Invention Application
- Patent Title: METHOD FOR TRAINING INFORMATION RETRIEVAL MODEL BASED ON WEAK-SUPERVISION AND METHOD FOR PROVIDING SEARCH RESULT USING SUCH MODEL
-
Application No.: US17744847Application Date: 2022-05-16
-
Publication No.: US20220343195A1Publication Date: 2022-10-27
- Inventor: Sung Bum PARK , Suehyun Chang , Geun Jin Ahn
- Applicant: Hoseo University Academic Cooperation Foundation , Livin Al Inc.
- Applicant Address: KR Asan -si; KR Cheonan-si
- Assignee: Hoseo University Academic Cooperation Foundation,Livin Al Inc.
- Current Assignee: Hoseo University Academic Cooperation Foundation,Livin Al Inc.
- Current Assignee Address: KR Asan -si; KR Cheonan-si
- Priority: KR10-2020-0053018 20200501
- Main IPC: G06N5/04
- IPC: G06N5/04 ; G06F16/93 ; G06N20/00
Abstract:
A search method using an artificial intelligence based information retrieval model and a method for training the artificial intelligence based information retrieval model used for the method are provided.
In the method, even if there is no labeled data and only a corpus exists, the artificial intelligence based information retrieval model can be trained using the weak-supervision methodology. Search can be performed by dividing documents into passages having short lengths. Compared to an information retrieval model based on unsupervised learning, improved search results are provided.
In the method, even if there is no labeled data and only a corpus exists, the artificial intelligence based information retrieval model can be trained using the weak-supervision methodology. Search can be performed by dividing documents into passages having short lengths. Compared to an information retrieval model based on unsupervised learning, improved search results are provided.
Public/Granted literature
Information query
