Relying on discourse analysis to answer complex questions by neural machine reading comprehension

This invention describes a system that answers complex questions by finding relevant text and then analyzing both the question and the text. It generates detailed linguistic information, including syntax trees and abstract meaning, from both the question and the found text. This linguistic data is then fed into a trained machine-learning model to identify the precise answer from the text.

Why it matters: Filed before large language models (LLMs) were widely capable of complex linguistic analysis. By 2026, advanced LLMs can perform the detailed syntactic, semantic, and discourse analysis described, simplifying the development of the core machine-learning model and linguistic data generation.

Status: Not in forceListed as no longer active. The specific reason is not in the record we hold.
How hard to build: SpecializedHeavy software system, machine learning, natural language processing

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