International Business Machines Corporation

Amazon Technologies, Inc.

Amita Misra

Jalal U Mahmud

Pritam S Gundecha

Zhe Liu

Rama Kalyani T Akkiraju

Anbang Xu

Xiaotong Liu

Gaurav Kumbhat

Alexander Brooks

Ojas Yashwant Joshi

Yash Bhalgat

Saurabh Tripathy

Gabriel Goodhart

Sukriti Sharma

Nhan Hoang

Zachary Branson

Pratyay Banerjee

Techniques are generally described for query evaluation for image retrieval and image generation. In various examples, a first encoded representation of first natural language input data may be generated. An image retrieval process may be selected from among the image retrieval process and an image generation process based at least in part on the first encoded representation of the first natural language input data. A second natural language encoder may generate a second encoded representation of the first natural language input data. The second encoded representation may be used to determine first image data stored in a first data repository. The first image data may be sent for output on a display of a first computing device.

Query evaluation for image retrieval and conditional image generation

An input text that is also transmitted to a text processing service (e.g., a cloud based text processing service) is received. Characterizing information (e.g., contiguous parts of speech, terms used per part of speech, payload length, etc.) is extracted from the input text. A text payload is generated using the characterizing information. A performance test is run on the text payload. The performance test can include performing at least one selected from a group consisting of: sentiment analysis on the text payload, entity analysis on the text payload, content classification on the text payload, and syntax analysis on the text payload. The performance test can yield a processing time required to perform the performance test. Memory and processing power resource allocation to the text processing service can be altered based on the processing time of the performance test.

Natural language processing payload generation

A method and a system for model training are provided. The method can include training a first classifier, a second classifier, and a third classifier with subsets of a labeled dataset. The method can also include predicting a pseudo labeled dataset from an unlabeled dataset using the first classifier, the second classifier, and the third classifier. The method further includes assigning a role to the first classifier, to the second classifier, and to the third classifier. The method can further include selecting a teaching sample dataset from the pseudo labeled dataset based on the role assigned to the third classifier, wherein the third classifier is assigned a role of a student. The method can also include retraining the third classifier with the teaching sample dataset in conjunction with a subset of the labeled dataset.

Model training using a teacher-student learning paradigm

A method, system, and a computer program product automatically select training data for updating a model by applying human-annotated training data to a model to generate results that are evaluated to identify correct case results and false case results that are categorized into error type categories for use in building error models corresponding to the error type categories, where each error model is built from at least failed case results belonging to a corresponding error type, and where unlabeled data samples are applied to each error model to compute an error likelihood for each unlabeled data sample with respect to each error type category, thereby enabling the selection and display of unlabeled data samples for annotation by a subject matter expert based on a computed error likelihood for the one or more unlabeled data samples in a specified error type category meeting or exceeding an error threshold requirement.

Method and system for unlabeled data selection using failed case analysis

A method, system and computer-usable medium are disclosed for sentiment detection based on applying an antonym dictionary to a natural language processing (NLP) system. A binary classifier is trained to predict negation cues, where a constituency parse tree is used to create rules for scope detection. The trained binary classifier, a list of conversational negation terms, and a list of antonyms are used to annotate content that considers negation cues and scope for the created rules.

System and method for negation aware sentiment detection

Growing community of inventors

San Jose, CA, United States of America

Amita Misra