Geometry-aware Domain Adaptation for Unsupervised Alignment of Word Embeddings

被引:0
|
作者
Jawanpuria, Pratik [1 ]
Meghwanshi, Mayank [1 ]
Mishra, Bamdev [1 ]
机构
[1] Microsoft, Hyderabad, Telangana, India
关键词
OPTIMIZATION;
D O I
暂无
中图分类号
TP18 [人工智能理论];
学科分类号
081104 ; 0812 ; 0835 ; 1405 ;
摘要
We propose a novel manifold based geometric approach for learning unsupervised alignment of word embeddings between the source and the target languages. Our approach formulates the alignment learning problem as a domain adaptation problem over the manifold of doubly stochastic matrices. This viewpoint arises from the aim to align the second order information of the two language spaces. The rich geometry of the doubly stochastic manifold allows to employ efficient Riemannian conjugate gradient algorithm for the proposed formulation. Empirically, the proposed approach outperforms state-of-the-art optimal transport based approach on the bilingual lexicon induction task across several language pairs. The performance improvement is more significant for distant language pairs.
引用
收藏
页码:3052 / 3058
页数:7
相关论文
共 50 条
  • [1] Discriminative and Geometry-Aware Unsupervised Domain Adaptation
    Luo, Lingkun
    Chen, Liming
    Hu, Shiqiang
    Lu, Ying
    Wang, Xiaofang
    [J]. IEEE TRANSACTIONS ON CYBERNETICS, 2020, 50 (09) : 3914 - 3927
  • [2] Geometry-Aware Unsupervised Domain Adaptation for Stereo Matching
    Sakuma, Hiroki
    Konishi, Yoshinori
    [J]. 2021 IEEE INTERNATIONAL CONFERENCE ON ROBOTICS AND AUTOMATION (ICRA 2021), 2021, : 6116 - 6123
  • [3] Geometry-Aware Self-Training for Unsupervised Domain Adaptation on Object Point Clouds
    Zou, Longkun
    Tang, Hui
    Chen, Ke
    Jia, Kui
    [J]. 2021 IEEE/CVF INTERNATIONAL CONFERENCE ON COMPUTER VISION (ICCV 2021), 2021, : 6383 - 6392
  • [4] Domain Adaptation on Point Clouds via Geometry-Aware Implicits
    Shen, Yuefan
    Yang, Yanchao
    Yan, Mi
    Wang, He
    Zheng, Youyi
    Guibas, Leonidas
    [J]. 2022 IEEE/CVF CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR), 2022, : 7213 - 7222
  • [5] Geometry-Aware Symmetric Domain Adaptation for Monocular Depth Estimation
    Zhao, Shanshan
    Fu, Huan
    Gong, Mingming
    Tao, Dacheng
    [J]. 2019 IEEE/CVF CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR 2019), 2019, : 9780 - 9790
  • [6] Unsupervised Alignment of Distributional Word Embeddings
    Diallo, Aissatou
    Fuernkranz, Johannes
    [J]. ADVANCES IN ARTIFICIAL INTELLIGENCE, KI 2022, 2022, 13404 : 60 - 74
  • [7] Geometry-Aware Adaptation for Pretrained Models
    Roberts, Nicholas
    Li, Xintong
    Adila, Dyah
    Cromp, Sonia
    Huang, Tzu-Heng
    Zhao, Jitian
    Sala, Frederic
    [J]. ADVANCES IN NEURAL INFORMATION PROCESSING SYSTEMS 36 (NEURIPS 2023), 2023,
  • [8] Unsupervised Geometry-Aware Deep LiDAR Odometry
    Cho, Younggun
    Kim, Giseop
    Kim, Ayoung
    [J]. 2020 IEEE INTERNATIONAL CONFERENCE ON ROBOTICS AND AUTOMATION (ICRA), 2020, : 2145 - 2152
  • [9] Unsupervised Domain Adaptation With Class-Aware Memory Alignment
    Wang, Hui
    Zheng, Liangli
    Zhao, Hanbin
    Li, Shijian
    Li, Xi
    [J]. IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS, 2024, 35 (07) : 9930 - 9942
  • [10] Unsupervised Domain Adaptation for Neural Machine Translation with Domain-Aware Feature Embeddings
    Dou, Zi-Yi
    Hu, Junjie
    Anastasopoulos, Antonios
    Neubig, Graham
    [J]. 2019 CONFERENCE ON EMPIRICAL METHODS IN NATURAL LANGUAGE PROCESSING AND THE 9TH INTERNATIONAL JOINT CONFERENCE ON NATURAL LANGUAGE PROCESSING (EMNLP-IJCNLP 2019): PROCEEDINGS OF THE CONFERENCE, 2019, : 1417 - 1422