公开(公告)号：US20240427998A1

公开(公告)日：2024-12-26

申请号：US18339694

申请日：2023-06-22

Applicant: Adobe Inc.

Inventor： Haoliang Wang ,  Tong Yu ,  Sungchul Kim ,  Ruiyi Zhang ,  Paiheng Xu ,  Junda Wu ,  Handong Zhao ,  Ani Nenkova

IPC: G06F40/30 ,  G06N5/04

Abstract: Contextual query generation techniques are described that enable generation of a contextual query for output to a question-answering (QA) model. A content processing system, for instance, configures a language model using in-context learning to generate queries based on semantic contexts of input documents, e.g., based on one or more linguistic cues from text of the input documents. The content processing system receives an input that includes a document having text and a reference query. The content processing system leverages the language model to generate a contextual query based on a semantic context of the text of the document and the reference query. The content processing system then outputs the contextual query and the document to a QA model. Using the QA model, the content processing system generates a response as an answer to the contextual query based on the contextual query and the document.

公开(公告)号：US20250028751A1

公开(公告)日：2025-01-23

申请号：US18355901

申请日：2023-07-20

Applicant: Adobe Inc.

Inventor： Tong Yu ,  Kaige Xie ,  Haoliang Wang ,  Junda Wu ,  Handong Zhao ,  Ruiyi Zhang ,  Kanak Vivek Mahadik ,  Ani Nenkova

IPC: G06F16/34 ,  G06F40/35

Abstract: Dialogue skeleton assisted prompt transfer for dialogue summarization techniques are described that support training of a language model to perform dialogue summarization in a few-shot scenario. A processing device, for instance, receives a training dataset that includes training dialogues. The processing device then generates dialogue skeletons based on the training dialogues using one or more perturbation-based probes. The processing device trains a language model using prompt transfer between a source task, e.g., dialogue state tracking, and a target task, e.g., dialogue summarization, using the dialogue skeletons as supervision. The processing device then receives an input dialogue and uses the trained language model to generate a summary of the input dialogue.

公开(公告)号：US20250005289A1

公开(公告)日：2025-01-02

申请号：US18343389

申请日：2023-06-28

Applicant: Adobe Inc.

Inventor： Haoliang Wang ,  Kaige Xie ,  Tong Yu ,  Junda Wu ,  Handong Zhao ,  Ruiyi Zhang ,  Kanak Vivek Mahadik ,  Ani Nenkova

IPC: G06F40/35 ,  G06F16/34 ,  G06F16/35

Abstract: Dialogue state aware dialogue summarization techniques are described that enable generation of dialogue summaries from target domains with limited training data. A content processing system, for instance, generates one or more clusters based on training dialogues from one or more source domains. The clusters represent domain-specific features of the training dialogues and are further based on dialogue states of the training dialogues. The content processing system trains a machine learning model to generate summaries of dialogues by using the one or more clusters as prefixes in a prefix-tuning approach. The content processing system receives an input that includes a dialogue from a target domain. The content processing system generates an input prompt based on the dialogue and the one or more clusters, and the model generates a summary of the dialogue based on the input prompt.

公开(公告)号：US20250061609A1

公开(公告)日：2025-02-20

申请号：US18451201

申请日：2023-08-17

Applicant: ADOBE INC.

Inventor： Junda Wu ,  Haoliang Wang ,  Tong Yu ,  Stefano Petrangeli ,  Gang Wu ,  Viswanathan Swaminathan ,  Sungchul Kim ,  Handong Zhao

IPC: G06T9/40 ,  G06V10/70 ,  G06V10/75

Abstract: One or more aspects of the method, apparatus, and non-transitory computer readable medium include obtaining image data and computing a prediction residue value for a pixel of the image data using a prediction function. An entropy value for the pixel can then be determined based on the prediction residue value using context modeling, and progressive compressed image data for the image data can be generated based on the entropy value. The compressed image data can be used to enable collaborative image editing and other image processing tasks.