Research on Machine Translation of Deep Neural Network Learning Model Based on Ontology

Tian, Yun; Khanna, Shaweta; Pljonkin, Anton

doi:10.31449/inf.v45i5.3559

Cited by 6 publications

(4 citation statements)

References 40 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…We carry out two filtering steps to remove low-quality parallel sentence pairs: (i) align parallel sentence pairs and (ii) data filtering. In the first step, the temporary dataset is aligned by three tools: Vecalign 5 , Bleualign 6 , and Hunalign 7 . Vecalign utilizes word embeddings to align sentences based on semantic similarity.…”

Section: Data Augmentation Methods Via English Pivot Languagementioning

confidence: 99%

See 1 more Smart Citation

Low-Resource Neural Machine Translation Improvement Using Data Augmentation Strategies

Quoc,

Thanh,

Van

2023

IJCAI

View full text Add to dashboard Cite

The development of neural models has greatly improved the performance of machine translation, but these methods require large-scale parallel data, which can be difficult to obtain for low-resource language pairs. To address this issue, this research employs a pre-trained multilingual model and fine-tunes it by using a small bilingual dataset. Additionally, two data-augmentation strategies are proposed to generate new training data: (i) back-translation with the dataset from the source language; (ii) data augmentation via the English pivot language. The proposed approach is applied to the Khmer-Vietnamese machine translation. Experimental results show that our proposed approach outperforms the Google Translator model by 5.3% in terms of BLEU score on a test set of 2,000 Khmer-Vietnamese sentence pairs. Povzetek: Raziskava uporablja predhodno usposobljen večjezični model in povečanje podatkov. Rezultati presegajo Google Translator za 5,3%.

show abstract

Section: Data Augmentation Methods Via English Pivot Languagementioning

confidence: 99%

“…Machine translation (MT) is the task of automatically translating text from one language to another. There are three common approaches to MT: rule-based approach [1], statistical-based approach [2,3], and neural-based one [4,5,6]. The rule-based approach depends on translation rules and dictionaries created by human experts.…”

Section: Introductionmentioning

confidence: 99%

Low-Resource Neural Machine Translation Improvement Using Data Augmentation Strategies

Quoc,

Thanh,

Van

2023

IJCAI

View full text Add to dashboard Cite

show abstract

“…This paper used BLEU [17] to automatically evaluate the quality of machine translation. BLEU index was based on N-ary grammar.…”

Section: Evaluation Indexmentioning

confidence: 99%

English Semantic Recognition Based on Intelligent Algorithm

Deng¹

2021

IJCAI

View full text Add to dashboard Cite

“…In addition, Wang et al 47 proposed a high-quality parallel Wave Net based on CNN for speech synthesis, and Facebook presented the convolution neural network with attention mechanism for machine translation in 2017. 48 More recently, a specialized CNN architecture known as temporal convolutional networks (TCN) has acquired popularity due to its suitability in sequence modeling tasks. The TCN networks operate causal dilated convolution to enable an exponentially sizeable receptive field and reduce information loss.…”

mentioning

confidence: 99%

State of Charge Estimation for Lithium-Ion Batteries Based on TCN-LSTM Neural Networks

Cheng

et al. 2022

J. Electrochem. Soc.

View full text Add to dashboard Cite

Accurately estimating the state of charge (SOC) of lithium-ion batteries is critical for developing more reliable and efficient electric vehicles. However, the commonly used models cannot simultaneously extract effective spatial and temporal features from the original data, leading to an inefficient SOC estimation. This paper proposes a novel neural network method for accurate and robust battery SOC estimation, which incorporates the temporal convolutional network (TCN) and the long short-term memory (LSTM), namely TCN-LSTM model. Specifically, the TCN is employed to extract more advanced spatial features among multivariate variables, and the LSTM captures long-term dependencies from time-series data and maps battery temporal information into current SOC and historical inputs. The proposed model performs well in various estimation conditions. The average value of mean absolute error, root mean square error, and maximum error of SOC estimation achieve 0.48%, 0.60%, and 2.3% at multiple temperature conditions, respectively, and reach 0.70%, 0.81%, and 2.7% for a different battery, respectively. In addition, the proposed method has better accuracy than the LSTM or TCN used independently and the CNN-LSTM network. The computational burden with varying length of input is also investigated. In summary, experiment results show that the proposed method has excellent generalization and robustness.

show abstract

Research on Machine Translation of Deep Neural Network Learning Model Based on Ontology

Cited by 6 publications

References 40 publications

Low-Resource Neural Machine Translation Improvement Using Data Augmentation Strategies

Low-Resource Neural Machine Translation Improvement Using Data Augmentation Strategies

English Semantic Recognition Based on Intelligent Algorithm

State of Charge Estimation for Lithium-Ion Batteries Based on TCN-LSTM Neural Networks

Contact Info

Product

Resources

About