Patents by Inventor Bakhtiyar Hussain Syed
Bakhtiyar Hussain Syed 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: 11900056Abstract: 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.Type: GrantFiled: February 21, 2023Date of Patent: February 13, 2024Assignee: Adobe Inc.Inventors: Balaji Vasan Srinivasan, Gaurav Verma, Bakhtiyar Hussain Syed, Anandhavelu Natarajan
-
Publication number: 20230196014Abstract: 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.Type: ApplicationFiled: February 21, 2023Publication date: June 22, 2023Applicant: Adobe Inc.Inventors: Balaji Vasan Srinivasan, Gaurav Verma, Bakhtiyar Hussain Syed, Anandhavelu Natarajan
-
Patent number: 11636264Abstract: 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.Type: GrantFiled: September 7, 2021Date of Patent: April 25, 2023Assignee: Adobe Inc.Inventors: Balaji Vasan Srinivasan, Gaurav Verma, Bakhtiyar Hussain Syed, Anandhavelu Natarajan
-
Publication number: 20210406465Abstract: 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.Type: ApplicationFiled: September 7, 2021Publication date: December 30, 2021Applicant: Adobe Inc.Inventors: Balaji Vasan Srinivasan, Gaurav Verma, Bakhtiyar Hussain Syed, Anandhavelu Natarajan
-
Patent number: 11157693Abstract: 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.Type: GrantFiled: February 25, 2020Date of Patent: October 26, 2021Assignee: Adobe Inc.Inventors: Balaji Vasan Srinivasan, Gaurav Verma, Bakhtiyar Hussain Syed, Anandhavelu Natarajan
-
Publication number: 20210264109Abstract: 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.Type: ApplicationFiled: February 25, 2020Publication date: August 26, 2021Applicant: Adobe Inc.Inventors: Balaji Vasan Srinivasan, Gaurav Verma, Bakhtiyar Hussain Syed, Anandhavelu Natarajan