Amazon Technologies, Inc.

Sanjiv Ranjan Das

Krishnaram Kenthapadi

Muhammad Bilal Zafar

Cedric Philippe Archambeau

Shuai Zheng

Yue Zhao

Michele Donini

Li Zhang

Zheng Zhang

Pinar Altin Yilmaz

Xinyu Liu

Tyler Stephen Hill

Sheng Zha

Xin Huang

Shenghua Yue

Michaela Hardt

Keerthan Harish Vasist

Pedro L Larroy

Zhijiang He

Techniques for machine learning (ML) and natural language processing (NLP) are described. One technique enables the creation of a clean training dataset through just a few API calls. Another technique provides an automated process for generating a domain-specific lexicon, which is then used to generate ML training datasets, in a manner that requires little to no human labor. Another technique gathers ML training data from domain-specific public sources, which are more likely than typical public sources to contain focused terminology and to be free from errors, thus resulting in trained ML models that provide more accurate inferences.

Domain-specific language models

A determination is made that an explanatory data set for a common set of predictions generated by a machine learning model for records containing text tokens is to be provided. Respective groups of related tokens are identified from the text attributes of the records, and record-level prediction influence scores are generated for the token groups. An aggregate prediction influence score is generated for at least some of the token groups from the record-level scores, and an explanatory data set based on the aggregate scores is presented.

Global explanations of machine learning model predictions for input containing text attributes

Growing community of inventors

San Jose, CA, United States of America

Sanjiv Ranjan Das