公开(公告)号：US10776693B2

公开(公告)日：2020-09-15

申请号：US15420119

申请日：2017-01-31

Applicant: XEROX CORPORATION

Inventor： Ganesh Jawahar ,  Himanshu Sharad Bhatt ,  Manjira Sinha ,  Shourya Roy

IPC: G06N3/08 ,  G06N3/04

Abstract: The disclosed embodiments illustrate a domain adaptation method for learning transferable feature representations from a source domain for a target domain. The method includes receiving input data comprising a plurality of labeled instances of the source domain and a plurality of unlabeled instances of the target domain. The method includes learning common representation shared between the source domain and the target domain, based on the plurality of labeled instances of the source domain. The method includes labeling one or more unlabeled instances in the plurality of unlabeled instances of the target domain, based on the common representation. The method includes determining a target specific representation corresponding to the target domain. The method includes training a target specific classifier based on the target specific representation and the common representation to perform text classification on remaining one or more unlabeled instances of the plurality of unlabeled instances of the target domain.

公开(公告)号：US20180218284A1

公开(公告)日：2018-08-02

申请号：US15420119

申请日：2017-01-31

Applicant: XEROX CORPORATION

Inventor： Ganesh Jawahar ,  Himanshu Sharad Bhatt ,  Manjira Sinha ,  Shourya Roy

IPC: G06N99/00 ,  G06N7/00

CPC classification number: G06N3/08 ,  G06N3/0454

Abstract: The disclosed embodiments illustrate a domain adaptation method for learning transferable feature representations from a source domain for a target domain. The method includes receiving input data comprising a plurality of labeled instances of the source domain and a plurality of unlabeled instances of the target domain. The method includes learning common representation shared between the source domain and the target domain, based on the plurality of labeled instances of the source domain. The method includes labeling one or more unlabeled instances in the plurality of unlabeled instances of the target domain, based on the common representation. The method includes determining a target specific representation corresponding to the target domain. The method includes training a target specific classifier based on the target specific representation and the common representation to perform text classification on remaining one or more unlabeled instances of the plurality of unlabeled instances of the target domain.