Invention Application
- Patent Title: LEARNING FROM INTERACTIONS FOR A SPOKEN DIALOG SYSTEM
-
Application No.: US15483213Application Date: 2017-04-10
-
Publication No.: US20170213546A1Publication Date: 2017-07-27
- Inventor: Mazin GILBERT , Esther LEVIN , Michael Lederman LITTMAN , Robert E. Schapire
- Applicant: AT&T Intellectual Property II, L.P.
- Main IPC: G10L15/065
- IPC: G10L15/065 ; G10L15/18 ; G10L15/06
Abstract:
In one embodiment, a semantic classifier input and a corresponding label attributed to the semantic classifier input may be obtained. A determination may be made whether the corresponding label is correct based on logged interaction data. An entry of an adaptation corpus may be generated based on a result of the determination. Operation of the semantic classifier may be adapted based on the adaptation corpus.
Public/Granted literature
- US10217457B2 Learning from interactions for a spoken dialog system Public/Granted day:2019-02-26
Information query
