Google Inc.

Sandeep Tata

Marc Alexander Najork

Qi Zhao

James Bradley Wendt

Navneet Potti

Bodhisattwa Prasad Majumder

Cayden Meyer

Reuben Kan

Alexandre Mah

Jing Xie

Ying Sheng

Alan Green

Julian Gibbons

Michael Smith

Yuchen Lin

Nguyen Vo

Divanshu Garg

Alexandrin Popescul

Abbas Kazerouni

The present disclosure is directed to extracting text from form-like documents. In particular, a computing system can obtain an image of a document that contains a plurality of portions of text. The computing system can extract one or more candidate text portions for each field type included in a target schema. The computing system can generate a respective input feature vector for each candidate for the field type. The computing system can generate a respective candidate embedding for the candidate text portion. The computing system can determine a respective score for each candidate text portion for the field type based at least in part on the respective candidate embedding for the candidate text portion. The computing system can assign one or more of the candidate text portions to the field type based on the respective scores.

System for information extraction from form-like documents

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

Provided are computing systems and methods directed to active learning and may provide advantages or improvements to active learning applications for skewed data sets. A challenge in training and developing high-quality models for many supervised learning scenarios is obtaining labeled training examples. Provided are systems and methods for active learning on a training dataset that includes both labeled and unlabeled datapoints. In particular, the systems and methods described herein can select (e.g., at each of a number of iterations) a number of the unlabeled datapoints for which labels should be obtained to gain additional labeled datapoints on which to train a machine-learned model (e.g., machine-learned classifier model). Generally, provided are cost-effective methods and systems for selecting data to improve machine-learned models in applications such as the identification of content items in text, images, and/or audio.

Systems and methods for active learning

A user device can send, to a server, a request for a set of documents likely to be opened by a user, determine a client-suggested document to present to the user and a potential motive for the user to open the client-suggested document, receive a suggestion message from the server, the suggestion message including a set of documents likely to be opened by the user and potential motives for the user to open documents in the set of documents, and present, on a display of the user device, visual representations of the client-suggested document, the potential motive for the user to open the client-suggested document, multiple documents included in the set of documents, and the potential motives for the user to open the multiple documents in the set of documents.

Recommending a document for a user to access

Growing community of inventors

San Francisco, CA, United States of America

Sandeep Tata