Abstract: 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.

Abstract: 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.

Abstract: 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.

Abstract: 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.

Abstract: An input text that is also transmitted to a text processing service is received. Characterizing information is extracted from the input text. A text payload is generated using the characterizing information. A performance test is run on the text payload.

Abstract: 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.

Abstract: 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.

Abstract: 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.

Abstract: In this invention we describe a shaking device that is used to shake, stir, mix, rotate or agitate samples in containers attached to the shaking device. The shaking device, herein referred to as the shaker, is used to mix the solid, liquid or gaseous components of the sample in the container. The shaker described in this invention has a flexible arm to which the containers containing samples are attached. Due to the flexibility of the arm, its shape can be changed such that the speed and type of sample shaking can be varied based on the shape of the arm and based on where on the arm a sample container is attached. In this manner, orbital, linear, circular and other two or three-dimensional shaking, mixing, agitation and stirring of the sample can be achieved. The present invention provides an easy new method for shaking samples in containers of different shapes and volumes, at different speeds and in different orientations in space.

Abstract: In this invention we describe a magnet or magnetic material that is attached to a pipette to hang it on a ferrous or magnetic material. The magnet can be attached to any place on the pipette in such a way that the pipette can be hung as desired on the magnetic or ferrous surface such as ferrous clips, iron or steel sheets (refrigerator, lab bench, hood etc.). This will help to organize the laboratories. Furthermore this will reduce the contamination from pipette to pipette and sample to sample.

Abstract: In this invention we describe a shaking device that is used to shake, stir, mix, rotate or agitate samples in containers attached to the shaking device. The shaking device, herein referred to as the shaker, is used to mix the solid, liquid or gaseous components of the sample in the container. The shaker described in this invention has a flexible arm to which the containers containing samples are attached. Due to the flexibility of the arm, its shape can be changed such that the speed and type of sample shaking can be varied based on the shape of the arm and based on where on the arm a sample container is attached. In this manner, orbital, linear, circular and other two or three-dimensional shaking, mixing, agitation and stirring of the sample can be achieved. The present invention provides an easy new method for shaking samples in containers of different shapes and volumes, at different speeds and in different orientations in space.