Evaluating Semantic Matching Techniques for Technical Documents
Abstract
Machine learning models that employ NLP techniques have become more widely accessible, making them an attractive solution for text and document classification tasks traditionally accomplished by humans. Two such use cases are matching the specialized experience required for a job to statements in applicant resumes, and xC;finding and labelling clauses in legal contracts The AFMC has an immediate need for solutions to civilian hiring. However, there is currently no truth data to validate against. A similar task is contract understanding for which there is the CUAD, a recently published repository of 510 contracts manually labelled by legal experts. The presented semantic matching approach first extracts, preprocesses and embeds contract clauses into a 512-dimesnion TF-IDF feature vector. Four logistic models are trained on a subset of these vectors. Then, the models are tuned to accept the contracts as text documents split into sliding windows of words. Next, the model performances are measured on a previously isolated test set and compared against the transformer models employed in the original CUAD research.
Document Details
- Document Type
- Technical Report
- Publication Date
- Mar 24, 2022
- Accession Number
- AD1166894
Entities
People
- Rain F. Dartt
Organizations
- Air Force Institute of Technology