scholarly journals Model and Verification of Medical English Machine Translation Based on Optimized Generalized Likelihood Ratio Algorithm

2021 ◽  
Vol 2021 ◽  
pp. 1-7
Author(s):  
Peng Yu ◽  
Youyu Zhu
Keyword(s):  
Machine Translation ◽  
Likelihood Ratio ◽  
Mapping Function ◽  
Medical Field ◽  
Generalized Likelihood Ratio ◽  
Translation Model ◽  
Part Of Speech ◽  
Medical English ◽  
New Perspective ◽  
Speed Accuracy

Phrase identification plays an important role in medical English machine translation. However, the phrases in medical English are complicated in internal structure and semantic relationship, which hinders the identification of machine translation and thus affects the accuracy of translation results. With the aim of breaking through the bottleneck of machine translation in medical field, this paper designed a machine translation model based on the optimized generalized likelihood ratio (GLR) algorithm. Specifically, the model in question established a medical phrase corpus of 250,000 English and 280,000 Chinese words, applied the symbol mapping function to the identification of the phrase’s part of speech, and employed the syntactic function of the multioutput analysis table structure to correct the structural ambiguity in the identification of the part of speech, eventually obtaining the final identification result. According to the comprehensive verification, the translation model employing the optimized GLR algorithm was seen to improve the speed, accuracy, and update performance of machine translation and was seen to be more suitable for machine translation in medical field, therefore providing a new perspective for the employment of medical machine translation.

scholarly journals Source-Word Decomposition for Neural Machine Translation

2020 ◽  
Vol 2020 ◽  
pp. 1-10
Author(s):  
Thien Nguyen ◽  
Hoai Le ◽  
Van-Huy Pham
Keyword(s):  
Machine Translation ◽  
Linguistic Features ◽  
Specialized Knowledge ◽  
Neural Machine Translation ◽  
Translation Model ◽  
Part Of Speech ◽  
Effective System ◽  
Feature Based ◽  
Transformer Model ◽  
Translation Systems

End-to-end neural machine translation does not require us to have specialized knowledge of investigated language pairs in building an effective system. On the other hand, feature engineering proves to be vital in other artificial intelligence fields, such as speech recognition and computer vision. Inspired by works in those fields, in this paper, we propose a novel feature-based translation model by modifying the state-of-the-art transformer model. Specifically, the encoder of the modified transformer model takes input combinations of linguistic features comprising of lemma, dependency label, part-of-speech tag, and morphological label instead of source words. The experiment results for the Russian-Vietnamese language pair show that the proposed feature-based transformer model improves over the strongest baseline transformer translation model by impressive 4.83 BLEU. In addition, experiment analysis reveals that human judgment on the translation results strongly confirms machine judgment. Our model could be useful in building translation systems translating from a highly inflectional language into a noninflectional language.

Identification and Transformation of Terminal Morphemes in Medical English

1969 ◽  
Vol 8 (02) ◽  
pp. 84-90 ◽  
Author(s):  
A. W. Pratt ◽  
M. Pacak
Keyword(s):  
Word Form ◽  
Subsequent Transformation ◽  
Part Of Speech ◽  
Morphological Segmentation ◽  
Medical English ◽  
Nominal Form ◽  
Admissible Path ◽  
Near Future ◽  
The Given ◽  
Admissible Sequences

The system for the identification and subsequent transformation of terminal morphemes in medical English is a part of the information system for processing pathology data which was developed at the National Institutes of Health.The recognition and transformation of terminal morphemes is restricted to classes of adjectivals including the -ING and -ED forms, nominals and homographic adjective/noun forms.The adjective-to-noun and noun-to-noun transforms consist basically of a set of substitutions of adjectival and certain nominal suffixes by a set of suffixes which indicate the corresponding nominal form(s).The adjectival/nominal suffix has a polymorphosyntactic transformational function if it has the property of being transformed into more than one nominalizing suffix (e.g., the adjectival suffix -IC can be substituted by a set of nominalizing suffixes -Ø, -A, -E, -Y, -IS, -IA, -ICS): the adjectival suffix has a monomorphosyntactic transformational property if there is only one admissible transform (e.g., -CIC → -X).The morphological segmentation and the subsequent transformations are based on the following principles:a. The word form is segmented according to the principle of »double consonant cut,« i.e., terminal characters following the last set of double consonants are analyzed and treated as a potential suffix. For practical purposes only such terminal suffixes of a maximum length of four have been analyzed.b. The principle that the largest segment of a word form common to both adjective and noun or to both noun stems is retained as a word base for transformational operations, and the non-identical segment is considered to be a »suffix.«The backward right-to-left character search is initiated by the identification of the terminal grapheme of the given word form and is extended to certain admissible sequences of immediately preceding graphemes.The nodes which represent fixed sequences of graphemes are labeled according to their recognition and/or transformation properties.The tree nodes are divided into two groups:a. productive or activatedb. non-productive or non-activatedThe productive (activated) nodes are sequences of sets of graphemes which possess certain properties, such as the indication about part-of-speech class membership, the transformation properties, or both. The non-productive (non-activated) nodes have the function of connectors, i.e., they specify the admissible path to the productive nodes.The computer program for the identification and transformation of the terminal morphemes is open-ended and is already operational. It will be extended to other sub-fields of medicine in the near future.

A Topic-Triggered Translation Model for Statistical Machine Translation

2017 ◽  
Vol 26 (1) ◽  
pp. 65-72 ◽  
Author(s):  
Jinsong Su ◽  
Zhihao Wang ◽  
Qingqiang Wu ◽  
Junfeng Yao ◽  
Fei Long ◽  
...  
Keyword(s):  
Machine Translation ◽  
Statistical Machine Translation ◽  
Translation Model

Fault Detection in Linear Discrete Dynamic Systems by a Pattern Recognition of a Generalized-Likelihood-Ratio

1990 ◽  
Vol 112 (2) ◽  
pp. 276-282 ◽  
Author(s):  
S. Tanaka ◽  
P. C. Mu¨ller
Keyword(s):  
Pattern Recognition ◽  
Likelihood Ratio ◽  
Dynamic Systems ◽  
Abrupt Change ◽  
Detection Method ◽  
Discrete Dynamical System ◽  
Generalized Likelihood Ratio ◽  
Robust Detection ◽  
Chi Squared ◽  
Discrete Dynamic Systems

The detection of an abrupt change in the parameters of a linear discrete dynamical system is considered in the framework of the easily implemented generalized-likelihood-ratio (GLR) method. This paper proposes a robust detection method based on a pattern recognition of the maximum GLR provided by the conventional step-hypothesized GLR method. A numerical example demonstrates that the proposed method is highly superior to the conventional step-hypothesized GLR method and to the Chi-squared test in both detection rate and detection speed.

Sign in / Sign up

Export Citation Format

Share Document