Invention Grant
- Patent Title: Accounting for positional bias in a document retrieval system using machine learning
-
Application No.: US15292033Application Date: 2016-10-12
-
Publication No.: US10565265B2Publication Date: 2020-02-18
- Inventor: Zachary Alexander , Scott Thurston Rickard, Jr. , Clifford Z. Huang , J. Justin Donaldson
- Applicant: salesforce.com, inc.
- Applicant Address: US CA San Francisco
- Assignee: salesforce.com, inc.
- Current Assignee: salesforce.com, inc.
- Current Assignee Address: US CA San Francisco
- Agency: Fenwick & West LLP
- Main IPC: G06F17/30
- IPC: G06F17/30 ; G06F16/93

Abstract:
A document retrieval system tracks user selections of documents from query search results and uses the selections as proxies for manual user labeling of document relevance. The system trains a model representing the significance of different document features when calculating true document relevance for users. To factor in positional biases inherent in user selections in search results, the system learns positional bias values for different search result positions, such that the positional bias values are accounted for when computing document feature features that are used to compute true document relevance.
Public/Granted literature
- US20180101534A1 Accounting for Positional Bias in A Document Retrieval System Using Machine Learning Public/Granted day:2018-04-12
Information query