Amazon Technologies, Inc.

Microsoft Technology Licensing, LLC

Thomas Park

Aaron A Eakin

Yusuf Bootwala

Jue Wang

Jianfeng Gao

Lars Hasso Liden

Madhu Madhava Kurup

Jared Scott Lundell

Swadheen Kumar Shukla

Rich Wasserman

Shahin Shayandeh

Jinchao Li

Eslam K Abdelreheem

Baolin Peng

Matthew D Mazzola

Richard Wasserman

Systems and methods are provided for determining a response to a query in a dialog. An entity extractor extracts rules and conditions associated with the query and determines a particular task. The disclosed technology generates a transformer-based dialog embedding by pre-training a transformer using dialog corpora including a plurality of tasks. A task-specific classifier generates a first set of candidate responses based on rules and conditions associated with the task. The transformer-based dialog embedding generates a second set of candidate responses to the query. The classifier accommodates changes made to a task by an interactive dialog editor as machine teaching. A response generator generates a response based on the first and second sets of candidate responses using an optimization function. The disclosed technology leverages both a data-driven, generative model (a transformer) based on dialog corpora and a user-driven, task-specific rule-based classifier that accommodating updates in rules and conditions associated with a particular task.

Hybrid transformer-based dialog processor

Methods and systems are disclosed for improving dialog management for task-oriented dialog systems. The disclosed dialog builder leverages machine teaching processing to improve development of dialog managers. In this way, the dialog builder combines the strengths of both rule-based and machine-learned approaches to allow dialog authors to: (1) import a dialog graph developed using popular dialog composers, (2) convert the dialog graph to text-based training dialogs, (3) continuously improve the trained dialogs based on log dialogs, and (4) generate a corrected dialog for retraining the machine learning.

Training a user-system dialog in a task-oriented dialog system

Disclosed are various embodiments related to intercepting, modifying, and analyzing messages being exchanged between two entities. In one embodiment, among others, a method comprises intercepting messages being exchanged between a first entity and a second entity. The intercepted messages are modified to substitute sender information identifying the sender with proxy sender information such that the sender is anonymous to the intended recipient. The messages are also analyzed to determine at least one performance metric associated with the messages being exchanged.

Closed loop communication

Technologies are described herein for classifying structured documents based on the structure of the document. A structured document is received, and the structural elements are parsed from the document to generate a text string representing the structure of the document instead of the semantic textual content of the document. The text string may be broken into N-grams utilizing a sliding window, and a classifier trained from similar structured documents labeled as belonging to one of a number of document classes is utilized to determine a probability that the document belongs to each of the document classes based on the N-grams.

Classifying structured documents

Aspects of the present disclosure relate to management of evaluated rule data sets. Specifically, a unreduced evaluated rule data set may contain a number of items to be compared or analyzed according to a number of rules, and may also contain the results of such analysis. An illustrative reduced evaluated data set can include the results of evaluated rules. When utilized in conjunction with an item data set and a rule data set, the information contained within the unreduced evaluated rule data set may be maintained. The reduce memory requirements of the reduced evaluated rule data set may facilitate storage of the reduced evaluated rule data set in faster to access memory, or may facilitate distributed computation of the reduced evaluated rule data set.

Machine learning memory management and distributed rule evaluation

Disclosed are various embodiments of a system. In one embodiment, among others, a method comprises intercepting a communication between a first party and a second party in a communication forum. The communication includes first party proxy information as an intended recipient information. The method further comprises accessing a communication pair using the intended recipient information. The intended recipient information is associated with second party proxy information. The second party proxy information is associated with second party information. Additionally, the method comprises determining whether the identity of the sender is valid.

Disclosed are various embodiments of a system. In one embodiment, among others, a method comprises intercepting a communication between a first party and a second party in a communication forum, the communication including a first party proxy information as an intended recipient information. The method further comprises accessing a communication pair using the intended recipient information, the intended recipient information being associated with a second party proxy information, the second party proxy information being associated with a second party information. Additionally, the method comprises determining whether the identity of the sender is valid.

Growing community of inventors

Seattle, WA, United States of America

Thomas Park