2021
DOI: 10.12928/telkomnika.v19i2.16134
|View full text |Cite
|
Sign up to set email alerts
|

Translating cuneiform symbols using artificial neural network

Abstract: Cuneiform language is an old language that was invented by the people of Sumerian nation. It is an essential language for many archeologists. Especially who are interested in studying and investigating the old nations of Iraq. Dealing with this type of language usually requires specialist to translate its symbols, which are basically forms of nail shapes. This study presents a new approach to translate the cuneiform writing by employing artificial neural network (ANN) technique. Effectively, multi-layer percep… Show more

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
2
1
1
1

Citation Types

0
8
0
1

Year Published

2022
2022
2024
2024

Publication Types

Select...
4
3
2

Relationship

0
9

Authors

Journals

citations
Cited by 13 publications
(9 citation statements)
references
References 20 publications
0
8
0
1
Order By: Relevance
“…Недоліками нейронних мереж є [12][13][14]:  труднощі визначення структури мережі, оскільки відсутні методи розрахунку кількості шарів та нейронів у кожному шарі для конкретних додатків;  складність формування представницької вибірки;…”
Section: метод динамічного управління буфером запасів на основі м'яки...unclassified
“…Недоліками нейронних мереж є [12][13][14]:  труднощі визначення структури мережі, оскільки відсутні методи розрахунку кількості шарів та нейронів у кожному шарі для конкретних додатків;  складність формування представницької вибірки;…”
Section: метод динамічного управління буфером запасів на основі м'яки...unclassified
“…where X is the data distribution and Z(x) is the loss function over the sample x. Substituting equation ( 6) into equation (7) e proposed method further enhances the corpus based on the reverse translation by using word substitution methods to enhance the training data containing low-frequency words through language model substitution for lowfrequency words, which constructs a more diverse pseudoparallel corpus and makes the pseudoparallel corpus covers a more realistic data distribution, thus improving the translation performance in resource-rich scenarios. In lowresource scenarios, the word substitution method additionally adds a linguistic error correction module to eliminate errors such as syntactic semantics generated by substitution.…”
Section: Deep Learning Combined With Prior Knowledge English Translat...mentioning
confidence: 99%
“…In this paper, we investigate the implicit learning capability of the neural machine translation model to stimulate its potential and enhance its performance accordingly in several translation subdomains [6]. Specifically, we first exploit its implicitly acquired multiheaded attention mechanism to achieve improvement on the diversity translation task, then improve the quality of low-resource translation by masking the attention heads within the model, and finally exploit its own potential long-range text modeling capability to achieve a breakthrough on the document translation task [7].…”
Section: Introductionmentioning
confidence: 99%
“…Adopting the paradigm of handwritten text recognition, preliminary results published in the project's website suggest an 83% success 5 and, furthermore, their transliteration to English letters [35].…”
Section: Re Shaping Interpretation and Restoration With Aimentioning
confidence: 99%