Amazon patents method to rank importance of topics in short text snippets
Amazon describes a system that uses a neural network to measure how central a specific topic or entity is to a short piece of text. It compares a digital fingerprint of the text with a fingerprint of the entity, which may include a description from a knowledge base, to assign an importance score. This score helps the system decide what extra information to show a user alongside their original query.
In the filing’s own words
Systems and methods are described for predicting entity salience in segments of text, including short segments of text, where salience may refer to the importance or centrality of the entity to the content of the text. The system may use an entity salience model that can encode the context (e.g., the segment of text) into a passage embedding and an entity into an entity embedding. In some cases, the entity embedding may be determined using the entity as well as a natural language description of the entity from, for example, a knowledge graph or other resource. The entity salience model may calculate an entity score for each entity represented in the text based on, for example, a similarity between that entity's entity embedding and the passage embedding. The entity salience score maybe used to, for example, identify additional content with which to augment a response to a user input.
What exactly they claim (claim 1)
1. A computer-implemented method comprising: receiving first data representing a first natural language passage of text; determining first embedding data using the first data and a first neural network encoder; determining, using the first embedding data and second embedding data corresponding to a first entity represented in the first data, a first salience of the first entity to the first natural language passage of text; determining first output data corresponding to the first data; receiving second data corresponding to the first entity; causing output of the first output data corresponding to the first data; and based at least in part on the first salience, causing output of an indication of the second data.
Facts
- Company
- Amazon (Amazon Technologies, Inc.)
- Official title
- PREDICTING ENTITY SALIENCE
- Publication number
- US20260351250A1
- Application number
- 19449636
- Filed
- Jan 15, 2026
- Published
- Nov 5, 2026
- Inventors
- 2
- Claims
- 20
Classified under
G10L 15/16 Physics & computingG10L 15/063 Physics & computingG10L 15/197 Physics & computingG10L 15/22 Physics & computingMore from Amazon in AI & software
- Amazon patents system that cites sources for AI answers Sep 29, 2026
- Amazon patents voice assistants that adjust personality based on your mood Nov 3, 2026
- Amazon patents tech to swap words in movies using actor's voice Sep 8, 2026
- Amazon patents ML tool to add graphics to live sports from moving cameras Sep 15, 2026
- Amazon patents shopping assistant that remembers your search filters Oct 6, 2026
Summaries are simplified from the filing’s own abstract and first claim. A patent filing is not a product announcement.
Patent data and drawings: U.S. Patent and Trademark Office (USPTO). Nebula is not affiliated with or endorsed by the USPTO.
