Neural Machine Translation with Attention Based on a New Syntactic Branch Distance

Peng, Ru Shu; Chen, Zhitao; Hao, Tianyong; Fang, Yi

doi:10.1007/978-981-15-1721-1_5

Cited by 5 publications

(2 citation statements)

References 15 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The disadvantage of this model is that, compared with our method, the prior knowledge will be diluted when faced with long sentences. Peng et al [26] established the syntactic dependency matrix of each word based on the syntactic dependency tree and integrated quantitative syntactic knowledge into the translation model to guide translation, effectively learning syntactic details and eliminating the dispersion of attention scores.…”

Section: Related Workmentioning

confidence: 99%

Machine Translation of Electrical Terminology Constraints

Wang,

Chen,

Zhang

2023

Information

View full text Add to dashboard Cite

In practical applications, the accuracy of domain terminology translation is an important criterion for the performance evaluation of domain machine translation models. Aiming at the problem of phrase mismatch and improper translation caused by word-by-word translation of English terminology phrases, this paper constructs a dictionary of terminology phrases in the field of electrical engineering and proposes three schemes to integrate the dictionary knowledge into the translation model. Scheme 1 replaces the terminology phrases of the source language. Scheme 2 uses the residual connection at the encoder end after the terminology phrase is replaced. Scheme 3 uses a segmentation method of combining character segmentation and terminology segmentation for the target language and uses an additional loss module in the training process. The results show that all three schemes are superior to the baseline model in two aspects: BLEU value and correct translation rate of terminology words. In the test set, the highest accuracy of terminology words was 48.3% higher than that of the baseline model. The BLEU value is up to 3.6 higher than the baseline model. The phenomenon is also analyzed and discussed in this paper.

show abstract

Section: Related Workmentioning

confidence: 99%

Machine Translation of Electrical Terminology Constraints

Wang,

Chen,

Zhang

2023

Information

View full text Add to dashboard Cite

show abstract

“…Dependency distance In line with previous work [5,17,18,25], the dependency tree is extracted from the sentence by an external syntax parser, which is employed to derive the word-level dependency distance. The dependency distance is defined as the length of the path traversed from a word to another word on the tree, and the distance between two connected words is assigned as 1.…”

Section: Approachmentioning

confidence: 99%

Deps-SAN: Neural Machine Translation with Dependency-Scaled Self-Attention Network

Peng¹,

Lin²,

Fang³

et al. 2021

Preprint

Self Cite

View full text Add to dashboard Cite

The neural machine translation model assumes that syntax knowledge can be learned from the bilingual corpus via an attention network automatically. However, the attention network trained in weak supervision actually cannot capture the deep structure of the sentence. Naturally, we expect to introduce external syntax knowledge to guide the learning of the attention network. Thus, we propose a novel, parameterfree, dependency-scaled self-attention network, which integrates explicit syntactic dependencies into the attention network to dispel the dispersion of attention distribution. Finally, two knowledge sparse techniques are proposed to prevent the model from overfitting noisy syntactic dependencies. Experiments and extensive analyses on the IWSLT14 German-to-English and WMT16 German-to-English translation tasks validate the effectiveness of our approach. 1

show abstract