Amazon Technologies, Inc.

Krishnakumar Rajagopalan

Bing Xiang

Peng Xu

Sudipta Sengupta

Ramesh M Nallapati

Zhiguo Wang

Saurabh Kumar Singh

Dimitrios Soulios

Yong Yuan

Xiaofei Ma

Ankit Sultania

Dong Wang

Zhiheng Huang

Andrew M Grant

Milan Saini

Jean-Pierre Dodel

Jared Lee Katzman

Nithin Kunala

Techniques for searching documents are described. An exemplary method includes receiving a document search query; querying at least one index based upon the document search query to identify matching data; fetching the identified matched data; determining one or more of a top ranked passage and top ranked documents from the set of documents based upon one or more invocations of one or more machine learning models based at least on the fetched identified matched data and the document search query; and returning one or more of the top ranked passage and the proper subset of documents.

Systems, apparatuses, and methods for document querying

Techniques for intaking one or more documents are described. An exemplary method includes receiving an ingestion request to ingest a document; extracting text from the document; pre-processing the extracted text to generate pre-processed text that is predictable and analyzable; generating an index entry for the extracted text, the index entry to map the extracted text to a reserved field of a plurality of reserved fields; and storing the extracted text, index entry, and pre-processed text in at least one data storage location.

Systems, apparatuses, and method for document ingestion

Growing community of inventors

Edison, NJ, United States of America

Krishnakumar Rajagopalan