Abstractive sentence summarization

This invention describes a computer program that can create short summaries from longer sentences. It works by analyzing the input words and, using a neural network language model, predicts the most likely first word of the summary. It then continues to predict subsequent words, considering both the original text and the words already generated, to build a concise summary.

Why it matters: Filed before the widespread availability of highly capable Large Language Models (LLMs). While the core method of using neural networks for abstractive summarization was known in 2019, the performance and accessibility of such models have dramatically improved, making this approach far more effective today.

Status: Not in forceListed as no longer active. The specific reason is not in the record we hold.
How hard to build: SpecializedComplex software, neural network, training data

3 AI reinvention directions for this patent

See all three

AI gives you a few directions you could take this. Pick one, and we check whether your version is different enough to patent, then write the filing.

Reinvent this with AI

Where this one came from

Every morning we go through millions of abandoned patents and pick out 15 worth your time. This was one of today’s.

This one

+10