Adobe, Inc.

Joseph Barrow

Rajiv Jain

Franck Dernoncourt

Vlad Ion Morariu

Varun Manjunatha

Sasha Spala

Nicholas Miller

Jennifer Anne Healey

Nedim Lipka

Techniques for query based classification are described that support generation of classifications based on user proffered information. In an example, a processing device receives a query for processing by a machine learning model. The processing device then generates a user classification based on the query. The user classification, for instance, indicates one or more user characteristics. The processing device generates a prompt for processing by the machine learning model that includes the query and the user classification. The processing device then presents a result of the processing of the prompt by the machine learning model. For instance, the machine learning model generates a response to the query tailored to the classification. In this way, the techniques described herein support generation of content specific user classifications to perform various functionality.

Query based classification

Certain embodiments involve using a machine-learning tool to generate metadata identifying segments and topics for text within a document. For instance, in some embodiments, a text processing system obtains input text and applies a segmentation-and-labeling model to the input text. The segmentation-and-labeling model is trained to generate a predicted segment for the input text using a segmentation network. The segmentation-and-labeling model is also trained to generate a topic for the predicted segment using a pooling network of the model to the predicted segment. The output of the model is usable for generating metadata identifying the predicted segment and the associated topic.

Machine-learning tool for generating segmentation and topic metadata for documents

Systems and methods for natural language processing are described. One or more embodiments of the present disclosure identify a claim from a document, wherein the claim corresponds to a topic, create a graph comprising a plurality of nodes having a plurality of node types and a plurality of edges having a plurality of edge types, wherein one of the nodes represents the claim, and wherein each of the edges represents a relationship between a corresponding pair of the nodes, encode the claim based on the graph using a graph convolutional network (GCN) to obtain an encoded claim, classify the claim by decoding the encoded claim to obtain a stance label that indicates a stance of the claim towards the topic, and transmit information indicating a viewpoint of the document towards the topic based on the stance label.

Syntopical reading for collection understanding

Growing community of inventors

College Park, MD, United States of America

Joseph Barrow