18336380. UTILIZING EMBEDDING-BASED CLAIM-RELATION GRAPHS FOR EFFICIENT SYNTOPICAL READING OF CONTENT COLLECTIONS (Adobe Inc.)

From WikiPatents
Revision as of 07:32, 19 December 2024 by Wikipatents (talk | contribs) (Creating a new page)
(diff) ← Older revision | Latest revision (diff) | Newer revision → (diff)
Jump to navigation Jump to search

UTILIZING EMBEDDING-BASED CLAIM-RELATION GRAPHS FOR EFFICIENT SYNTOPICAL READING OF CONTENT COLLECTIONS

Organization Name

Adobe Inc.

Inventor(s)

Joseph Barrow of Alexandria VA (US)

Jennifer Healey of San Jose CA (US)

Franck Dernoncourt of Seattle WA (US)

Ani Nenkova of Philadelphia PA (US)

Vlad Morariu of Potomac MD (US)

Rajiv Jain of Falls Church VA (US)

Nedim Lipka of Santa Clara CA (US)

UTILIZING EMBEDDING-BASED CLAIM-RELATION GRAPHS FOR EFFICIENT SYNTOPICAL READING OF CONTENT COLLECTIONS

This abstract first appeared for US patent application 18336380 titled 'UTILIZING EMBEDDING-BASED CLAIM-RELATION GRAPHS FOR EFFICIENT SYNTOPICAL READING OF CONTENT COLLECTIONS



Original Abstract Submitted

This disclosure describes one or more implementations of systems, non-transitory computer-readable media, and methods that extract viewpoints from content for syntopical reading using an efficient claim-relation graph construction approach. For example, the disclosed systems utilize sentence transformers with claims from content to embed the claims within a metric space (as claim nodes). Furthermore, in some embodiments, the disclosed systems generate a claim relation graph for the claims by utilizing approximate nearest neighbor searches to determine relational edges between a claim node and the claim node's approximate nearest neighbors. Moreover, in some implementations, the disclosed systems utilize the claim relation graph with an edge weighted graph neural network to determine stance labels during extraction of viewpoints (e.g., stance, aspect, and topic) for the claims. Additionally, in one or more instances, the disclosed systems utilize the extracted viewpoints in content retrieval applications (e.g., viewpoint ranked search results and/or socially contextualized claims).