Hierarchical segmentation of unstructured text using neural networks

US12346361B2 · kind B2 · utility

Assignee

• Adobe Inc. · US

Inventors

• Inderjeet Jayakumar Nair · Ann Arbor, US
• Sumit Shekhar · Bengaluru, IN
• Srikrishna Karanam · Watertown, US
• Niyati Himanshu Chhaya · Chilpur, IN
• Natwar Modani · Savanuru, IN
• Balaji Vasan Srinivasan · Bengaluru, IN
• Aparna Garimella · Hyderabad, IN

Key dates

• Filing date: Nov 16, 2023
• Grant date: Jul 1, 2025
• Expiry date: Nov 16, 2043

Classification

• Technology area (CPC G): Physics
• CPC primary: G06F16/322
• WIPO field: Computer technology
• WIPO sector: Electrical engineering

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.