Multi-Stage Framework with Refinement Based Point Set Registration for Unsupervised Bi-Lingual Word Alignment

2022-10-01 · COLING 2022 10 · Silviu Vlad Oprea, Sourav Dutta, Haytham Assem

Cross-lingual alignment of word embeddings are important in knowledge transfer across languages, for improving machine translation and other multi-lingual applications. Current unsupervised approaches relying on learning structure-preserving transformations, using adversarial networks and refinement strategies, suffer from instability and convergence issues. This paper proposes BioSpere, a novel multi-stage framework for unsupervised mapping of bi-lingual word embeddings onto a shared vector space, by combining adversarial initialization, refinement procedure and point set registration. Experiments for parallel dictionary induction and word similarity demonstrate state-of-the-art unsupervised results for BioSpere on diverse languages – showcasing robustness against variable adversarial performance.

📄 PDF Abstract BibTeX

Code (0)

등록된 구현이 없습니다.

Tasks

Machine Translation Transfer Learning Translation Word AlignmentWord EmbeddingsWord Similarity

Multi-Stage Framework with Refinement based Point Set Registration for Unsupervised Bi-Lingual Word Alignment

2021-11-16 · ACL ARR November 2021 11 · Anonymous

Cross-lingual alignment of word embeddings play an important role in knowledge transfer across languages, for improving machine translation and other multi-lingual applications. Current unsupervised approaches rely on le…

Machine Translation Sentence Transfer Learning Translation+3

Learning multiview 3D point cloud registration

2020-01-15 · CVPR 2020 6 · Zan Gojcic, Caifa Zhou, Jan D. Wegner, Leonidas J. Guibas 외

We present a novel, end-to-end learnable, multiview 3D point cloud registration algorithm. Registration of multiple scans typically follows a two-stage pipeline: the initial pairwise alignment and the globally consistent…

Point Cloud Registration

Self-Supervised Cross-Modal Learning for Image-to-Point Cloud Registration

2025-09-19 · Xingmei Wang, Xiaoyu Hu, Chengkai Huang, Ziyan Zeng 외 arxiv

Bridging 2D and 3D sensor modalities is critical for robust perception in autonomous systems. However, image-to-point cloud (I2P) registration remains challenging due to the semantic-geometric gap between texture-rich bu…

Point Cloud Registration Contrastive Learning Pose Estimation Point Clouds

Coarse-to-Fine Non-rigid Multi-modal Image Registration for Historical Panel Paintings based on Crack Structures

2026-01-22 · Aline Sindel, Andreas Maier, Vincent Christlein arxiv

Art technological investigations of historical panel paintings rely on acquiring multi-modal image data, including visual light photography, infrared reflectography, ultraviolet fluorescence photography, x-radiography, a…

Graph Neural Network Keypoint Detection Image Registration

CVSD-Reg: Cross-Modal Visual Semantic Prior Distillation for Robust LiDAR Registration

2026-08-20 · Eunsoo Im, Junghun Suh, Gyeonggwan Lee, Seunghwan Hong arxiv

Learning-based global point cloud registration has achieved remarkable progress, yet its reliance on geometric representations makes existing methods sensitive to variations in point density, scan pattern, viewpoint, and…