Multiple Instance Learning for Content Feedback Localization Without Annotation
Summary
USPTO published patent application US20260093986A1 for a method predicting annotation spans without labeled annotation data, treating Automated Essay Scoring (AES) as a Multiple Instance Learning (MIL) task. The invention enables models to predict content scores and localize content using sentence-level predictions without annotation training data. Inventors include Scott HELLMAN, Peter W. FOLTZ, Lee BECKER, and William R. MURRAY.
What changed
The USPTO published patent application US20260093986A1 disclosing a method using Multiple Instance Learning (MIL) for Automated Essay Scoring (AES) that predicts annotation spans and localizes content without requiring labeled annotation data. The model leverages sentence-level score predictions to both predict content scores and identify specific content areas. CPC classifications include G06N 3/08, G06F 40/20, G06Q 50/20, and G09B 5/02, indicating applications in neural networks, natural language processing, education, and instructional technology.
Patent applicants and technology companies developing AI-driven educational assessment tools should review this application to understand emerging approaches to annotation-free content scoring. This represents a potential advancement in formative feedback and explainable AI models for educational assessment. The filing date was December 8, 2025, with application number 19412444.
Archived snapshot
Apr 2, 2026GovPing captured this document from the original source. If the source has since changed or been removed, this is the text as it existed at that time.
MULTIPLE INSTANCE LEARNING FOR CONTENT FEEDBACK LOCALIZATION WITHOUT ANNOTATION
Application US20260093986A1 Kind: A1 Apr 02, 2026
Inventors
Scott HELLMAN, Peter W. FOLTZ, Lee BECKER, William R. MURRAY
Abstract
The disclosed embodiments may include a method to predict annotation spans without requiring any labeled annotation data. The approach may consider AES as a Multiple Instance Learning (MIL) task. The disclosed embodiments may show that such models can both predict content scores and localize content by leveraging their sentence-level score predictions. This capability may arise despite never having access to annotation training data. Implications may be discussed for improving formative feedback and explainable AES models.
CPC Classifications
G06N 3/08 G06F 40/20 G06Q 50/20 G09B 5/02
Filing Date
2025-12-08
Application No.
19412444
Named provisions
Related changes
Get daily alerts for USPTO Patent Applications - AI & Computing (G06N)
Daily digest delivered to your inbox.
Free. Unsubscribe anytime.
Source
About this page
Every important government, regulator, and court update from around the world. One place. Real-time. Free. Our mission
Source document text, dates, docket IDs, and authority are extracted directly from USPTO.
The plain-English summary, classification, and "what to do next" steps are AI-generated from the original text. Cite the source document, not the AI analysis.
Classification
Who this affects
Taxonomy
Browse Categories
Get alerts for this source
We'll email you when USPTO Patent Applications - AI & Computing (G06N) publishes new changes.