Natural language processing on semi-structured data

US11847406B1 · kind B1 · utility

Assignee

• AMAZON TECHNOLOGIES, INC. · US

Inventors

• Sunil Mallya Kasaragod · San Francisco, US
• Yahor Pushkin · Redmond, US
• Saman Zarandioon · Seattle, US
• Graham Vintcent Horwood · Centreville, US
• Miguel Ballesteros Martinez · New York, US
• Yogarshi Paritosh Vyas · New York, US
• Yinxiao Zhang · Issaquah, US
• Diego Marcheggiani · Barcelona, ES
• Yaser Al-Onaizan · Whitehall Corners, US
• Xuan Zhu · Beijing, CN
• Liutong Zhou · Jersey City, US
• Yusheng Xie · Mountain View, US
• Aruni Roy Chowdhury · Seattle, US
• Bo Pang · Beijing, CN

Key dates

• Filing date: Mar 30, 2021
• Grant date: Dec 19, 2023
• Expiry date: Oct 23, 2041

Classification

• Technology area (CPC G): Physics
• CPC primary: G06N20/00
• WIPO field: Computer technology
• WIPO sector: Electrical engineering

Abstract

Techniques for performing natural language processing (NLP) on semi-structured data are described. An exemplary method includes receiving a semi-structured document to perform NLP on using a trained NLP model; converting the semi-structured document into a secondary format, wherein the secondary format includes spatial information for tokens of the semi-structured document; flattening the converted, secondary formatted semi-structured document into a Unicode Transformation Format text file; performing NLP on the Unicode Transformation Format text file using the trained NLP model; and providing a result of the NLP to a requester.