Oracle International Corporation

Michael Louis Wick

Jean-Baptiste Frederic George Tristan

Swetasudha Panda

Adam Pocock

Stephen Joseph Green

Jean-Baptiste Tristan

Pallika Haridas Kanani

Ariel Gedaliah Kobren

Katherine Silverstein

Jason Anthony Peck

Guy L Steele

Manzil Zaheer

Jay Yoon Lee

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 method for training a language model using negative data may include accessing a first training corpus comprising positive training data and accessing a second training corpus comprising negative training data. The method may further include training a first language model using at least the first training corpus, the second training corpus, and a maximum likelihood function. The maximum likelihood function may maximize the likelihood of the first language model predicting the positive training data while minimizing the likelihood of the first language model predicting the negative training data.

Removing undesirable signals from language models using negative data

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

Fairness of a trained classifier may be ensured by generating a data set for training, the data set generated using input data points of a feature space including multiple dimensions and according to different parameters including an amount of label bias, a control for discrepancy between rarity of features, and an amount of selection bias. Unlabeled data points of the input data comprising unobserved ground truths are labeled according to the amount of label bias and the input data sampled according to the amount of selection bias and the control for the discrepancy between the rarity of features. The classifier is then trained using the sampled and labeled data points as well as additional unlabeled data points. The trained classifier is then usable to determine unbiased classifications of one or more labels for one or more other data sets.

Enforcing fairness on unlabeled data to improve modeling performance

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.

Debiasing pre-trained sentence encoders with probabilistic dropouts

A Bayesian test of demographic parity for learning to rank may be applied to determine ranking modifications. A fairness control system receiving a ranking of items may apply Bayes factors to determine a likelihood of bias for the ranking. These Bayes factors may include a factor for determining bias in each item and a factor for determining bias in the ranking of the items. An indicator of bias may be generated using the applied Bayes factors and the fairness control system may modify the ranking if the determines likelihood of bias satisfies modification criteria for the ranking.

Control system for learning to rank fairness

A first set and a second set are identified as operands for a set operation of a similarity analysis task iteration. Using respective minimum hash information arrays and contributor count arrays of the two sets, a minimum hash information array and contributor count array of a derived set resulting from the set operation is generated. An entry in the contributor count array of the derived set indicates the number of child sets of the derived set that meet a criterion with respect to a corresponding entry in the minimum hash information array of the derived set. The generated minimum hash information array and the contributor count array are stored as part of input for a subsequent iteration. After a termination criterion of the task is met, output of the task is stored.

Similarity analysis using enhanced MinHash

According to embodiments, a recurrent neural network (RNN) is equipped with a set data structure whose operations are differentiable, which data structure can be used to store information for a long period of time. This differentiable set data structure can 'remember' an event in the sequence of sequential data that may impact another event much later in the sequence, thereby allowing the RNN to classify the sequence based on many kinds of long dependencies. An RNN that is equipped with the differentiable set data structure can be properly trained with backpropagation and gradient descent optimizations. According to embodiments, a differentiable set data structure can be used to store and retrieve information with a simple set-like interface. According to further embodiments, the RNN can be extended to support several add operations, which can make the differentiable set data structure behave like a Bloom filter.

Differentiable set to increase the memory capacity of recurrent neural net works

Embodiments employ an inference method for neural networks that enforces deterministic constraints on outputs without performing post-processing or expensive discrete search over the feasible space. Instead, for each input, the continuous weights are nudged until the network's unconstrained inference procedure generates an output that satisfies the constraints. This is achieved by expressing the hard constraints as an optimization problem over the continuous weights and employing backpropagation to change the weights of the network. Embodiments optimize over the energy of the violating outputs; since the weights directly determine the output through the energy, embodiments are able to manipulate the unconstrained inference procedure to produce outputs that conform to global constraints.

When output units must obey hard constraints

A method of evaluating a language model using negative data may include accessing a first language model that is trained using a first training corpus, and accessing a second language model. The second language model may be configured to generate outputs that are less grammatical than outputs generated by the first language model. The method may also include training the second language model using a second training corpus, and generating output text from the second language model. The method may further include testing the first language model using the output text from the second language model.

Evaluating language models using negative data

Systems and methods are disclosed to build and execute a decision system based on multiple machine learned decision models. In embodiments, the decision system performs a hashing technique to reduce relevant features of the input data into a feature vector for each decision model. The feature vector reduces the dimensionality of the feature universe of the input data, and its use allows the decision models to be trained and executed using less computing resources. In embodiments, the decision system implements an ensembled decision model that makes decisions based on a combination function that combines the decision results of the individual models in the ensemble. The decision models employ different hashing techniques to hash the input features differently, so that errors caused by the feature hashing of individual models are reduced in the aggregate.

Ensembled decision systems using feature hashing models

A scalable hierarchical coreference method that employs a homomorphic compression scheme that supports addition and partial subtraction to more efficiently represent the data and the evolving intermediate results of probabilistic inference. The method may encode the features underlying conditional random field models of coreference resolution so that cosine similarities can be efficiently computed. The method may be applied to compressing features and intermediate inference results for conditional random fields. The method may allow compressed representations to be added and subtracted in a way that preserves the cosine similarities.

Systems and methods for scalable hierarchical coreference

A system is provided that extracts attribute values. The system receives data including unstructured text from a data store. The system further tokenizes the unstructured text into tokens, where a token is a character of the unstructured text. The system further annotates the tokens with attribute labels, where an attribute label for a token is determined, in least in part, based on a word that the token originates from within the unstructured text. The system further groups the tokens into text segments based on the attribute labels, where a set of tokens that are annotated with an identical attribute label are grouped into a text segment, and where the text segments define attribute values. The system further stores the attribute labels and the attribute values within the data store.

Growing community of inventors

Medford, MA, United States of America

Michael Louis Wick