Pub Date : 2023-02-03DOI: 10.1109/ECEI57668.2023.10105346
Danlu Liao
This paper explores how to use artificial intelligence to innovate the teaching mode of English Listening Course, and how to apply artificial intelligence to teaching sessions, that is listening-driven, listening-facilitating and listening evaluation. To take Chongqing Vocational Institute of Tourism as a research project, from listening achievements, it analyzes the effect of teaching mode in terms of listening ability and listening motivation. The results show that the teaching mode of English listening course based on artificial intelligence is useful to improve students' enthusiasm and listening ability in English listening course.
{"title":"Reform of English Listening Course Teaching Mode in Vocational Colleges Based on Artificial Intelligence","authors":"Danlu Liao","doi":"10.1109/ECEI57668.2023.10105346","DOIUrl":"https://doi.org/10.1109/ECEI57668.2023.10105346","url":null,"abstract":"This paper explores how to use artificial intelligence to innovate the teaching mode of English Listening Course, and how to apply artificial intelligence to teaching sessions, that is listening-driven, listening-facilitating and listening evaluation. To take Chongqing Vocational Institute of Tourism as a research project, from listening achievements, it analyzes the effect of teaching mode in terms of listening ability and listening motivation. The results show that the teaching mode of English listening course based on artificial intelligence is useful to improve students' enthusiasm and listening ability in English listening course.","PeriodicalId":176611,"journal":{"name":"2023 IEEE 6th Eurasian Conference on Educational Innovation (ECEI)","volume":"30 1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-02-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123589594","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2023-02-03DOI: 10.1109/ECEI57668.2023.10105335
Lin Chen
Based on the form language structure, the chain grammar formal structure framework is used to realize the form of sentences and reconstruct the management system of the chain grammar sentence dictionary. It aims to establish an excellent error detection system in English sentences for Chinese learners. The test data shows that the recall rate of wrong sentence detection increases by 4.5% compared with the original dictionary, and the accuracy rate also increases by 15.7%. The learners' accurate parsing of sentence patterns is improved by 12.2%. The research results show that the linguistic basic verb pattern syntax and structural model chain syntax adopted in this study can be applied to the research and construction of the error detection system of the written English verb type for Chinese learners.
{"title":"Research on Verb Expression Error Detection Algorithm in College English Writing Based on Fonnal Model","authors":"Lin Chen","doi":"10.1109/ECEI57668.2023.10105335","DOIUrl":"https://doi.org/10.1109/ECEI57668.2023.10105335","url":null,"abstract":"Based on the form language structure, the chain grammar formal structure framework is used to realize the form of sentences and reconstruct the management system of the chain grammar sentence dictionary. It aims to establish an excellent error detection system in English sentences for Chinese learners. The test data shows that the recall rate of wrong sentence detection increases by 4.5% compared with the original dictionary, and the accuracy rate also increases by 15.7%. The learners' accurate parsing of sentence patterns is improved by 12.2%. The research results show that the linguistic basic verb pattern syntax and structural model chain syntax adopted in this study can be applied to the research and construction of the error detection system of the written English verb type for Chinese learners.","PeriodicalId":176611,"journal":{"name":"2023 IEEE 6th Eurasian Conference on Educational Innovation (ECEI)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-02-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129753088","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2023-02-03DOI: 10.1109/ECEI57668.2023.10105371
Ping Yang
To overcome the shortcomings of the quality evaluation of translation in the low-resource corpus, a cross-sentence pre-training model is proposed for English-Chinese translation. First of all, we provide an embedding technology to automatically adjust the position of words by using attention thought for reference. Then, the cross-layer language pre-training model is introduced into the reading efficiency test to solve the information sparsity caused by the low resource conditions of English. By regressing the sentence vector, the mechanical evaluation of translation quality is completed. The test results show that this model significantly improves the effectiveness of the evaluation of the quality of English-Chinese translation. Compared with the CEstmodel, the Pearson correlation coefficient of this algorithm has increased by 0.35, and the Spielbman correlation coefficient has increased by 0.15.
{"title":"Research on English-Chinese Translation Quality Evaluation Agorithm Based on Cross-Language Pre-Training Mode","authors":"Ping Yang","doi":"10.1109/ECEI57668.2023.10105371","DOIUrl":"https://doi.org/10.1109/ECEI57668.2023.10105371","url":null,"abstract":"To overcome the shortcomings of the quality evaluation of translation in the low-resource corpus, a cross-sentence pre-training model is proposed for English-Chinese translation. First of all, we provide an embedding technology to automatically adjust the position of words by using attention thought for reference. Then, the cross-layer language pre-training model is introduced into the reading efficiency test to solve the information sparsity caused by the low resource conditions of English. By regressing the sentence vector, the mechanical evaluation of translation quality is completed. The test results show that this model significantly improves the effectiveness of the evaluation of the quality of English-Chinese translation. Compared with the CEstmodel, the Pearson correlation coefficient of this algorithm has increased by 0.35, and the Spielbman correlation coefficient has increased by 0.15.","PeriodicalId":176611,"journal":{"name":"2023 IEEE 6th Eurasian Conference on Educational Innovation (ECEI)","volume":"30 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-02-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128359087","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
In this study, the human visual field test technology is established by using an optoelectrical system consisting of a translucent ellipsoid, an area light source, and a landscape scene with an indicator. During the test, the subjects stared at the indicator directly in front of them with one eye and kept their eyeballs still, scanning the light strip with peripheral vision and using the mouse button plus the playback program to record the start and end positions of the scanning light strip in the landscape scene. This method is tested subjectively, and the subject needs to respond during the test. Therefore, before the test, the subject needs to understand the test process and be trained in advance to improve the exam accuracy. In the experiment, fifteen subjects with normal vision and no eye disease were selected. Their visual fields were confirmed normal after a preliminary assessment. The test results showed that the subjects' eyes were within the normal visual field, indicating that this method was feasible. In this research, a digital optical platform for the near visual field is proposed to establish an optoelectric visual field measurement technology. The proposed method is characterized by small size, rapid operation, and easy portability. With the digital LCD and visual imaging technology, both dynamic and static visual fields can be tested. The test data on the eyes' upper, lower, nasal, and temporal sides were consistent with the normal visual field. This shows that this method is feasible and worthy of promotion in the optometry industry.
{"title":"Visual Field Examination Technology Based on Semi-transparent Elliptical Mirror","authors":"Chao-Kai Chang, Chun-Yu Chiang, Feng-Ming Yeh, Chi-Hung Lee, C. Tien, Der-Chin Chen","doi":"10.1109/ECEI57668.2023.10105389","DOIUrl":"https://doi.org/10.1109/ECEI57668.2023.10105389","url":null,"abstract":"In this study, the human visual field test technology is established by using an optoelectrical system consisting of a translucent ellipsoid, an area light source, and a landscape scene with an indicator. During the test, the subjects stared at the indicator directly in front of them with one eye and kept their eyeballs still, scanning the light strip with peripheral vision and using the mouse button plus the playback program to record the start and end positions of the scanning light strip in the landscape scene. This method is tested subjectively, and the subject needs to respond during the test. Therefore, before the test, the subject needs to understand the test process and be trained in advance to improve the exam accuracy. In the experiment, fifteen subjects with normal vision and no eye disease were selected. Their visual fields were confirmed normal after a preliminary assessment. The test results showed that the subjects' eyes were within the normal visual field, indicating that this method was feasible. In this research, a digital optical platform for the near visual field is proposed to establish an optoelectric visual field measurement technology. The proposed method is characterized by small size, rapid operation, and easy portability. With the digital LCD and visual imaging technology, both dynamic and static visual fields can be tested. The test data on the eyes' upper, lower, nasal, and temporal sides were consistent with the normal visual field. This shows that this method is feasible and worthy of promotion in the optometry industry.","PeriodicalId":176611,"journal":{"name":"2023 IEEE 6th Eurasian Conference on Educational Innovation (ECEI)","volume":"20 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-02-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129555014","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2023-02-03DOI: 10.1109/ECEI57668.2023.10105386
Chao Liu, Kene Li, Weiming Yuan, Liuying Li
Aiming to solve the problem of the redundant manipulator, it is necessary to complete the trajectory-tracking with a fixed orientation in tasks. Therefore, we propose a manipulator end orientation control scheme based on a gradient projection algorithm. Firstly, according to the property of the redundant manipulator that realizes self-motion, the orientation control problem is transformed into the self-motion problem of the manipulator. The angle between the end-effector of the manipulator and each coordinate axis of the base coordinate system is optimized as the objective. Secondly, according to the expected orientation required by the task, the corresponding objective optimization function is designed and its gradient vector is calculated. Then, the expected orientation is taken as the target criteria, and a reasonable joint velocity adjustment function is designed. Finally, the scheme uses MATLAB simulation software to simulate the four-link manipulator and the six-degree-of-freedom manipulator, respectively. The experimental results show that the scheme is effective and feasible.
{"title":"Redundant Manipulator Orientation Control Scheme Based on Gradient Projection Algorithm","authors":"Chao Liu, Kene Li, Weiming Yuan, Liuying Li","doi":"10.1109/ECEI57668.2023.10105386","DOIUrl":"https://doi.org/10.1109/ECEI57668.2023.10105386","url":null,"abstract":"Aiming to solve the problem of the redundant manipulator, it is necessary to complete the trajectory-tracking with a fixed orientation in tasks. Therefore, we propose a manipulator end orientation control scheme based on a gradient projection algorithm. Firstly, according to the property of the redundant manipulator that realizes self-motion, the orientation control problem is transformed into the self-motion problem of the manipulator. The angle between the end-effector of the manipulator and each coordinate axis of the base coordinate system is optimized as the objective. Secondly, according to the expected orientation required by the task, the corresponding objective optimization function is designed and its gradient vector is calculated. Then, the expected orientation is taken as the target criteria, and a reasonable joint velocity adjustment function is designed. Finally, the scheme uses MATLAB simulation software to simulate the four-link manipulator and the six-degree-of-freedom manipulator, respectively. The experimental results show that the scheme is effective and feasible.","PeriodicalId":176611,"journal":{"name":"2023 IEEE 6th Eurasian Conference on Educational Innovation (ECEI)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-02-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125519137","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2023-02-03DOI: 10.1109/ECEI57668.2023.10105263
Xiaohui Cui
In order to enhance the risk control of private loans, a risk assessment technology of network loan projects based on multi-feature information and a risk-sensitive decision tree is provided. In this method, the credit conditions of the lender in the customer information submitted in the online loan system is first established and then combined with the lender's historical loan records, personal characteristics, and enterprise characteristics. The analysis method with the maximization under the ROC curve and the minimum mutual information are used to select the information set most relevant to the project risk analysis and with the minimum redundancy. Finally, the risk evaluation of loan enterprises is carried out by using the perfect risk-sensitive decision tree method. The test result shows that this method has better performance in private loan risk assessment compared with the existing methods.
{"title":"Research on Risk Evaluation Algorithm of Private Lending Based on ROC Decision Tree","authors":"Xiaohui Cui","doi":"10.1109/ECEI57668.2023.10105263","DOIUrl":"https://doi.org/10.1109/ECEI57668.2023.10105263","url":null,"abstract":"In order to enhance the risk control of private loans, a risk assessment technology of network loan projects based on multi-feature information and a risk-sensitive decision tree is provided. In this method, the credit conditions of the lender in the customer information submitted in the online loan system is first established and then combined with the lender's historical loan records, personal characteristics, and enterprise characteristics. The analysis method with the maximization under the ROC curve and the minimum mutual information are used to select the information set most relevant to the project risk analysis and with the minimum redundancy. Finally, the risk evaluation of loan enterprises is carried out by using the perfect risk-sensitive decision tree method. The test result shows that this method has better performance in private loan risk assessment compared with the existing methods.","PeriodicalId":176611,"journal":{"name":"2023 IEEE 6th Eurasian Conference on Educational Innovation (ECEI)","volume":"15 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-02-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126777632","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2023-02-03DOI: 10.1109/ECEI57668.2023.10105413
P. Panjaburee, Gwo-jen Hwang, Ungsinun Intarakamhang, N. Srisawasdi, Sasipim Poompimol, Preeyada Tapingkae
Most schools often require youth students to receive essential skills in the 21st century as a basic requirement in daily life. Digital citizenship behaviors or digital literacy are relevant to each other and common as being essential in primary and secondary education. Although several curricula promote digital citizenship behaviors, students are still willing to study in a more enjoyable and proper learning environment with their preferences and current action. Game-based learning environment motivates students to learn with fantastic features, rewards, and active activities to enjoy learning. Scholars suggest that the story-telling or gaming scenario can enhance a well-design game-based learning environment if the students receive the opportunity to make and revise their decisions. The theory of making decisions through storyline telling is an application of the decision tree. However, the study efficiency of the decision tree in gaming scenarios needs to be verified. Thus, this study adopted a decision tree-based online gaming approach for assisting and adapting students in behaving good behaviors using digital tools. The results of pattern analysis for investigating the online gaming behaviors of the students indicate that those who followed the recommendations provided by the gaming approach had more positive digital citizenship behaviors, such as acting upstanders more often than bystander behavior.
{"title":"Effects of Decision Tree-based Online Gaming Framework on Students' Digital Citizenship Behaviors and Patterns","authors":"P. Panjaburee, Gwo-jen Hwang, Ungsinun Intarakamhang, N. Srisawasdi, Sasipim Poompimol, Preeyada Tapingkae","doi":"10.1109/ECEI57668.2023.10105413","DOIUrl":"https://doi.org/10.1109/ECEI57668.2023.10105413","url":null,"abstract":"Most schools often require youth students to receive essential skills in the 21st century as a basic requirement in daily life. Digital citizenship behaviors or digital literacy are relevant to each other and common as being essential in primary and secondary education. Although several curricula promote digital citizenship behaviors, students are still willing to study in a more enjoyable and proper learning environment with their preferences and current action. Game-based learning environment motivates students to learn with fantastic features, rewards, and active activities to enjoy learning. Scholars suggest that the story-telling or gaming scenario can enhance a well-design game-based learning environment if the students receive the opportunity to make and revise their decisions. The theory of making decisions through storyline telling is an application of the decision tree. However, the study efficiency of the decision tree in gaming scenarios needs to be verified. Thus, this study adopted a decision tree-based online gaming approach for assisting and adapting students in behaving good behaviors using digital tools. The results of pattern analysis for investigating the online gaming behaviors of the students indicate that those who followed the recommendations provided by the gaming approach had more positive digital citizenship behaviors, such as acting upstanders more often than bystander behavior.","PeriodicalId":176611,"journal":{"name":"2023 IEEE 6th Eurasian Conference on Educational Innovation (ECEI)","volume":"11 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-02-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122229779","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2023-02-03DOI: 10.1109/ECEI57668.2023.10105401
Lvting Li
In order to solve the difficulty in teaching chime bells, a virtual simulation was developed according to the requirements of course construction. This research reconstructed a set of virtual chimes and performances that were completely consistent with the shape, scale, and proportion of the chimes. Students conducted experiments such as tone recognition, solo, ensemble, solo, and ensemble creation through the way that “the left-hand keyboard controls the performance strength, and the right-hand mouse controls the performance speed and pitch”. The teaching effect showed that the experiment broadened the depth of traditional music teaching, improved students' learning enthusiasm and initiative, extended students' learning time and learning space, and cultivated students' collaborative interaction ability and cooperative innovation spirit.
{"title":"Design and Application of Virtual Simulation Teaching Function of Chime Performance and Creation Based on VR","authors":"Lvting Li","doi":"10.1109/ECEI57668.2023.10105401","DOIUrl":"https://doi.org/10.1109/ECEI57668.2023.10105401","url":null,"abstract":"In order to solve the difficulty in teaching chime bells, a virtual simulation was developed according to the requirements of course construction. This research reconstructed a set of virtual chimes and performances that were completely consistent with the shape, scale, and proportion of the chimes. Students conducted experiments such as tone recognition, solo, ensemble, solo, and ensemble creation through the way that “the left-hand keyboard controls the performance strength, and the right-hand mouse controls the performance speed and pitch”. The teaching effect showed that the experiment broadened the depth of traditional music teaching, improved students' learning enthusiasm and initiative, extended students' learning time and learning space, and cultivated students' collaborative interaction ability and cooperative innovation spirit.","PeriodicalId":176611,"journal":{"name":"2023 IEEE 6th Eurasian Conference on Educational Innovation (ECEI)","volume":"73 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-02-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116063822","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2023-02-03DOI: 10.1109/ECEI57668.2023.10105399
I. Lin
Many countries are using big data to understand users' behavior to improve policies or promote new policies to provide better services to public users. Using a medium-sized city in Taiwan as a case study, the application of big data is reviewed by using Python to interface with Google Maps API for traffic information. Through the GIS interface, the government can understand the traffic service (or policies) for the public.
{"title":"Combining Big Data and GIS Interface to Achieve Effectiveness of E-government","authors":"I. Lin","doi":"10.1109/ECEI57668.2023.10105399","DOIUrl":"https://doi.org/10.1109/ECEI57668.2023.10105399","url":null,"abstract":"Many countries are using big data to understand users' behavior to improve policies or promote new policies to provide better services to public users. Using a medium-sized city in Taiwan as a case study, the application of big data is reviewed by using Python to interface with Google Maps API for traffic information. Through the GIS interface, the government can understand the traffic service (or policies) for the public.","PeriodicalId":176611,"journal":{"name":"2023 IEEE 6th Eurasian Conference on Educational Innovation (ECEI)","volume":"24 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-02-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114655418","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2023-02-03DOI: 10.1109/ECEI57668.2023.10105339
Ping Yang
English translation content estimation is a key work in natural language processing. Unlike the conventional automatic evaluation method of English translation content, the translation quality estimation method does not use manual reference translation to evaluate the ability of English translation. However, according to the content quality estimation of the current sentences in English translation, the feature information extraction method lacks the generalization analysis of linguistic research, which also affects the use of subsequent vector regression methods. Therefore, the feature information of the vocabulary vector is studied to obtain the context vocabulary prediction model and matrix analysis model of deep learning. They are combined with the recursive neural network language modeling to enhance the reliability of the independent estimation and manual evaluation of translation quality. The experimental results using the data set of the sub-task of translation content quality estimation in WMT 15 and WMT 16 show that the method of obtaining the feature of sentence vector through context lexical analysis is consistently more effective than the original QuEst method and the feature acquisition method of sentence vector graph in continuous space language mode. It is also clarified that the newly established feature extraction method does not require linguistic means but significantly enhances the effectiveness of translation quality evaluation.
{"title":"Intelligent Evaluation Model of English Translation Content Quality Based on Improved Neural Network Algorithm","authors":"Ping Yang","doi":"10.1109/ECEI57668.2023.10105339","DOIUrl":"https://doi.org/10.1109/ECEI57668.2023.10105339","url":null,"abstract":"English translation content estimation is a key work in natural language processing. Unlike the conventional automatic evaluation method of English translation content, the translation quality estimation method does not use manual reference translation to evaluate the ability of English translation. However, according to the content quality estimation of the current sentences in English translation, the feature information extraction method lacks the generalization analysis of linguistic research, which also affects the use of subsequent vector regression methods. Therefore, the feature information of the vocabulary vector is studied to obtain the context vocabulary prediction model and matrix analysis model of deep learning. They are combined with the recursive neural network language modeling to enhance the reliability of the independent estimation and manual evaluation of translation quality. The experimental results using the data set of the sub-task of translation content quality estimation in WMT 15 and WMT 16 show that the method of obtaining the feature of sentence vector through context lexical analysis is consistently more effective than the original QuEst method and the feature acquisition method of sentence vector graph in continuous space language mode. It is also clarified that the newly established feature extraction method does not require linguistic means but significantly enhances the effectiveness of translation quality evaluation.","PeriodicalId":176611,"journal":{"name":"2023 IEEE 6th Eurasian Conference on Educational Innovation (ECEI)","volume":"36 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-02-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123016175","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
京公网安备 11010802042870号
京ICP备2023020795号-1
扫码关注我们
求助内容：
应助结果提醒方式：