HIERARCHICAL SEGMENTATION OF UNSTRUCTURED TEXT USING NEURAL NETWORKS

    公开(公告)号:US20250165517A1

    公开(公告)日:2025-05-22

    申请号:US18511186

    申请日:2023-11-16

    Applicant: Adobe Inc.

    Abstract: Embodiments are disclosed for a digital design system trained to segment unstructured text into topically coherent segments. The method may include receiving unstructured text, the unstructured text including a sequence of sentences. The disclosed systems and methods further comprise generating, by a neural network, a hierarchically segmented tree structure representing the unstructured text. The tree structure comprises a plurality of tree structure nodes, where a node of the tree structure nodes represents a sentence from the sequence of sentences. The segments and sub-segments of the unstructured text can then be determined based on node data for nodes of the hierarchically segmented tree structure. Using the determined segments and sub-segments of the unstructured text, a modified representation of the unstructured text can be displayed.

    MULTI-DOCUMENT INTEGRATED READING
    2.
    发明公开

    公开(公告)号:US20240135087A1

    公开(公告)日:2024-04-25

    申请号:US17954558

    申请日:2022-09-28

    Applicant: ADOBE INC.

    CPC classification number: G06F40/166 G06F3/0484 G06F16/93 G06Q50/18

    Abstract: Embodiments of the technology described herein provide a method for generating a unified contract view. The method identifies, within a contract change document, a change instruction for a main contract. The change instruction includes a change introduction and a change content. The method determines an editing intent associated with the change instruction. The method identifies, using the change instruction, a target element in the main contract to be changed. The method generates a unified contract view that depicts the target element modified according to the editing intent and the change content. The method causes the unified contract view to be output for display.

Patent Agency Ranking