Meaning preservation in Example-based Machine Translation with structural semantics

Chua, Chong Chai; Lim, Theam Soon; Soon, Lay-Ki; Tang, Enya Kong; Ranaivo-Malançon, Bali

doi:10.1016/j.eswa.2017.02.021

Cited by 15 publications

(7 citation statements)

References 14 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Due to the poor encoder effect of the NMT model, Tan, Z. et al proposed the lattice-to-sequence attentional NMT model, which generalizes the CNN encoder to the lattice topology, and the proposed encoder reduces the negative impact of errors in the model operation, and outputs more expressive and flexible translated sentences [17]. Chua, C. C. et al introduced a structural, semantic approach to the EBMT model based on the introduction of a structural semantics approach to optimize EBMT from the meaning level, and the structural semantics ensures the consistency and completeness of sentences in the input process, thus improving the accuracy of translation [18]. Zhao, Y. et al in order to enhance the impact of semantic information in the visual feature capture, proposed the MNMT approach with semantic image regions, utilized the CNNs to improve the performance of the model, constructed the training dataset of 30k size, the proposed algorithm was tested in simulation experiments, and the experimental results show that the proposed algorithm can extract semantic information that matches the translated text according to the visual features and improve the performance of translation [19].…”

Section: Literature Reviewmentioning

confidence: 99%

Research on English Translation of Intangible Cultural Heritage in the Age of AIGC

Sun

2023

Applied Mathematics and Nonlinear Sciences

View full text Add to dashboard Cite

Cultural dissemination and display methods with the progress of science and technology requirements continue to improve, especially in the AIGC era. The traditional cultural dissemination methods are no longer applicable, and “non-legacy digitization” needs to become more and more urgent. This paper analyzes the neural machine translation method and constructs a back-translation model by synthesizing a corpus and generating parameters. BLEU and other evaluation indexes are used to optimize the factors that affect the computation of synthetic data. An enhanced synthetic corpus is created using the kNN algorithm to construct a monolingual translation memory. Using the semantic information-sharing strategy, generate the parameters of the embedding layer of the non-legacy translation model while introducing the encoding layer to complete the overall construction of the non-legacy translation model. Comparative experiments and empirical analyses are set up to study the heterogeneity of the quality and dissemination effect of English translation of NRLs, and the experiments show that in the first set of translation tasks, the BLEU scores of the model proposed in this paper are 1 and 1.4 higher than those of the wait-k model when the value of k is 5 and 7, and the translation quality of the model proposed in this paper is better. The values of primary and secondary term coefficients of the English translation of non-legacy are 14.974 and -3.071, respectively, in the case of not establishing samples, showing an inverted U-shaped linear relationship.

show abstract

Section: Literature Reviewmentioning

confidence: 99%

Research on English Translation of Intangible Cultural Heritage in the Age of AIGC

Sun

2023

Applied Mathematics and Nonlinear Sciences

View full text Add to dashboard Cite

show abstract

“…Neural machine translation is the mainstream [7], but it can only learn from bilingual parallel corpus, ignoring linguistic knowledge, which leads to the poor quality of translation [8]. The natural language contains a lot of fuzziness, near meaning, and polysemy [9]. Therefore, semantic recognition is of great N. Dang value to NMT.…”

Section: Neural Machine Translation Combined With Semantic Roles 21 Semantic Role Labelingmentioning

confidence: 99%

English Semantic Recognition Based on Intelligent Algorithm

Deng¹

2021

IJCAI

View full text Add to dashboard Cite

“…According Wulandari and Harida (2021) state that by writing English sentences according to the grammatical structure, the meaning of it will be accurate, easily understood and acceptable. The findings Tse (2014) also showed that the English writing skill of the secondary male students in schools needs more reinforcement and development (Chua, Lim, Soon, Tang, & Ranaivo-Malançon, 2017).…”

Section: Introductionmentioning

confidence: 95%

Grammatical Errors Made By Students’ on the Technique of Making Idiomatic Translation in the Politic Texts

Widya¹

2021

View full text Add to dashboard Cite

English is an important role in education or technology since it functions as one of the international languages. The aim is to describe a type of grammatical error and find out the causes of errors in translating vocative text based on the idiomatic translation. The research was conducted at SMP Swasta Al-Maksum. The research design used descriptive quantitative. The population of this research was students consist of 41 students. The technique sampling was purposive sampling, sample is 41 students. The test was teacher-made. The data were acquired by administrating an objective test was a text which consisted of 10 items to test their knowledge in translating the text based on idiomatic translation, each correct translation has scores one and the incorrect translation was scored zero. The findings showed that 71% of samples were able and 29% of samples were unable in translating the text based on idiomatic translation. It means that students were able to translate the text-based on idiomatic translation.

show abstract

Meaning preservation in Example-based Machine Translation with structural semantics

Cited by 15 publications

References 14 publications

Research on English Translation of Intangible Cultural Heritage in the Age of AIGC

Research on English Translation of Intangible Cultural Heritage in the Age of AIGC

English Semantic Recognition Based on Intelligent Algorithm

Grammatical Errors Made By Students’ on the Technique of Making Idiomatic Translation in the Politic Texts

Contact Info

Product

Resources

About