View The Document

Accession Number:

AD1157022

Title:

Using Custom NER Models to Extract DOD Specific Entities from Contracts

Author(s):

• Haberstich, Kayla P

Author Organization(s):

• AIR FORCE INSTITUTE OF TECHNOLOGY WRIGHT-PATTERSON AFB OH

Report Date:

2021-12-23

Abstract:

The Air Force Sustainment Center collected 3.7 million contracts onto the Air Force Research Laboratory's high power computers. They are in the format of a .pdf or scanned document, making them unstructured data. The Data Analytics Resource Team extracted the documents into a textual format for use in further analysis. This thesis looks to extract four DOD specific entities (NSN, Part Number, CAGE Code, and Supplier Name) from the contracts using custom NER models. This newly extracted information will allow the Air Force to identify what parts are supplied by which vendors. This information along with historical CLIN pricing for the vendor specific part number can give decision makers the ability to negotiate pricing based on historical data and competitor pricing. In addition to just pricing, part numbers can be aligned with maintenance data to make informed decisions on which vendor to go with by analyzing life cycle costs of a part.

Document Type:

Conference:

Journal:

Pages:

73

File Size:

1.13MB

Contracts:

Grants:

Descriptors:

Identifiers:

• ner (Named Entity Recognition)
• High Power Computing
• Word Embedding
• data EXTRACTION
• NSN (national stock number)
• Part Number
• cage (Commercial and Government Entity)
• CAGE Code
• Supplier Name
• machine learning algorithms
• ner evaluation metrics
• regex (regular expression)

SubjectCategory:

• Mathematical and Computer Sciences
• Behavioral and Social Sciences
• Military Sciences

Communities of Interest:

• Autonomy

Distribution Statement:

Approved For Public Release

View The Document