Structural analogy from a single image pair
The task of unsupervised image‐to‐image translation has seen substantial advancements in
recent years through the use of deep neural networks. Typically, the proposed solutions …
recent years through the use of deep neural networks. Typically, the proposed solutions …
Leveraging vector space similarity for learning cross-lingual word embeddings: A systematic review
This article presents a systematic literature review on quantifying the proximity between
independently trained monolingual word embedding spaces. A search was carried out in the …
independently trained monolingual word embedding spaces. A search was carried out in the …
Semi-supervised bilingual lexicon induction with two-way interaction
Semi-supervision is a promising paradigm for Bilingual Lexicon Induction (BLI) with limited
annotations. However, previous semisupervised methods do not fully utilize the knowledge …
annotations. However, previous semisupervised methods do not fully utilize the knowledge …
A survey and evaluation of iterative optimization algorithms for cooperative localization
YS Fan, F Meng, GJ Li, XG Qi - Physical Communication, 2023 - Elsevier
Cooperative localization (Co-localization) refers to the establishment of an objective function
through relative measurements and obtaining the relative position information by solving the …
through relative measurements and obtaining the relative position information by solving the …
Adversarial training with wasserstein distance for learning cross-lingual word embeddings
Recent studies have managed to learn cross-lingual word embeddings in a completely
unsupervised manner through generative adversarial networks (GANs). These GANs-based …
unsupervised manner through generative adversarial networks (GANs). These GANs-based …
A Novel Unsupervised Approach for Cross-Lingual Word Alignment in Low Isomorphic Embedding Spaces
Q Tao, Z Xiong, B Han, X Fan… - IEEE/ACM Transactions on …, 2023 - ieeexplore.ieee.org
Cross-lingual word alignment is the task for word translation between monolingual word
embedding spaces of two different languages. Recent work is mostly based on supervised …
embedding spaces of two different languages. Recent work is mostly based on supervised …
Cross-lingual embeddings with auxiliary topic models
Projection-based methods for generating high-quality Cross-Lingual Embeddings (CLEs)
have shown state-of-the-art performance in many multilingual applications. Supervised …
have shown state-of-the-art performance in many multilingual applications. Supervised …
A Structure-Aware Generative Adversarial Network for Bilingual Lexicon Induction
B Han, Q Tao, L Li, Z Xiong - Findings of the Association for …, 2023 - aclanthology.org
Bilingual lexicon induction (BLI) is the task of inducing word translations with a learned
mapping function that aligns monolingual word embedding spaces in two different …
mapping function that aligns monolingual word embedding spaces in two different …
[HTML][HTML] Bilingual autoencoder-based efficient harmonization of multi-source private data for accurate predictive modeling
Sharing electronic health record data is essential for advanced analysis, but may put
sensitive information at risk. Several studies have attempted to address this risk using …
sensitive information at risk. Several studies have attempted to address this risk using …
An unsupervised cross-lingual word alignment approach based on cycle-GAN and hybrid training
Z Xiong, Q Tao - 2021 International Conference on Electrical …, 2021 - ieeexplore.ieee.org
Cross-lingual word alignment is an important task which would produce an effect on many
downstream tasks. Most work on cross-lingual word alignment learn a mapping between the …
downstream tasks. Most work on cross-lingual word alignment learn a mapping between the …