paper-with-me

Papers

ATOGAN:Adaptive Training Objective Generative Adversarial Network for Cross-lingual Word Alignment in Non-Isomorphic Embedding Spaces

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

Cross-lingual word alignment is a task for word translation from monolingual word embedding spaces of two languages. Recent works are mostly based on supervised approaches, which need specific bilingual seed dictionaries. The unsupervised adversarial approaches, which utilize the generative adversarial networks to map the whole monolingual space, do not need any aligned data. However these approaches pay no attention to the problem of mode collapse and gradient disappearance in generative adversarial networks(GAN). We proposed an adaptive training objective generative adversarial network(ATOGAN). We combined particle swarm optimization(PSO) with GAN to select the training objective in GAN's training, which alleviates the problem of mode collapse and gradient disappearance. Moreover, we improved the word alignment by bi-directional mapping and consistency loss. Experimental results demonstrate that our approach is better than several state-of-the-art approaches in distant language pairs(non-isomorphic embedding spaces).

📄 PDF Abstract BibTeX

Code (0)

등록된 구현이 없습니다.

Tasks

Generative Adversarial NetworkTranslationWord AlignmentWord Translation

Similar Papers 제목 키워드 기반

PotatoGANs: Utilizing Generative Adversarial Networks, Instance Segmentation, and Explainable AI for Enhanced Potato Disease Identification and Classification

2024-05-12 · Mohammad Shafiul Alam, Fatema Tuj Johora Faria, Mukaffi Bin Moin, Ahmed Al Wase 외

Numerous applications have resulted from the automation of agricultural disease segmentation using deep learning techniques. However, when applied to new conditions, these applications frequently face the difficulty of o…

Data AugmentationInstance SegmentationSemantic Segmentation

Exploring Model Robustness with Adaptive Networks and Improved Adversarial Training

2020-05-30 · Zheng Xu, Ali Shafahi, Tom Goldstein

Adversarial training has proven to be effective in hardening networks against adversarial examples. However, the gained robustness is limited by network capacity and number of training samples. Consequently, to build mor…

Evolutionary Generative Adversarial Networks

2018-03-01 · Chaoyue Wang, Chang Xu, Xin Yao, DaCheng Tao

Generative adversarial networks (GAN) have been effective for learning generative models for real-world data. However, existing GANs (GAN and its variants) tend to suffer from training problems such as instability and mo…

Diversity

Solving a class of non-convex min-max games using adaptive momentum methods

2021-04-26 · Babak Barazandeh, Davoud Ataee Tarzanagh, George Michailidis

Adaptive momentum methods have recently attracted a lot of attention for training of deep neural networks. They use an exponential moving average of past gradients of the objective function to update both search directio…

Generative Multi-Adversarial Networks

2016-11-05 · Ishan Durugkar, Ian Gemp, Sridhar Mahadevan

Generative adversarial networks (GANs) are a framework for producing a generative model by way of a two-player minimax game. In this paper, we propose the \emph{Generative Multi-Adversarial Network} (GMAN), a framework t…

Image Generation