Improving neural machine translation with sentence alignment learning

Shi, Xuewen; Huang, Heyan; Jian, Ping; Tang, Yi-Kun

doi:10.1016/j.neucom.2020.05.104

Cited by 30 publications

(11 citation statements)

References 11 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The rest baseline can be categorized into two classes. GraphDG [48], CGCF [49], ConfVAE [91], ConfGF [86], and DGSM [92] combine generative models with distance geometry, which first generates interatomic distance matrices and then iteratively generates atomic coordinates. CVGAE [50], GeoMol [51], DMCG [93], and GeoDiff [94] directly generate atomic coordinates.…”

Section: C4 Molecular Conformation Generationmentioning

confidence: 99%

Uni-Mol: A Universal 3D Molecular Representation Learning Framework

Zhou

Gao

Ding

et al. 2023

Preprint

107

111

View full text Add to dashboard Cite

Molecular representation learning (MRL) has gained tremendous attention due to its critical role in learning from limited supervised data for applications like drug design. In most MRL methods, molecules are treated as 1D sequential tokens or 2D topology graphs, limiting their ability to incorporate 3D information for downstream tasks and, in particular, making it almost impossible for 3D geometry prediction/generation. In this paper, we propose a universal 3D MRL framework, called Uni-Mol, that significantly enlarges the representation ability and application scope of MRL schemes. Uni-Mol contains two pretrained models with the same SE(3) Transformer architecture: a molecular model pretrained by 209M molecular conformations; a pocket model pretrained by 3M candidate protein pocket data. Besides, Uni-Mol contains several finetuning strategies to apply the pretrained models to various downstream tasks. By properly incorporating 3D information, Uni-Mol outperforms SOTA in 14/15 molecular property prediction tasks. Moreover, Uni-Mol achieves superior performance in 3D spatial tasks, including protein-ligand binding pose prediction, molecular conformation generation, etc. The code, model, and data are made publicly available at https://github.com/dptech-corp/Uni-Mol.

show abstract

Section: C4 Molecular Conformation Generationmentioning

confidence: 99%

Uni-Mol: A Universal 3D Molecular Representation Learning Framework

Zhou

Gao

Ding

et al. 2023

Preprint

107

111

View full text Add to dashboard Cite

show abstract

“…Diffusion probabilistic models learn to generate data via denoising samples from a prior distribution [44, 17, 45]. Recently, progress has been made in developing equivariant diffusion models for molecular 3D structures [51, 19, 42]. Atoms in a molecule do not have natural orientations so the generation process is different from generating protein structures.…”

Section: Related Workmentioning

confidence: 99%

Antigen-Specific Antibody Design and Optimization with Diffusion-Based Generative Models for Protein Structures

Luo

Peng

et al. 2022

Preprint

103

View full text Add to dashboard Cite

Antibodies are immune system proteins that protect the host by binding to specific antigens such as viruses and bacteria. The binding between antibodies and antigens are mainly determined by the complementarity-determining regions (CDR) on the antibodies. In this work, we develop a deep generative model that jointly models sequences and structures of CDRs based on diffusion processes and equivariant neural networks. Our method is the first deep learning-based method that can explicitly target specific antigen structures and generate antibodies at atomic resolution. The model is a ''Swiss Army Knife'' which is capable of sequence-structure co-design, sequence design for given backbone structures, and antibody optimization. For antibody optimization, we propose a special sampling scheme that first perturbs the given antibody and then denoises it. As the number of available antibody structures is relatively scarce, we curate a new dataset that contains antibody-like proteins as a complement to the original antibody dataset for training. We conduct extensive experiments to evaluate the quality of both sequences and structures of designed antibodies. We find that our model could yield highly competitive results in terms of binding affinity measured by biophysical energy functions and other protein design metrics.

show abstract

“…Multi-source translation, an approach to exploit multiple inputs (e.g., in two different languages) to increase performance, and missing data management investigated by Nishimura et al [95] might also be a way to achieve better Bangla MT performance. Gated recurrent unit (GRU), an advanced LSTM model, and its updated model [96] might perform well for Bangla MT. Moreover, recently developed HMT techniques, such as [34] [35] [33], might bring good motivation for better Bangla MT system development.…”

Section: Future Prospects Of Bangla Mt From This Studymentioning

confidence: 99%

Recent Progress, Emerging Techniques, and Future Research Prospects of Bangla Machine Translation: A Systematic Review

Akhand¹,

Roy²,

Dhar³

et al. 2021

IJACSA

View full text Add to dashboard Cite

Machine Translation (MT), the way of translating texts or documents from a source language to a target language automatically without human intervention, has gained popularity in the growing information technology-based era of globalization. Bangla is a major language, and several MT studies with different tools and techniques have been investigated in the last two decades. Considering the importance of the Bangla language and its prospects in MT studies, this study provides a comprehensive review of existing Bangla MT studies to meet the timely demand. Specifically, at first, the basic ideas of different MT methods (Rule-based, Example-based, Statistical, Neural, and Hybrid) and performance measures of MT are presented as a background study of the present review. Then an overview of the Bangla language and a brief description of the available Bangla-English corpora are provided. Next, a description of the existing Bangla MT studies is provided categorically following the common strategic fashion to create a valuable reference for current researchers in the field that is also suitable for nonexpert users. The achieved performances of individual methods are also compared in a tabular form. Finally, a number of future research prospects are revealed from the studies, encouraging researchers and practitioners to develop a better and comprehensive Bangla MT system.

show abstract

Improving neural machine translation with sentence alignment learning

Cited by 30 publications

References 11 publications

Uni-Mol: A Universal 3D Molecular Representation Learning Framework

Uni-Mol: A Universal 3D Molecular Representation Learning Framework

Antigen-Specific Antibody Design and Optimization with Diffusion-Based Generative Models for Protein Structures

Recent Progress, Emerging Techniques, and Future Research Prospects of Bangla Machine Translation: A Systematic Review

Contact Info

Product

Resources

About