-up utterances from the first set of utterances, calculating a second loss for a second semantic parsing task based on one or more initial utterances and associated one or more follow-up utterances from the second set of utterances, combining the first and second losses to obtain a final loss, and updating model parameters of the model based on the final loss.

Transforming natural language to structured query language based on multi- task learning and joint training

Techniques are provided for generating training data to facilitate fine-tuning embedding models. Training data including anchor utterances is obtained. Positive utterances and negative utterances are generated from the anchor utterances. Tuples including the anchor utterances, the positive utterances, and the negative utterances are formed. Embeddings for the tuples are generated and a pre-trained embedding model is fine-tuned based on the embeddings. The fine-tuned model can be deployed to a system.

Training data generation to facilitate fine-tuning embedding models

Techniques for augmentation and batch balancing of training data to enhance negation and fairness of a machine learning model. In one particular aspect, a method is provided that includes generating a list of demographic words associated with a demographic group, searching an unlabeled corpus of text to identify unlabeled examples in a target domain comprising at least one demographic word from the list of demographic words, rewriting the unlabeled examples to create one or more versions of each of the unlabeled examples and generate a fairness invariance data set, and training the machine learning model using unlabeled examples from the fairness invariance data set.

Data augmentation and batch balancing methods to enhance negation and fairness

A data corpus is partitioned into text strings for header classification. A group characteristic is computed for a text string, and whether the group characteristic satisfies a group characteristic criterion is determined. The text string may be disqualified from header classification if the group characteristic criterion is not satisfied, or one or more font characteristics may be determined for the text string if the group characteristic criterion is satisfied. A font characteristic that meets one or more prevalence criteria may be identified and evaluated to determine whether the font characteristic meets at least one font characteristic criterion. The text string may be disqualified from header classification if the font characteristic criterion is not satisfied, or if the font characteristic meets the font characteristic criterion, the text string is classified as a header, and tagged content is generated by applying a header tag to the text string.

Identifying and formatting headers for text content

Techniques are provided for improved training of a machine-learning model that includes multiple layers and is configured to process textual language input. The machine-learning model includes one or more blocks in which each block includes a multi-head self-attention network, a first connection for providing input to the multi-head self-attention network, and a second (residual) connection for providing the input to a normalization layer, bypassing the multi-head self-attention network. During training, the second connection is dropped out according to a dropout parameter. Additionally, or alternatively, an attention weight matrix is used for dropout by blocking diagonal entries in the attention weight matrix. As a result, the machine-learning model increasingly focuses on contextual information, which provides more accurate language processing results.

Path dropout for natural language processing

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.

Transforming natural language to structured query language based on scalable search and content-based schema linking

Techniques are disclosed for tuning hyperparameters of a model. Datasets are obtained for training the model and metrics are selected for evaluating performance of the model. Each metric is assigned a weight specifying an importance to the performance of the model. A function is created that measures performance based on the weighted metrics. Hyperparameters are tuned to optimize the model performance. Tuning the hyperparameters includes: (i) training the model that is configured based on a current values for the hyperparameters; (ii) evaluating a performance of the model using the function; (iii) determining whether the model is optimized for the metrics; (iv) in response to the model not being optimized, searching for a new values for the hyperparameters, reconfiguring the model with the new values, and repeating steps (i)-(iii) using the reconfigured model; and (v) in response to the model being optimized for the metrics, providing a trained model.

Method and system for constraint based hyperparameter tuning

Techniques for adjusting outlier datasets for training chatbot systems in natural language processing are disclosed. In one particular aspect, a method is provided that includes receiving a dataset that includes training or inference data. An initial set of outlier data points can be identified within the dataset based on a score of the outlier data points being above or below a threshold. The initial set can be adjusted by identifying one or more nearest neighbors, which can be included in the dataset. Outlier data points that include a label that matches a number of labels of the nearest neighbors that exceeds a predetermined threshold can be removed from the initial set of outlier data points to generate a final set. Outlier data points of the final set can be adjusted with respect to the dataset to generate a set of training data that is used to train a machine-learning model.

Adjusting outlier data points for training a machine-learning model

Deep learning techniques are disclosed for extraction of embedded data from documents. In an exemplary technique, a set of unstructured text data is received. One or more text groupings are generated by processing the set of unstructured text data. One or more text grouping embeddings are generated in a format for input to a machine learning model based on the one or more generated text groupings. One or more output predictions are generated by inputting the one or more text grouping embeddings into the machine learning model. Each output prediction of the one or more output predictions correspond to a predicted aspect of a text grouping of the one or more text groupings.

Deep learning techniques for extraction of embedded data from documents

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.

Context tag integration with named entity recognition models

Techniques for improving a semantic parser of a dialog system, by breaking the semantic parser into a coarse semantic parser and a fine semantic parser, are described. A method described herein includes accessing an utterance received in a dialog system. The utterance is a text-based natural language expression. The method further includes applying a coarse semantic parser to the utterance to determine an intermediate logical form for the utterance. The intermediate logical form indicates one or more intents in the utterance. The method further includes applying a fine semantic parser to the intermediate logical form to determine a logical form for the utterance. The logical form is a syntactic expression of the utterance according to an established grammar, and the logical form includes one or more parameters of the one or more intents. The logical form can be used to conduct a dialog with a user of the dialog system.

Semantic parser including a coarse semantic parser and a fine semantic parser

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.

Data manufacturing frameworks for synthesizing synthetic training data to facilitate training a natural language to logical form model

Growing community of inventors

Castle Cove, Australia

Mark Edward Johnson