Google Inc.

Ying Sheng

Jie Yang

Luis Garcia Pueyo

James Bradley Wendt

Jing Xie

Jinan Lou

Sandeep Tata

Yifeng Lu

Yuchen Lin

Nguyen Vo

Systems and methods for efficiently identifying and extracting machine-actionable structured data from web documents are provided. The technology employs neural network architectures which process the raw HTML content of a set of seed websites to create transferable models regarding information of interest. These models can then be applied to the raw HTML of other websites to identify similar information of interest. Data can thus be extracted across multiple websites in a functional, structured form that allows it to be used further by a processing system.

Transferable neural architecture for structured data extraction from web documents

Techniques are described herein for automatically generating data extraction templates for structured documents (e.g., B2C emails, invoices, bills, invitations, etc.), and for assigning classifications to those data extraction templates to streamline data extraction from subsequent structured documents. In various implementations, a data extraction template generated from a cluster of structured documents that share fixed content may be identified. Features of the cluster of structured documents may be applied as input to extraction machine learning model(s) trained to provide location(s) of transient field(s) in structured documents, to determine location(s) of transient field(s) in the cluster of structured documents. An association between the data extraction template and the determined transient field location(s) may be stored. Based on the association, data point(s) may be extracted from a given structured document of a user that shares fixed content with the cluster of structured documents. The extracted data point(s) may be surfaced to the user.

Template-based structured document classification and extraction

Methods and apparatus are described herein for creating associations between user interests and electronic document templates generated from B2C electronic documents. Once these associations are created, interest(s) of a user (e.g., a user profile) may be determined automatically based on B2C electronic documents addressed to the user. In various implementations, an electronic document addressed to a user may be identified. A particular electronic document template that corresponds to the electronic document addressed to the user may be selected from a plurality of electronic document templates. The selecting may be based on attribute(s) shared between the electronic document addressed to the user and the selected electronic document template. The particular electronic template may be generated from a plurality of electronic documents that share fixed content. Interest(s) associated with the particular electronic document template may be identified, and association(s) between the user and the identified interest(s) may be stored.

Template-based identification of user interest

Growing community of inventors

Sunnyvale, CA, United States of America

Ying Sheng