Method for Training ML Model to Generate Text
Summary
USPTO published patent application US20260093959A1 for a computer-implemented method training machine learning models for text generation. The method involves preprocessing input text into character vectors, encoding to word vectors, generating predictive word vectors via a backbone model, and decoding to character probabilities for model updates. Inventors: Lukas Balles and Pit Neitemeier. Application filed September 29, 2025.
What changed
The USPTO published a patent application disclosing a method for training machine learning models to generate text. The claimed invention involves inputting and preprocessing text into character vector representations, encoding these via an encoder to obtain word vectors, generating predictive word vectors using a backbone model, decoding to obtain character-probabilities, and updating the model accordingly. The application is classified under CPC G06N 3/0455 (combination of neural network models), G06F 18/10, and G06F 18/21355.
This publication represents a routine patent application filing rather than an issued patent or regulatory requirement. Technology companies developing text generation systems, NLP models, or related AI applications may wish to review the disclosed method for potential licensing considerations or competitive analysis. The patent application does not impose compliance obligations on any party.
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.
METHOD, DEVICE AND COMPUTER PROGRAM FOR TRAINING A MACHINE LEARNING MODEL TO GENERATE TEXT AND FOR GENERATING TEXT USING THE TRAINED MACHINE LEARNING MODEL
Application US20260093959A1 Kind: A1 Apr 02, 2026
Inventors
Lukas BALLES, Pit NEITEMEIER
Abstract
The disclosure generally relates to a computer-implemented method for training a machine learning model for text generation, the method comprising inputting text into the machine learning model; preprocessing the input text to obtain a plurality of character vector representations; encoding, using an encoder, each of the plurality of character vector representations to obtain a plurality of word vector representations; generating, using a backbone model, a plurality of predictive word vector representations based on the plurality of word vector representations; decoding, using a decoder, the plurality of predictive word vector representations to obtain a plurality of character-probabilities; and updating the machine learning model based the plurality of character-probabilities. The disclosure also relates to a computer implemented method for generating text, a corresponding device, system and computer program.
CPC Classifications
G06N 3/0455 G06F 18/10 G06F 18/21355
Filing Date
2025-09-29
Application No.
19343221
Named provisions
Related changes
Get daily alerts for ChangeBridge: Patent Apps - 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 ChangeBridge: Patent Apps - AI & Computing (G06N) publishes new changes.