Abstract: Rewriting text in the writing style of a target author is described. A stylistic rewriting system receives input text and an indication of the target author. The system trains a language model to understand the target author's writing style using a corpus of text associated with the target author. The language model may be transformer-based, and is first trained on a different corpus of text associated with a range of different authors to understand linguistic nuances of a particular language. Copies of the language model are then cascaded into an encoder-decoder framework, which is further trained using a masked language modeling objective and a noisy version of the target author corpus. After training, the encoder-decoder framework of the trained language model automatically rewrites input text in the writing style of the target author and outputs the rewritten text as stylized text.

Abstract: Embodiments of the present disclosure are directed to a system, methods, and computer-readable media for facilitating stylistic expression transfers in machine translation of source sequence data. Using integrated loss functions for style transfer along with content preservation and/or cross entropy, source sequence data is processed by an autoencoder trained to reduce loss values across the loss functions at each time step encoded for the source sequence data. The target sequence data generated by the autoencoder therefore exhibits reduced loss values for the integrated loss functions at each time step, thereby improving content preservation and providing for stylistic expression transfer.

Abstract: Rewriting text in the writing style of a target author is described. A stylistic rewriting system receives input text and an indication of the target author. The system trains a language model to understand the target author's writing style using a corpus of text associated with the target author. The language model may be transformer-based, and is first trained on a different corpus of text associated with a range of different authors to understand linguistic nuances of a particular language. Copies of the language model are then cascaded into an encoder-decoder framework, which is further trained using a masked language modeling objective and a noisy version of the target author corpus. After training, the encoder-decoder framework of the trained language model automatically rewrites input text in the writing style of the target author and outputs the rewritten text as stylized text.

Abstract: Rewriting text in the writing style of a target author is described. A stylistic rewriting system receives input text and an indication of the target author. The system trains a language model to understand the target author's writing style using a corpus of text associated with the target author. The language model may be transformer-based, and is first trained on a different corpus of text associated with a range of different authors to understand linguistic nuances of a particular language. Copies of the language model are then cascaded into an encoder-decoder framework, which is further trained using a masked language modeling objective and a noisy version of the target author corpus. After training, the encoder-decoder framework of the trained language model automatically rewrites input text in the writing style of the target author and outputs the rewritten text as stylized text.

Abstract: A system for generating text using a trained language model comprises an encoder that includes a debiased language model that penalizes generated text based on an equalization loss that quantifies first and second probabilities of respective first and second tokens occurring at a first point in the generated text. The first and second tokens define respective first and second groups of people. The system further comprises a decoder configured to generate text using the debiased language model. The decoder is further configured to penalize the generated text based on a bias penalization loss that quantifies respective probabilities of the first and second tokens co-occurring with a generated word. The encoder and decoder are trained to produce the generated text using a task-specific training corpus.

Abstract: Embodiments of the present invention provide systems, methods, and computer storage media directed to facilitating predicting style breaches within content. In one embodiment, target content for which style breach prediction is desired is obtained. Style features associated with the target content are identified. Such style features and a style breach prediction model are used to predict a style breach within the target content, the style breach indicating a change of style used within the target content (e.g., a single document).

Abstract: Embodiments of the present disclosure are directed to a system, methods, and computer-readable media for facilitating stylistic expression transfers in machine translation of source sequence data. Using integrated loss functions for style transfer along with content preservation and/or cross entropy, source sequence data is processed by an autoencoder trained to reduce loss values across the loss functions at each time step encoded for the source sequence data. The target sequence data generated by the autoencoder therefore exhibits reduced loss values for the integrated loss functions at each time step, thereby improving content preservation and providing for stylistic expression transfer.

Abstract: Rewriting text in the writing style of a target author is described. A stylistic rewriting system receives input text and an indication of the target author. The system trains a language model to understand the target author's writing style using a corpus of text associated with the target author. The language model may be transformer-based, and is first trained on a different corpus of text associated with a range of different authors to understand linguistic nuances of a particular language. Copies of the language model are then cascaded into an encoder-decoder framework, which is further trained using a masked language modeling objective and a noisy version of the target author corpus. After training, the encoder-decoder framework of the trained language model automatically rewrites input text in the writing style of the target author and outputs the rewritten text as stylized text.

Abstract: Embodiments of the present disclosure are directed to a system, methods, and computer-readable media for facilitating stylistic expression transfers in machine translation of source sequence data. Using integrated loss functions for style transfer along with content preservation and/or cross entropy, source sequence data is processed by an autoencoder trained to reduce loss values across the loss functions at each time step encoded for the source sequence data. The target sequence data generated by the autoencoder therefore exhibits reduced loss values for the integrated loss functions at each time step, thereby improving content preservation and providing for stylistic expression transfer.

Abstract: Rewriting text in the writing style of a target author is described. A stylistic rewriting system receives input text and an indication of the target author. The system trains a language model to understand the target author's writing style using a corpus of text associated with the target author. The language model may be transformer-based, and is first trained on a different corpus of text associated with a range of different authors to understand linguistic nuances of a particular language. Copies of the language model are then cascaded into an encoder-decoder framework, which is further trained using a masked language modeling objective and a noisy version of the target author corpus. After training, the encoder-decoder framework of the trained language model automatically rewrites input text in the writing style of the target author and outputs the rewritten text as stylized text.

Abstract: Rewriting text in the writing style of a target author is described. A stylistic rewriting system receives input text and an indication of the target author. The system trains a language model to understand the target author's writing style using a corpus of text associated with the target author. The language model may be transformer-based, and is first trained on a different corpus of text associated with a range of different authors to understand linguistic nuances of a particular language. Copies of the language model are then cascaded into an encoder-decoder framework, which is further trained using a masked language modeling objective and a noisy version of the target author corpus. After training, the encoder-decoder framework of the trained language model automatically rewrites input text in the writing style of the target author and outputs the rewritten text as stylized text.

Abstract: Embodiments of the present invention provide systems, methods, and computer storage media directed to facilitating predicting brand personality. In one embodiment, target content for which brand personality prediction is desired is obtained. Content features associated with the target content are identified. Such content features and a brand personality prediction model are used to predict a brand personality of the target content, the brand personality indicating personality of a brand associated with the target content.

Abstract: Embodiments are disclosed for bundling and arranging online content fragments for presentation based on content-specific metrics and inter-content constraints. For example, a content management application accesses candidate content fragments, a content-specific metric, and an inter-content constraint. The content management application computes minimum and maximum contribution values for the candidate content fragments. The content management application selects, based on the computed minimum and maximum contribution values, a subset of the candidate content fragments. The content management application applies, subject to the inter-content constraint, a bundle-selection function to the selected candidate content fragments and thereby identifies a bundle of online content fragments. The content management application outputs the identified bundle of online content fragments for presentation via an online service.

Abstract: Embodiments of the present disclosure are directed to a system, methods, and computer-readable media for facilitating stylistic expression transfers in machine translation of source sequence data. Using integrated loss functions for style transfer along with content preservation and/or cross entropy, source sequence data is processed by an autoencoder trained to reduce loss values across the loss functions at each time step encoded for the source sequence data. The target sequence data generated by the autoencoder therefore exhibits reduced loss values for the integrated loss functions at each time step, thereby improving content preservation and providing for stylistic expression transfer.

Abstract: Systems and techniques for searching within a document include receiving a query by way of a user interface of an application, and in conjunction with identification of the at least one document. A feature value characterizing a relevance of each grammatical unit of the document to the query may be extracted. The grammatical units may be ranked, based on each feature value of each grammatical unit. At least one selected grammatical unit of the plurality of grammatical units may then be displayed, based on the ranking.

Abstract: Embodiments of the present invention provide systems, methods, and computer storage media directed to facilitating predicting style breaches within content. In one embodiment, target content for which style breach prediction is desired is obtained. Style features associated with the target content are identified. Such style features and a style breach prediction model are used to predict a style breach within the target content, the style breach indicating a change of style used within the target content (e.g., a single document).

Abstract: Embodiments of the present invention provide systems, methods, and computer storage media directed to facilitating predicting style breaches within content. In one embodiment, target content for which style breach prediction is desired is obtained. Style features associated with the target content are identified. Such style features and a style breach prediction model are used to predict a style breach within the target content, the style breach indicating a change of style used within the target content (e.g., a single document).

Abstract: Embodiments of the present invention relate to providing business customers with predictive capabilities, such as identifying valuable customers or estimating the likelihood that a product will be purchased. An adaptive sampling scheme is utilized, which helps generate sample data points from large scale data that is imbalanced (for example, digital website traffic with hundreds of millions of visitors but only a small portion of them are of interest). In embodiments, a stream of sample data points is received. Positive samples are added to a positive list until the desired number of positives is reached and negative samples are added to a negative list until the desired number of negative samples is reached. The positive list and the negative list can then be combined, shuffled, and fed into a prediction model.

Abstract: Systems and techniques for searching within a document include receiving a query by way of a user interface of an application, and in conjunction with identification of the at least one document. A feature value characterizing a relevance of each grammatical unit of the document to the query may be extracted. The grammatical units may be ranked, based on each feature value of each grammatical unit. At least one selected grammatical unit of the plurality of grammatical units may then be displayed, based on the ranking.

Abstract: Embodiments of the present invention provide systems, methods, and computer storage media directed to facilitating predicting style breaches within content. In one embodiment, target content for which style breach prediction is desired is obtained. Style features associated with the target content are identified. Such style features and a style breach prediction model are used to predict a style breach within the target content, the style breach indicating a change of style used within the target content (e.g., a single document).