Invention Application
- Patent Title: MODEL-INDEPENDENT CONFIDENCE VALUE PREDICTION MACHINE LEARNED MODEL
-
Application No.: US17354202Application Date: 2021-06-22
-
Publication No.: US20220366301A1Publication Date: 2022-11-17
- Inventor: Nurzat Rakhmanberdieva , Alexey Streltsov , Christian Reisswig
- Applicant: SAP SE
- Applicant Address: DE Walldorf
- Assignee: SAP SE
- Current Assignee: SAP SE
- Current Assignee Address: DE Walldorf
- Main IPC: G06N20/00
- IPC: G06N20/00 ; G06K9/62 ; G06K9/00 ; G06N3/02

Abstract:
In an example embodiment, a confidence score is computed for a predicted label (from a first model) for information extracted from a document. The confidence score is computed using a machine learned model different than the first model which is based on a Sliding-Window method. The Sliding-Window method may be based on convolutional neural networks classification, using sliding windows. It receives as input (1) the string of extracted information from an independent previous information extracted step (the “input text”), (2) the string's predicted class label, (3) the string's coordinate location in the document, and (4) the text of the document (for additional context information). The Sliding-Window method's task is to predict the confidence score to determine the correctness of the predicted label for the information.
Information query