Invention Grant
- Patent Title: Rich descriptor framework to text generation using graphs and structural neural encoders
-
Application No.: US16919208Application Date: 2020-07-02
-
Publication No.: US11321541B2Publication Date: 2022-05-03
- Inventor: Lingfei Wu , Chen Wang
- Applicant: International Business Machines Corporation
- Applicant Address: US NY Armonk
- Assignee: International Business Machines Corporation
- Current Assignee: International Business Machines Corporation
- Current Assignee Address: US NY Armonk
- Agent David B. Woycechowsky
- Main IPC: G06F40/58
- IPC: G06F40/58 ; G06F40/47 ; G06F16/901 ; G06N3/08 ; G06F16/332 ; G06F40/20 ; G06N3/04 ; G06N3/02

Abstract:
Technology for using a bi-directed graph convolutional neural network (“BGCNN”) to convert RDF data into natural language text. Some embodiments perform RDF-to-Text generation by learning graph-augmented structural neural encoders, consisting of: (a) bidirected graph-based meta-paths encoder; (b) bidirected graph convolutional networks encoder, and (c) separated attention mechanism for combining encoders and decoder to translate RDF triplets to natural language description.
Public/Granted literature
- US20220004720A1 RICH DESCRIPTOR FRAMEWORK TO TEXT GENERATION USING GRAPHS AND STRUCTURAL NEURAL ENCODERS Public/Granted day:2022-01-06
Information query