Abstract: A method for error reduction in intent classification according to an embodiment includes determining a set of possible intent classes for a section of input text, mapping each of the possible intent classes into a respective group of a plurality of groups, determining which groups of the plurality of groups are contradictory to one or more other groups of the plurality of groups, splitting the section of input text into a plurality of sub-parts, performing intent classification on the section of input text to determine an intent of the section of input text and on each sub-part of the plurality of sub-parts to determine a respective intent of each sub-part, evaluating the determined intent of the section of input text and the respective intents of the sub-parts for intent contradiction, and overriding the determined intent of the section of input text in response to identifying an intent contradiction.

Abstract: A system and method of training a machine-learning (ML) based model by at least one processor may include receiving an initial dataset, including a plurality of annotated data samples; based on the initial dataset, training at least one ML-based first-level model to perform a first-level task; based on training the at least one ML-based first-level model, calculating at least one characteristic, representing, for each data sample, a value of contribution into a training of a ML-based second-level model to perform a second-level task; omitting a subset of data samples from the initial dataset based on the at least one characteristic, to obtain a target dataset; and training ML-based second-level model, to perform the second-level task, based on the target dataset.

Abstract: A method and a system of classifying textual data blocks are claimed. The method includes receiving at least one textual data block in an original version, including a plurality of textual data elements; performing a preprocessing procedure on the at least one textual data block in the original version, wherein the preprocessing procedure includes replacing the textual data elements characterized by pertinence to at least one specific part-of-speech (POS) category with a respective POS token, thereby obtaining the at least one textual data block in a preprocessed version; inferring a pretrained ML-based model on the at least one textual data block in the preprocessed version, to classify the at least one textual data block by pertinence to the at least one class.

Abstract: A method for training a multi-class classification model includes receiving training data corresponding to a plurality of classes. For each class in the plurality of classes, the method includes training a binary classification model configured to determine whether or not an observation of training data belongs to the class and for each observation of training data identified as belonging to the class, extracting one or more class identification features from the observation of training data based on activations of an intermediate attention layer in the binary classification model. A multi-class classification model is trained using the class identification features extracted for each of the plurality of classes.

Abstract: A method for error reduction in intent classification according to an embodiment includes determining a set of possible intent classes for a section of input text, mapping each of the possible intent classes into a respective group of a plurality of groups, determining which groups of the plurality of groups are contradictory to one or more other groups of the plurality of groups, splitting the section of input text into a plurality of sub-parts, performing intent classification on the section of input text to determine an intent of the section of input text and on each sub-part of the plurality of sub-parts to determine a respective intent of each sub-part, evaluating the determined intent of the section of input text and the respective intents of the sub-parts for intent contradiction, and overriding the determined intent of the section of input text in response to identifying an intent contradiction.

Abstract: A method and a system for improving classification of data samples, which may be considered as class outliers, are claimed. The method includes inferring a pretrained classifying ML-based model on the incoming data sample, to assign a particular class of a plurality of classes thereto; calculating a similarity metric value representing a degree of similarity between the incoming data sample and one or more previously classified data samples of the particular class; and validating assignment of the particular class to the incoming data sample, based on the calculated similarity metric value.

Abstract: A method and a system of classifying textual data blocks are claimed. The method includes receiving at least one textual data block in an original version, including a plurality of textual data elements; performing a preprocessing procedure on the at least one textual data block in the original version, wherein the preprocessing procedure includes replacing the textual data elements characterized by pertinence to at least one specific part-of-speech (POS) category with a respective POS token, thereby obtaining the at least one textual data block in a preprocessed version; inferring a pretrained ML-based model on the at least one textual data block in the preprocessed version, to classify the at least one textual data block by pertinence to the at least one class.

Abstract: A system and method of training a machine-learning (ML) based model by at least one processor may include receiving an initial dataset, including a plurality of annotated data samples; based on the initial dataset, training at least one ML-based first-level model to perform a first-level task; based on training the at least one ML-based first-level model, calculating at least one characteristic, representing, for each data sample, a value of contribution into a training of a ML-based second-level model to perform a second-level task; omitting a subset of data samples from the initial dataset based on the at least one characteristic, to obtain a target dataset; and training ML-based second-level model, to perform the second-level task, based on the target dataset.

Abstract: A method for training a multi-class classification model includes receiving training data corresponding to a plurality of classes. For each class in the plurality of classes, the method includes training a binary classification model configured to determine whether or not an observation of training data belongs to the class and for each observation of training data identified as belonging to the class, extracting one or more class identification features from the observation of training data based on activations of an intermediate attention layer in the binary classification model. A multi-class classification model is trained using the class identification features extracted for each of the plurality of classes.

Abstract: A computer implemented method of document classification includes receiving a text document. A first classification is generated for the document, and a text corpus is searched for one or more terms from the document. Searched terms having an incidence in the text corpus lower than a threshold incidence are flagged, and at least one classification is generated after removing at least one flagged term from the document. An output is generated if the further classification is different from the first classification.

Abstract: A method for training a multi-class classification model includes receiving training data corresponding to a plurality of classes. For each class in the plurality of classes, the method includes training a binary classification model configured to determine whether or not an observation of training data belongs to the class and for each observation of training data identified as belonging to the class, extracting one or more class identification features from the observation of training data based on activations of an intermediate attention layer in the binary classification model. A multi-class classification model is trained using the class identification features extracted for each of the plurality of classes.