Journal of Computer Science and Technology


Unsupervised Domain Adaptation on Sentence Matching Through Self-Supervision

Gui-Rong Bai1,2 (白桂荣), Qing-Bin Liu1,2 (刘庆斌), Shi-Zhu He1,2,* (何世柱), Kang Liu1,2 (刘康), and Jun Zhao1,2 (赵军)   

  1. 1National Laboratory of Pattern Recognition, Institute of Automation, Chinese Academy of Sciences, Beijing 100190, China
    2School of Artificial Intelligence, University of Chinese Academy of Sciences, Beijing 100049, China

Although neural approaches have yielded state-of-the-art results in the sentence matching task, the performance of them inevitably drops dramatically when applied to unseen domains. To tackle this cross-domain challenge, we address unsupervised domain adaptation on sentence matching, in which the goal is to have good performance on a target domain with only unlabeled target domain data as well as labeled source domain data. Specifically, we propose to perform self-supervised tasks to achieve it. Different from previous unsupervised domain adaptation methods, self-supervision can not only flexibly suit the characteristics of sentence matching with special design, but also be much easier to optimize. When training, each self-supervised task is performed on both domains simultaneously in an easy-to-hard curriculum, which gradually brings the two domains closer together along the direction relevant to that task. As a result, the classifier trained on the source domain is able to generalize to the unlabeled target domain. In total, we present three types of self-supervised tasks and the results demonstrate the superiority of them. In addition, we further study the performance of different usages of self-supervised tasks, which would inspire how to effectively utilize self-supervision for cross-domain scenarios.



Key words: unsupervised domain adaptation, sentence matching, self-supervision


No related articles found!
Full text



[1] Zhou Di;. A Recovery Technique for Distributed Communicating Process Systems[J]. , 1986, 1(2): 34 -43 .
[2] Li Wei;. A Structural Operational Semantics for an Edison Like Language(2)[J]. , 1986, 1(2): 42 -53 .
[3] Li Wanxue;. Almost Optimal Dynamic 2-3 Trees[J]. , 1986, 1(2): 60 -71 .
[4] Feng Yulin;. Recursive Implementation of VLSI Circuits[J]. , 1986, 1(2): 72 -82 .
[5] C.Y.Chung; H.R.Hwa;. A Chinese Information Processing System[J]. , 1986, 1(2): 15 -24 .
[6] Jin Lan; Yang Yuanyuan;. A Modified Version of Chordal Ring[J]. , 1986, 1(3): 15 -32 .
[7] Wu Enhua;. A Graphics System Distributed across a Local Area Network[J]. , 1986, 1(3): 53 -64 .
[8] Zhang Cui; Zhao Qinping; Xu Jiafu;. Kernel Language KLND[J]. , 1986, 1(3): 65 -79 .
[9] Wang Jianchao; Wei Daozheng;. An Effective Test Generation Algorithm for Combinational Circuits[J]. , 1986, 1(4): 1 -16 .
[10] Huang Heyan;. A Parallel Implementation Model of HPARLOG[J]. , 1986, 1(4): 27 -38 .

ISSN 1000-9000(Print)

CN 11-2296/TP

Editorial Board
Author Guidelines
Journal of Computer Science and Technology
Institute of Computing Technology, Chinese Academy of Sciences
P.O. Box 2704, Beijing 100190 P.R. China
  Copyright ©2015 JCST, All Rights Reserved