Dynamic Mask Curriculum Learning for Non-Autoregressive Neural Machine Translation

Wang, Yisong; Hou, Hongxu; Sun, Shuo; Wu, Nanping; Jian, Weichen; Yang, Zongheng; Wang, Pengcong

doi:10.1007/978-981-19-7960-6_8

Cited by 5 publications

(7 citation statements)

References 9 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Depending on the representation of molecules, the sequence can be a series of SMILES tokens or molecular edit actions on the molecule graph. By adopting SMILES representation, a popular paradigm of existing retrosynthesis methods is to formulate retrosynthesis prediction as a sequence‐to‐sequence translation problem 73 . This translation process is usually token‐by‐token and autoregressive, that is, based on the input product SMILES and the already decoded reactant SMILES, to obtain the next possible reactant token.…”

Section: Single‐step Retrosynthesis Methodsmentioning

confidence: 99%

“…By adopting SMILES representation, a popular paradigm of existing retrosynthesis methods is to formulate retrosynthesis prediction as a sequence-to-sequence translation problem. 73 This translation process is usually token-by-token and autoregressive, that is, based on the input product SMILES and the already decoded reactant SMILES, to obtain the next possible reactant token. Researchers first create a token dictionary with the molecules in the training set.…”

Section: Template-free Generationmentioning

confidence: 99%

See 1 more Smart Citation

Recent advances in deep learning for retrosynthesis

Zhong,

Song,

Feng

et al. 2023

WIREs Comput Mol Sci

View full text Add to dashboard Cite

Retrosynthesis is the cornerstone of organic chemistry, providing chemists in material and drug manufacturing access to poorly available and brand‐new molecules. Conventional rule‐based or expert‐based computer‐aided synthesis has obvious limitations, such as high labor costs and limited search space. In recent years, dramatic breakthroughs driven by deep learning have revolutionized retrosynthesis. Here we aim to present a comprehensive review of recent advances in AI‐based retrosynthesis. For single‐step and multi‐step retrosynthesis both, we first introduce their goal and provide a thorough taxonomy of existing methods. Afterwards, we analyze these methods in terms of their mechanism and performance, and introduce popular evaluation metrics for them, in which we also provide a detailed comparison among representative methods on several public datasets. In the next part, we introduce popular databases and established platforms for retrosynthesis. Finally, this review concludes with a discussion about promising research directions in this field.This article is categorized under: Data Science > Artificial Intelligence/Machine Learning Data Science > Computer Algorithms and Programming Data Science > Chemoinformatics

show abstract

Section: Single‐step Retrosynthesis Methodsmentioning

confidence: 99%

Section: Template-free Generationmentioning

confidence: 99%

Recent advances in deep learning for retrosynthesis

Zhong,

Song,

Feng

et al. 2023

WIREs Comput Mol Sci

View full text Add to dashboard Cite

show abstract

“…The conversion of a complex sentence to a simpler one, can be modelled as a translation task, making Neural Machine Translation (NMT) [20] a good fit for the problem. NMT with attention mechanisms, selectively focus on different parts of the input sentence dur-ing the translation process [12]. By doing so, the model can give appropriate emphasis to crucial elements, resulting in simplified sentences that preserve the original meaning.…”

Section: Ats Based On Neural Machine Translation (Nmt) With Attention...mentioning

confidence: 99%

“…The datasets comprise 200 summarized documents (100 for each court), addressing topics from different legal domains. The evaluated methods were: two unsupervised models, i.e., MUSS (English and Portuguese versions), and two supervised approaches, namely Transformers and NMT + Attention [10,11,12]. Readability metrics were employed in order to assess the quality of the produced, such as Flesch Reading Ease (FRE).…”

Section: Introductionmentioning

confidence: 99%

Automatic Simplification of Legal Texts in Portuguese Using Machine Learning

Alves,

Miranda,

Mello

et al. 2023

Frontiers in Artificial Intelligence and Applications

View full text Add to dashboard Cite

Texts produced by the Brazilian judiciary have a complex and technical vocabulary, with elaborate use of the Portuguese language and many legal terms difficult to be understood, generating a barrier in communication between the judiciary and the population. In this sense, the Automatic Text Simplification (ATS), activity of the Natural Language Processing (NLP) area, can be applied to improve the readability of these types of text using specialized algorithms, and promote scalability in simplifying them, in view of the great demand in the courts. In this context, this article presents an evaluation of four methods of state of the art in text simplification, evaluated according to readability metrics, to improve the quality of existing texts in the judicial summaries, dataset containing 100 summaries of the Federal Regional Court of the 5th Region (TRF5) and another 100 of the Federal Supreme Court (STF). The methods MUSS(EN), MUSS(PT), Transformers and NMT + Attention were tested, and the results of the simplifications exceeded the FRE readability index of the original texts, making them more readable.

show abstract

“…The purpose of validation data is to validate the model while in the training process. It will be simulated as a test set however in the training process [5].…”

Section: Data Preparationmentioning

confidence: 99%

Implementation of Neural Machine Translation for English-Sundanese Language using Long Short Term Memory (LSTM)

Ramadhan

Supriatman

2022

bits

View full text Add to dashboard Cite

In this modern era, machine translation has been used all over the world for solving humankind’s problems such as it deals with language. Machine translation is almost used by people who want to translate their native language into their foreign language. The international language being used is the English language. Machine translation is the task to translate a source language to another language. The input of it is a word or a sentence from the source language and it will be translated into another language. The input of it is a word or a sentence from the source language and it will be translated into another language. There are many purposes for using machine translation such as learning another language, communicating, finding a certain or better word to use, and even writing something in a book or another article. Several methods have been conducted to do the machine translation task such as the statistical approach and the neural approach In terms of Sundanese machine translation, there are several methods or several approaches that other researchers have conducted. However the study about Sundanese machine translation, none of the research conducted the English into Sundanese language. In this study using the encoder and decoder LSTM architecture achieve a good result regarding building a model for machine translation task. The performance of this model has achieved 0.99 accuracies in both training and testing as well as less than 0.1 loss value to both training and testing data. This model also achieves more than 0.8 average BLEU score for both training and testing data.

show abstract

Dynamic Mask Curriculum Learning for Non-Autoregressive Neural Machine Translation

Cited by 5 publications

References 9 publications

Recent advances in deep learning for retrosynthesis

Recent advances in deep learning for retrosynthesis

Automatic Simplification of Legal Texts in Portuguese Using Machine Learning

Implementation of Neural Machine Translation for English-Sundanese Language using Long Short Term Memory (LSTM)

Contact Info

Product

Resources

About