Patents by Inventor Cicero Nogueira Dos Santos
Cicero Nogueira Dos Santos has filed for patents to protect the following inventions. This listing includes patent applications that are pending as well as patents that have already been granted by the United States Patent and Trademark Office (USPTO).
-
Patent number: 11645555Abstract: A machine learning system that implements Sobolev Independence Criterion (SIC) for feature selection is provided. The system receives a dataset including pairings of stimuli and responses. Each stimulus includes multiple features. The system generates a correctly paired sample of stimuli and responses from the dataset by pairing stimuli and responses according to the pairings of stimuli and responses in the dataset. The system generates an alternatively paired sample of stimuli and responses from the dataset by pairing stimuli and responses differently than the pairings of stimuli and responses in the dataset. The system determines a witness function and a feature importance distribution across the features that optimizes a cost function that is evaluated based on the correctly paired and alternatively paired samples of the dataset. The system selects one or more features based on the computed feature importance distribution.Type: GrantFiled: October 12, 2019Date of Patent: May 9, 2023Assignee: INTERNATIONAL BUSINESS MACHINES CORPORATIONInventors: Youssef Mroueh, Tom Sercu, Mattia Rigotti, Inkit Padhi, Cicero Nogueira Dos Santos
-
Patent number: 11481626Abstract: A computer-implemented method according to one aspect includes training a latent variable model (LVM), utilizing labeled data and unlabeled data within a data set; training a classifier, utilizing the labeled data and associated labels within the data set; and generating new data having a predetermined set of labels, utilizing the trained LVM and the trained classifier.Type: GrantFiled: October 15, 2019Date of Patent: October 25, 2022Assignee: International Business Machines CorporationInventors: Payel Das, Tom D. J. Sercu, Kahini Wadhawan, Cicero Nogueira Dos Santos, Inkit Padhi, Sebastian Gehrmann
-
Patent number: 11481416Abstract: Mechanisms are provided for implementing a Question Answering (QA) system utilizing a trained generator of a generative adversarial network (GAN) that generates a bag-of-ngrams (BoN) output representing unlabeled data for performing a natural language processing operation. The QA system obtains a plurality of candidate answers to a natural language question, where each candidate answer comprises one or more ngrams. For each candidate answer, a confidence score is generated based on a comparison of the one or more ngrams in the candidate answer to ngrams in the BoN output of the generator neural network of the GAN. A final answer to the input natural language question is selected from the plurality of candidate answers based on the confidence scores associated with the candidate answers, and is output.Type: GrantFiled: July 12, 2018Date of Patent: October 25, 2022Assignee: International Business Machines CorporationInventors: Dheeru Dua, Cicero Nogueira Dos Santos, Bowen Zhou
-
Patent number: 11475067Abstract: Techniques for generation of synthetic queries from customer data for training of document querying machine learning (ML) models as a service are described. A service may receive one or more documents from a user, generate a set of question and answer pairs from the one or more documents from the user using a machine learning model trained to predict a question from an answer, and store the set of question and answer pairs generated from the one or more documents from the user. The question and answer pairs may be used to train another machine learning model, for example, a document ranking model, a passage ranking model, a question/answer model, or a frequently asked question (FAQ) model.Type: GrantFiled: November 27, 2019Date of Patent: October 18, 2022Assignee: Amazon Technologies, Inc.Inventors: Cicero Nogueira Dos Santos, Xiaofei Ma, Peng Xu, Ramesh M. Nallapati, Bing Xiang, Sudipta Sengupta, Zhiguo Wang, Patrick Ng
-
Patent number: 11373760Abstract: A machine learning system receives a witness function that is determined based on an initial sample of a dataset comprising multiple pairs of stimuli and responses. Each stimulus includes multiple features. The system receives a holdout sample of the dataset comprising one or more pairs of stimuli and responses that are not used to determine the witness function. The system generates a simulated sample based on the holdout sample. Values of a particular feature of the stimuli of the simulated sample are predicted based on values of features other than the particular feature of the stimuli of the simulated sample. The system applies the holdout sample to the witness function to obtain a first result. The system applies the simulated sample to the witness function to obtain a second result. The system determines whether to select the particular feature based on a comparison between the first result and the second result.Type: GrantFiled: October 12, 2019Date of Patent: June 28, 2022Assignee: INTERNATIONAL BUSINESS MACHINES CORPORATIONInventors: Youssef Mroueh, Tom Sercu, Mattia Rigotti, Inkit Padhi, Cicero Nogueira Dos Santos
-
Patent number: 11281976Abstract: Mechanisms are provided to implement a generative adversarial network (GAN) for natural language processing. With these mechanisms, a generator neural network of the GAN is configured to generate a bag-of-ngrams (BoN) output based on a noise vector input and a discriminator neural network of the GAN is configured to receive a BoN input, where the BoN input is either the BoN output from the generator neural network or a BoN input associated with an actual portion of natural language text. The mechanisms further configure the discriminator neural network of the GAN to output an indication of a probability as to whether the input BoN is from the actual portion of natural language text or is the BoN output of the generator neural network.Type: GrantFiled: July 12, 2018Date of Patent: March 22, 2022Assignee: International Business Machines CorporationInventors: Dheeru Dua, Cicero Nogueira Dos Santos, Bowen Zhou
-
Publication number: 20210366580Abstract: Techniques for filtering artificial intelligence (AI)-designed molecules for laboratory testing provided. According to an embodiment, computer implemented method can comprise selecting, by a system operatively coupled to a processor, a first subset of AI-designed molecules from a set of AI-designed molecules as candidate pharmaceutical agents based on classification of the AI-designed molecules using one or more classifiers. The method further comprises selecting, by the system, a second subset of the candidate pharmaceutical agents for wet laboratory testing based on evaluation of molecular interactions between the candidate pharmaceutical agents and one or more biological targets using one or more computer simulations.Type: ApplicationFiled: May 21, 2020Publication date: November 25, 2021Inventors: Payel Das, Flaviu Cipcigan, Kahini Wadhawan, Inkit Padhi, Enara C Vijil, Pin-Yu Chen, Aleksandra Mojsilovic, Tom D.J. Sercu, Cicero Nogueira dos Santos
-
Patent number: 11170270Abstract: Techniques for content generation are provided. A plurality of discriminative terms is determined based at least in part on a first plurality of documents that are related to a first concept, and a plurality of positive exemplars and a plurality of negative exemplars are identified using the plurality of discriminative terms. A first machine learning (ML) model is trained to classify images into concepts, based on the plurality of positive exemplars and the plurality of negative exemplars. A second concept related to the first concept is then determined, based on the first ML model. A second ML model is trained to generate images based on the second concept, and a first image is generated using the second ML model. The first image is then refined using a style transfer ML model that was trained using a plurality of style images.Type: GrantFiled: October 17, 2019Date of Patent: November 9, 2021Assignee: International Business Machines CorporationInventors: Michele Merler, Mauro Martino, Cicero Nogueira Dos Santos, Alfio Massimiliano Gliozzo, John R. Smith
-
Publication number: 20210157857Abstract: Techniques for generation of synthetic queries from customer data for training of document querying machine learning (ML) models as a service are described. A service may receive one or more documents from a user, generate a set of question and answer pairs from the one or more documents from the user using a machine learning model trained to predict a question from an answer, and store the set of question and answer pairs generated from the one or more documents from the user. The question and answer pairs may be used to train another machine learning model, for example, a document ranking model, a passage ranking model, a question/answer model, or a frequently asked question (FAQ) model.Type: ApplicationFiled: November 27, 2019Publication date: May 27, 2021Inventors: Cicero NOGUEIRA DOS SANTOS, Xiaofei MA, Peng XU, Ramesh M. NALLAPATI, Bing XIANG, Sudipta SENGUPTA, Zhiguo WANG, Patrick NG
-
Publication number: 20210117736Abstract: Techniques for content generation are provided. A plurality of discriminative terms is determined based at least in part on a first plurality of documents that are related to a first concept, and a plurality of positive exemplars and a plurality of negative exemplars are identified using the plurality of discriminative terms. A first machine learning (ML) model is trained to classify images into concepts, based on the plurality of positive exemplars and the plurality of negative exemplars. A second concept related to the first concept is then determined, based on the first ML model. A second ML model is trained to generate images based on the second concept, and a first image is generated using the second ML model. The first image is then refined using a style transfer ML model that was trained using a plurality of style images.Type: ApplicationFiled: October 17, 2019Publication date: April 22, 2021Inventors: Michele Merler, Mauro Martino, Cicero NOGUEIRA DOS SANTOS, Alfio Massimiliano Gliozzo, John R. Smith
-
Publication number: 20210110285Abstract: A machine learning system that implements Sobolev Independence Criterion (SIC) for feature selection is provided. The system receives a dataset including pairings of stimuli and responses. Each stimulus includes multiple features. The system generates a correctly paired sample of stimuli and responses from the dataset by pairing stimuli and responses according to the pairings of stimuli and responses in the dataset. The system generates an alternatively paired sample of stimuli and responses from the dataset by pairing stimuli and responses differently than the pairings of stimuli and responses in the dataset. The system determines a witness function and a feature importance distribution across the features that optimizes a cost function that is evaluated based on the correctly paired and alternatively paired samples of the dataset. The system selects one or more features based on the computed feature importance distribution.Type: ApplicationFiled: October 12, 2019Publication date: April 15, 2021Inventors: Youssef Mroueh, Tom Sercu, Mattia Rigotti, Inkit Padhi, Cicero Nogueira Dos Santos
-
Publication number: 20210110409Abstract: A machine learning system receives a witness function that is determined based on an initial sample of a dataset comprising multiple pairs of stimuli and responses. Each stimulus includes multiple features. The system receives a holdout sample of the dataset comprising one or more pairs of stimuli and responses that are not used to determine the witness function. The system generates a simulated sample based on the holdout sample. Values of a particular feature of the stimuli of the simulated sample are predicted based on values of features other than the particular feature of the stimuli of the simulated sample. The system applies the holdout sample to the witness function to obtain a first result. The system applies the simulated sample to the witness function to obtain a second result. The system determines whether to select the particular feature based on a comparison between the first result and the second result.Type: ApplicationFiled: October 12, 2019Publication date: April 15, 2021Inventors: Youssef Mroueh, Tom Sercu, Mattia Rigotti, Inkit Padhi, Cicero Nogueira Dos Santos
-
Publication number: 20210110255Abstract: A computer-implemented method according to one aspect includes training a latent variable model (LVM), utilizing labeled data and unlabeled data within a data set; training a classifier, utilizing the labeled data and associated labels within the data set; and generating new data having a predetermined set of labels, utilizing the trained LVM and the trained classifier.Type: ApplicationFiled: October 15, 2019Publication date: April 15, 2021Inventors: Payel Das, Tom D. J. Sercu, Kahini Wadhawan, Cicero Nogueira Dos Santos, Inkit Padhi, Sebastian Gehrmann
-
Patent number: 10902345Abstract: A computer-implemented method includes extracting a plurality of topics from a plurality of unlabeled social media posts, mapping the plurality of topics to a plurality of frequencies, each frequency in the plurality of frequencies indicating how often a corresponding topic in the plurality of topics occurs in the plurality of unlabeled social media posts, and predicting, based in part on the plurality of frequencies, a future social media posting behavior of a specific social media user, wherein the future social media posting behavior includes a specific topic about which the specific social media user is likely to post at a time in the future and a frequency with which the specific topic is likely to occur in posts of the specific social media user that are created at the time in the future.Type: GrantFiled: January 19, 2017Date of Patent: January 26, 2021Assignee: International Business Machines CorporationInventors: Paulo Rodrigo Cavalin, Maira Gatti de Bayser, Alexandre Rademaker, Cicero Nogueira Dos Santos
-
Publication number: 20200342361Abstract: A method, system and apparatus of ensembling, including inputting a set of models that predict different sets of attributes, determining a source set of attributes and a target set of attributes using a barycenter with an optimal transport metric, and determining a consensus among the set of models whose predictions are defined on the source set of attributes.Type: ApplicationFiled: April 29, 2019Publication date: October 29, 2020Inventors: Youssef Mroueh, Pierre L. Dognin, Igor Melnyk, Jarret Ross, Tom Sercu, Cicero Nogueira Dos Santos
-
Publication number: 20200110797Abstract: An unsupervised text style transfer method, system, and computer program product include classifying a style of an input message, translating the input message into a second style, re-writing the input message into a second message having the second style, and distributing the second message in the second style.Type: ApplicationFiled: October 4, 2018Publication date: April 9, 2020Inventors: Igor Melnyk, Cicero Nogueira Dos Santos, Inkit Padhi, Kahini Wadhawan, Abhishek Kumar
-
Publication number: 20200019863Abstract: Mechanisms are provided to implement a generative adversarial network (GAN) for natural language processing. With these mechanisms, a generator neural network of the GAN is configured to generate a bag-of-ngrams (BoN) output based on a noise vector input and a discriminator neural network of the GAN is configured to receive a BoN input, where the BoN input is either the BoN output from the generator neural network or a BoN input associated with an actual portion of natural language text. The mechanisms further configure the discriminator neural network of the GAN to output an indication of a probability as to whether the input BoN is from the actual portion of natural language text or is the BoN output of the generator neural network.Type: ApplicationFiled: July 12, 2018Publication date: January 16, 2020Inventors: Dheeru Dua, Cicero Nogueira Dos Santos, Bowen Zhou
-
Publication number: 20200019642Abstract: Mechanisms are provided for implementing a Question Answering (QA) system utilizing a trained generator of a generative adversarial network (GAN) that generates a bag-of-ngrams (BoN) output representing unlabeled data for performing a natural language processing operation. The QA system obtains a plurality of candidate answers to a natural language question, where each candidate answer comprises one or more ngrams. For each candidate answer, a confidence score is generated based on a comparison of the one or more ngrams in the candidate answer to ngrams in the BoN output of the generator neural network of the GAN. A final answer to the input natural language question is selected from the plurality of candidate answers based on the confidence scores associated with the candidate answers, and is output.Type: ApplicationFiled: July 12, 2018Publication date: January 16, 2020Inventors: Dheeru Dua, Cicero Nogueira Dos Santos, Bowen Zhou
-
Publication number: 20180204125Abstract: A computer-implemented method includes extracting a plurality of topics from a plurality of unlabeled social media posts, mapping the plurality of topics to a plurality of frequencies, each frequency in the plurality of frequencies indicating how often a corresponding topic in the plurality of topics occurs in the plurality of unlabeled social media posts, and predicting, based in part on the plurality of frequencies, a future social media posting behavior of a specific social media user, wherein the future social media posting behavior includes a specific topic about which the specific social media user is likely to post at a time in the future and a frequency with which the specific topic is likely to occur in posts of the specific social media user that are created at the time in the future.Type: ApplicationFiled: January 19, 2017Publication date: July 19, 2018Inventors: Paulo Rodrigo Cavalin, Maira Gatti de Bayser, Alexandre Rademaker, Cicero Nogueira Dos Santos
-
Publication number: 20170308790Abstract: According to an aspect a method includes configuring a convolutional neural network (CNN) for classifying text based on word embedding features into a predefined set of classes identified by class labels. The predefined set of classes includes a class labeled none-of-the-above for text that does not fit into any of the other classes in the predefined set of classes. The CNN is trained based on a set of training data. The training includes learning parameters of class distributed vector representations (DVRs) of each of the predefined set of classes. The learning includes minimizing a pair-wise ranking loss function over the set of training data. A class embedding matrix of the class DVRs of the predefined set of classes that excludes a class embedding for the none-of-the-above class is generated. Each column in the class embedding matrix corresponds to one of the predefined classes.Type: ApplicationFiled: April 21, 2016Publication date: October 26, 2017Inventors: Cicero Nogueira dos Santos, Bing Xiang, Bowen Zhou