Oracle International Corporation

Ariel Gedaliah Kobren

Michael Louis Wick

Naveen Jafer Nizar

Swetasudha Panda

Stephen Joseph Green

Jean-Baptiste Frederic George Tristan

Jason Anthony Peck

Qinlan Shen

Online post-processing may be performed for rankings generated with constrained utility maximization. A stream of data items may be received. A batch of data items from the stream may be ranked according to a ranking model trained to rank data items in a descending order of relevance. The batch of data items may be associated with a current time step. A re-ranking model may be applied to generate a re-ranking of the batch of data items according to a re-ranking policy that considers the current batch and previous batches with regard to a ranking constraint. The re-ranked items may then be sent to an application.

Online post-processing in rankings for constrained utility maximization

A target set of texts, for training and/or evaluating a text classification model, is augmented using insertions into a base text within the original target set. In an embodiment, an expanded text, including the base text and an insertion word, must satisfy one or more inclusion criteria in order to be added to the target set. The inclusion criteria may require that the expanded text constitutes a successful attack on the classification model, the expanded text has a satisfactory perplexity score, and/or the expanded text is verified as being valid. In an embodiment, if a number of expanded texts added into the target set is below a threshold number, insertions are made into an expanded text (which was generated based on the base text). Inclusion criteria are evaluated against the doubly-expanded text to determine whether to add the doubly-expanded text to the target set.

Augmented training set or test set for improved classification model robustness

Techniques are described for identifying successful adversarial attacks for a black box reading comprehension model using an extracted white box reading comprehension model. The system trains a white box reading comprehension model that behaves similar to the black box reading comprehension model using the set of queries and corresponding responses from the black box reading comprehension model as training data. The system tests adversarial attacks, involving modified informational content for execution of queries, against the trained white box reading comprehension model. Queries used for successful attacks on the white box model may be applied to the black box model itself as part of a black box improvement process.

Extracted model adversaries for improved black box attacks

Techniques are disclosed for augmenting data sets used for training machine learning models and for generating predictions by trained machine learning models. These techniques may increase a number and diversity of examples within an initial training dataset of sentences by extracting a subset of words from the existing training dataset of sentences. The techniques may conserve scarce sample data in few-shot situations by training a data generation model using general data obtained from a general data source.

Guided augmentation of data sets for machine learning models

Debiasing pre-trained sentence encoders with probabilistic dropouts may be performed by various systems, services, or applications. A sentence may be received, where the words of the sentence may be provided as tokens to an encoder of a machine learning model. A token-wise correlation using semantic orientation may be determined to determine a bias score for the tokens in the input sentence. A probability of dropout that for tokens in the input sentence may be determined from the bias scores. The machine learning model may be trained or tuned based on the probabilities of dropout for the tokens in the input sentence.

Growing community of inventors

Cambridge, MA, United States of America

Ariel Gedaliah Kobren