In the era of artificial intelligence, computer-aided translation (CAT) tools are also constantly integrating and adding new functions based on artificial intelligence technology. The purpose is to further improve translation efficiency, shorten project cycle and reduce translation cost through the adoption of new technology. With the wide application of computer-aided translation tools in translation teaching and other fields, people put forward higher requirements for the human-machine interactive translation system based on artificial intelligence. Artificial intelligence technology, which can also be used as an educational technology, has been paid more attention to its application in teaching fields. AI-powered non-translatables function can efficiently assist automatic pre-translation and post-editing. This thesis analyzes the processing and application of AI-powered non-translatables function in computer-aided translation, and expects to provide reference for the development of computer-aided translation industry and education based on artificial intelligence and help for the research of artificial intelligence in natural language processing and computer-aided translation.
{"title":"Application Study of AI-powered Non-translatables Function in Computer-aided Translation","authors":"Hao Xing","doi":"10.1145/3582580.3582597","DOIUrl":"https://doi.org/10.1145/3582580.3582597","url":null,"abstract":"In the era of artificial intelligence, computer-aided translation (CAT) tools are also constantly integrating and adding new functions based on artificial intelligence technology. The purpose is to further improve translation efficiency, shorten project cycle and reduce translation cost through the adoption of new technology. With the wide application of computer-aided translation tools in translation teaching and other fields, people put forward higher requirements for the human-machine interactive translation system based on artificial intelligence. Artificial intelligence technology, which can also be used as an educational technology, has been paid more attention to its application in teaching fields. AI-powered non-translatables function can efficiently assist automatic pre-translation and post-editing. This thesis analyzes the processing and application of AI-powered non-translatables function in computer-aided translation, and expects to provide reference for the development of computer-aided translation industry and education based on artificial intelligence and help for the research of artificial intelligence in natural language processing and computer-aided translation.","PeriodicalId":138087,"journal":{"name":"Proceedings of the 2022 5th International Conference on Education Technology Management","volume":"35 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-12-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124920361","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}
Information technology, especially multimedia technology, with its strong interactive, visible and experiential nature, can significantly increase students' enthusiasm for active learning and the creation of awareness, and has more significant advantages for utilization. Computer multimedia technology is able to show the content that users want to convey in the form of audio and animation, which enriches the way of information dissemination and can show more space for development in future life. Nowadays, multimedia technology has been widely used in all aspects of real life and has achieved certain effects, especially in teaching activities through the use of multimedia technology, which can bring more convenience to English teaching. On this basis, this paper first analyzes the characteristics and utilization value of computer multimedia technology, then studies the design of English classroom teaching based on computer multimedia technology, and finally gives the application strategy of multimedia technology in the design of college English classroom. Due to the continuous development of computer information technology, multimedia has gradually become a new way to change teaching methods, and the use of computer multimedia technology during actual teaching can lead to effective improvement of English teaching effect, and promote the whole teaching content to have more vivid characteristics and enhance the teaching effect.
{"title":"Research on College English Classroom Teaching Design Based on Computer Multimedia Technology","authors":"Qing Song","doi":"10.1145/3582580.3584813","DOIUrl":"https://doi.org/10.1145/3582580.3584813","url":null,"abstract":"Information technology, especially multimedia technology, with its strong interactive, visible and experiential nature, can significantly increase students' enthusiasm for active learning and the creation of awareness, and has more significant advantages for utilization. Computer multimedia technology is able to show the content that users want to convey in the form of audio and animation, which enriches the way of information dissemination and can show more space for development in future life. Nowadays, multimedia technology has been widely used in all aspects of real life and has achieved certain effects, especially in teaching activities through the use of multimedia technology, which can bring more convenience to English teaching. On this basis, this paper first analyzes the characteristics and utilization value of computer multimedia technology, then studies the design of English classroom teaching based on computer multimedia technology, and finally gives the application strategy of multimedia technology in the design of college English classroom. Due to the continuous development of computer information technology, multimedia has gradually become a new way to change teaching methods, and the use of computer multimedia technology during actual teaching can lead to effective improvement of English teaching effect, and promote the whole teaching content to have more vivid characteristics and enhance the teaching effect.","PeriodicalId":138087,"journal":{"name":"Proceedings of the 2022 5th International Conference on Education Technology Management","volume":"8 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-12-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123623839","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}
The emergence of MOOC has constantly affected and changed people's learning methods. With the development and popularization of the Internet and computer technology, it has brought a huge impact on the traditional teaching of mathematics, and has also brought great convenience to our learning. In order to solve the shortcomings of the existing research on the application of BP neural algorithm in the development of mathematical MOOC system, this paper discusses the characteristics of MOOC system and the back propagation and generalization ability of BP neural algorithm, and briefly discusses the Python graphical interface development and system development environment for the application of BP neural algorithm in the development of mathematical MOOC system. Through the analysis of the mathematical formula recognition model by using the full convolution neural network and the bidirectional cyclic neural network, the experimental data analysis shows that HGNN can obtain more useful information from a smaller set of items to identify mathematical formulas. The teaching process design of mathematical MOOC system based on BP neural algorithm is designed, and the mathematical MOOC course is developed using the application of BP neural algorithm in mathematical MOOC system. It provides a reference for the application of mathematical MOOC system under BP neural algorithm.
{"title":"Development of Mathematical MOOC System Based on BP Neural Algorithm","authors":"Youzeng Wang, Qing-Tang Su, Zijie Wang","doi":"10.1145/3582580.3584814","DOIUrl":"https://doi.org/10.1145/3582580.3584814","url":null,"abstract":"The emergence of MOOC has constantly affected and changed people's learning methods. With the development and popularization of the Internet and computer technology, it has brought a huge impact on the traditional teaching of mathematics, and has also brought great convenience to our learning. In order to solve the shortcomings of the existing research on the application of BP neural algorithm in the development of mathematical MOOC system, this paper discusses the characteristics of MOOC system and the back propagation and generalization ability of BP neural algorithm, and briefly discusses the Python graphical interface development and system development environment for the application of BP neural algorithm in the development of mathematical MOOC system. Through the analysis of the mathematical formula recognition model by using the full convolution neural network and the bidirectional cyclic neural network, the experimental data analysis shows that HGNN can obtain more useful information from a smaller set of items to identify mathematical formulas. The teaching process design of mathematical MOOC system based on BP neural algorithm is designed, and the mathematical MOOC course is developed using the application of BP neural algorithm in mathematical MOOC system. It provides a reference for the application of mathematical MOOC system under BP neural algorithm.","PeriodicalId":138087,"journal":{"name":"Proceedings of the 2022 5th International Conference on Education Technology Management","volume":"15 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-12-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123202374","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}
Desi Indrawati, Meitty Josephin Balontia, B. Benny
In the current digital era, video production has become more effective. This is due to the availability of new technologies such as Information and Communication Technology (ICT) in education. In other words, the use of video has triggered teachers to use it in teaching and learning. This research was encouraged by the fact that the teachers keep motivating their students in classes to preserve their local language. Thus, it was necessary to use a recent method such as a VPA learning model to assist students in improving their Local language learning outputs. The objective of the research was to determine whether there were prominent differences in students' Local language learning outputs between the project assignment they made through Video Project Assignment (VPA) and the script without video. A quasi-experimental study was done with the study population being students at Public Junior High School 2 Parigi. The sample was a class with 31 students as a control group who were given a Local language Writing Project Assignment for the pre-test and another class was an experimental class that consisted of 31 students who were given a Video Project Assignment (VPA) in the form of Local language speech for the post-test. The findings indicated that the VPA successfully enhanced students' Local language ability because it was attractive and encouraging, inspiring, reassuring, enlightening, amusing, and achievable. Moreover, the VPA was also found to be more fulfilled in improving students' Local language ability than a Writing Project Assignment, and by creating Video Project Assignment (VPA), students confirmed positive responses, rendezvous, and attainment.
{"title":"The Effectiveness of Video Project Assignment in Local Language Class","authors":"Desi Indrawati, Meitty Josephin Balontia, B. Benny","doi":"10.1145/3582580.3582644","DOIUrl":"https://doi.org/10.1145/3582580.3582644","url":null,"abstract":"In the current digital era, video production has become more effective. This is due to the availability of new technologies such as Information and Communication Technology (ICT) in education. In other words, the use of video has triggered teachers to use it in teaching and learning. This research was encouraged by the fact that the teachers keep motivating their students in classes to preserve their local language. Thus, it was necessary to use a recent method such as a VPA learning model to assist students in improving their Local language learning outputs. The objective of the research was to determine whether there were prominent differences in students' Local language learning outputs between the project assignment they made through Video Project Assignment (VPA) and the script without video. A quasi-experimental study was done with the study population being students at Public Junior High School 2 Parigi. The sample was a class with 31 students as a control group who were given a Local language Writing Project Assignment for the pre-test and another class was an experimental class that consisted of 31 students who were given a Video Project Assignment (VPA) in the form of Local language speech for the post-test. The findings indicated that the VPA successfully enhanced students' Local language ability because it was attractive and encouraging, inspiring, reassuring, enlightening, amusing, and achievable. Moreover, the VPA was also found to be more fulfilled in improving students' Local language ability than a Writing Project Assignment, and by creating Video Project Assignment (VPA), students confirmed positive responses, rendezvous, and attainment.","PeriodicalId":138087,"journal":{"name":"Proceedings of the 2022 5th International Conference on Education Technology Management","volume":"32 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-12-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123475580","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}
Technological media has become a vital component for educators, enabling greater efficiency in lesson planning and preparation, providing active repositories of student work, as well as more personalised learning for students. The construction of intelligent systems, which encompass the use of these technologies, allow the learning process to be simpler for the student and the teaching process for the teacher to be more efficient. Thus, ambient intelligence will be the element used to connect the classroom to the intelligent classroom and used to adapt the learning process. With the rapid development of the Internet of Things (IoT) and Artificial Intelligence (AI), their applicability in education will be easy to implement and can solve some defects of the traditional education model and the computer-aided system teaching model, and at the same time make learning more motivating and enticing for the student. The aim of this research is to identify the most recent studies on the application of artificial intelligence in education and to make a comparative study of the different models and existing applications that use this technology to promote learning efficiently
{"title":"Survey for Smart and Adaptative Education","authors":"Rita M. A. Bezerra, D. Durães, Paulo Novais","doi":"10.1145/3582580.3582622","DOIUrl":"https://doi.org/10.1145/3582580.3582622","url":null,"abstract":"Technological media has become a vital component for educators, enabling greater efficiency in lesson planning and preparation, providing active repositories of student work, as well as more personalised learning for students. The construction of intelligent systems, which encompass the use of these technologies, allow the learning process to be simpler for the student and the teaching process for the teacher to be more efficient. Thus, ambient intelligence will be the element used to connect the classroom to the intelligent classroom and used to adapt the learning process. With the rapid development of the Internet of Things (IoT) and Artificial Intelligence (AI), their applicability in education will be easy to implement and can solve some defects of the traditional education model and the computer-aided system teaching model, and at the same time make learning more motivating and enticing for the student. The aim of this research is to identify the most recent studies on the application of artificial intelligence in education and to make a comparative study of the different models and existing applications that use this technology to promote learning efficiently","PeriodicalId":138087,"journal":{"name":"Proceedings of the 2022 5th International Conference on Education Technology Management","volume":"9 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-12-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123147268","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}
Digital resources are the basis to support students' online learning and autonomous learning. Based on the difficulties of college students in understanding abstract text resources, this paper adds explanatory resources in the construction of digital textbooks according to the actual situation of students, that is, for words or content that students do not understand in digital text resources, it provides text type explanatory resources to improve the readability of text resources and the comprehensibility of content. Through tracking research in natural situations, interpretative resources can improve the readability of digital textbooks, guide students to read in depth, thus improving students' learning effect, and provide directional suggestions for the construction of digital resources.
{"title":"Research on the Explanatory Text Resources Promoting College Students' Deep Learning","authors":"Yueting Yang, Mei Jing, Yue-liang Zhou","doi":"10.1145/3582580.3582584","DOIUrl":"https://doi.org/10.1145/3582580.3582584","url":null,"abstract":"Digital resources are the basis to support students' online learning and autonomous learning. Based on the difficulties of college students in understanding abstract text resources, this paper adds explanatory resources in the construction of digital textbooks according to the actual situation of students, that is, for words or content that students do not understand in digital text resources, it provides text type explanatory resources to improve the readability of text resources and the comprehensibility of content. Through tracking research in natural situations, interpretative resources can improve the readability of digital textbooks, guide students to read in depth, thus improving students' learning effect, and provide directional suggestions for the construction of digital resources.","PeriodicalId":138087,"journal":{"name":"Proceedings of the 2022 5th International Conference on Education Technology Management","volume":"5 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-12-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131056988","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}
This article is focusing on the digital branding of vocational high schools with industrial partnership. The method used was qualitative for implementing the strategy and achieving the target to digital branding the school. The program was done according to the schedule made by the School Principal together with the team. In collaboration with Industrial and Business Community (IDUKA) and monitored by MITRASDUDI together with Research Interest Group – Cross Cultural Communication, Binus University, the program ran well in a given period. The result showed that the collaboration between Industries and SMK Muhammadiyah Kandanghaur was improving the teaching and learning process in the school, so that activities succeeded in digital branding the school as well.
{"title":"Digital Branding of Vocational High School with Industrial Partnership: Case Study of SMK Muhammadiyah Kandanghaur, Indonesia","authors":"M. Willyarto, U. Yunus, Supeno SMK Muhammadiyah","doi":"10.1145/3582580.3582640","DOIUrl":"https://doi.org/10.1145/3582580.3582640","url":null,"abstract":"This article is focusing on the digital branding of vocational high schools with industrial partnership. The method used was qualitative for implementing the strategy and achieving the target to digital branding the school. The program was done according to the schedule made by the School Principal together with the team. In collaboration with Industrial and Business Community (IDUKA) and monitored by MITRASDUDI together with Research Interest Group – Cross Cultural Communication, Binus University, the program ran well in a given period. The result showed that the collaboration between Industries and SMK Muhammadiyah Kandanghaur was improving the teaching and learning process in the school, so that activities succeeded in digital branding the school as well.","PeriodicalId":138087,"journal":{"name":"Proceedings of the 2022 5th International Conference on Education Technology Management","volume":"74 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-12-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114552096","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}
Experiment teaching is the teaching difficulty of Engineering Mechanics in vocational colleges. The lack of relevant equipment poses a great challenge to teaching. In order to solve this problem and improve the quality of teaching, the research group proposed a strategy using simulation technology. The torsion experiment of Engineering Mechanics was used as a case for teaching practice. Firstly, the problems in the teaching were analyzed. Secondly, the research group proposed a targeted teaching design. Thirdly, the finite element model was established and simulated on a server. Fourthly, the digital teaching resources were sorted out based on the simulation results. Fifthly, teaching practice had been implemented in the classroom. Finally, the quality of teaching practice was evaluated. The results show that modeling and simulation technology can significantly improve the quality of teaching. The enthusiasm of the students has been significantly improved. The colorful nephograms are convenient for students to understand the boring knowledge. This study provides ideas for the innovation of experimental teaching and the development of curriculum resources in vocational colleges. More new technologies should be explored and tried by more scholars.
{"title":"Application of Modeling and Simulation Technology in Teaching Practice of Engineering Mechanics","authors":"Shang Wang, Qingsong Zhu, Xuesong Zhen","doi":"10.1145/3582580.3582598","DOIUrl":"https://doi.org/10.1145/3582580.3582598","url":null,"abstract":"Experiment teaching is the teaching difficulty of Engineering Mechanics in vocational colleges. The lack of relevant equipment poses a great challenge to teaching. In order to solve this problem and improve the quality of teaching, the research group proposed a strategy using simulation technology. The torsion experiment of Engineering Mechanics was used as a case for teaching practice. Firstly, the problems in the teaching were analyzed. Secondly, the research group proposed a targeted teaching design. Thirdly, the finite element model was established and simulated on a server. Fourthly, the digital teaching resources were sorted out based on the simulation results. Fifthly, teaching practice had been implemented in the classroom. Finally, the quality of teaching practice was evaluated. The results show that modeling and simulation technology can significantly improve the quality of teaching. The enthusiasm of the students has been significantly improved. The colorful nephograms are convenient for students to understand the boring knowledge. This study provides ideas for the innovation of experimental teaching and the development of curriculum resources in vocational colleges. More new technologies should be explored and tried by more scholars.","PeriodicalId":138087,"journal":{"name":"Proceedings of the 2022 5th International Conference on Education Technology Management","volume":"72 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-12-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133839930","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}
The purpose of the study explores the challenges of online education from three aspects, include: lecturers, students, and the external environment. This paper conducts through an online questionnaire survey of 389 faculty and students from eight colleges of Shenyang Jianzhu University based on the Likert scale to measure the degree of identification between lecturers and students in online learning challenges during the pandemic, identified the most important challenges faced by lecturers, students, and the external environment through quantitative analysis, and gave recommendations for various problems. The study was conducted from May 2022 to November 2022, and the quantitative results are as follows:1) The biggest challenge for lecturers is the cognitive overload caused by e-education, with the Degree of approval index (DAI); 2) and the highest approval index (HAI) for students' lack of self-directed learning ability and self-control; 3) From an environmental point of view, network stability issues plague all respondents (lecturers, students) and are the most urgent problem to solve. As for the further data analysis, we found the factors of age and self-control ability were also influence on cognitive load.
{"title":"Challenges of E-learning in Shenyang Jianzhu University","authors":"Bo Qin, Yue Li","doi":"10.1145/3582580.3582587","DOIUrl":"https://doi.org/10.1145/3582580.3582587","url":null,"abstract":"The purpose of the study explores the challenges of online education from three aspects, include: lecturers, students, and the external environment. This paper conducts through an online questionnaire survey of 389 faculty and students from eight colleges of Shenyang Jianzhu University based on the Likert scale to measure the degree of identification between lecturers and students in online learning challenges during the pandemic, identified the most important challenges faced by lecturers, students, and the external environment through quantitative analysis, and gave recommendations for various problems. The study was conducted from May 2022 to November 2022, and the quantitative results are as follows:1) The biggest challenge for lecturers is the cognitive overload caused by e-education, with the Degree of approval index (DAI); 2) and the highest approval index (HAI) for students' lack of self-directed learning ability and self-control; 3) From an environmental point of view, network stability issues plague all respondents (lecturers, students) and are the most urgent problem to solve. As for the further data analysis, we found the factors of age and self-control ability were also influence on cognitive load.","PeriodicalId":138087,"journal":{"name":"Proceedings of the 2022 5th International Conference on Education Technology Management","volume":"40 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-12-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116088335","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}
We introduce a method for learning to embed word senses as defined in a given set of dictionaries. In our approach, senses as definition triples, are transformed into low-dimension vectors aimed at maximizing the probability of reconstructing the definitions in an autoencoder. The method involves automatically training sense autoencoder for encoding sense definitions, automatically aligning sense definitions, and automatically generating embeddings of arbitrary description. At run-time, queries from users are mapped to the embedding space and re-ranking is performed on the sense definition retrieved. We present a prototype sense definition embedding, SenseNet, that applies the method to two dictionaries. Blind evaluation on a set of real queries shows that the method significantly outperforms a baseline based on the Lesk algorithm. Our methodology clearly supports combining multiple dictionaries resulting in additional improvement in representing sense definitions of multiple dictionaries. Although there is no distinctive header, this is the abstract. This submission template allows authors to submit their papers for review to an ACM Conference or Journal without any output design specifications incorporated at this point in the process. The ACM manuscript template is a single column document that allows authors to type their content into the pre-existing set of paragraph formatting styles applied to the sample placeholder text here. Throughout the document you will find further instructions on how to format your text.
{"title":"Learning Sense Embeddings from Dictionary Definition","authors":"Kai-Wen Tuan, Kuan-lin Lee, Jason J. S. Chang","doi":"10.1145/3582580.3582603","DOIUrl":"https://doi.org/10.1145/3582580.3582603","url":null,"abstract":"We introduce a method for learning to embed word senses as defined in a given set of dictionaries. In our approach, senses as definition triples, are transformed into low-dimension vectors aimed at maximizing the probability of reconstructing the definitions in an autoencoder. The method involves automatically training sense autoencoder for encoding sense definitions, automatically aligning sense definitions, and automatically generating embeddings of arbitrary description. At run-time, queries from users are mapped to the embedding space and re-ranking is performed on the sense definition retrieved. We present a prototype sense definition embedding, SenseNet, that applies the method to two dictionaries. Blind evaluation on a set of real queries shows that the method significantly outperforms a baseline based on the Lesk algorithm. Our methodology clearly supports combining multiple dictionaries resulting in additional improvement in representing sense definitions of multiple dictionaries. Although there is no distinctive header, this is the abstract. This submission template allows authors to submit their papers for review to an ACM Conference or Journal without any output design specifications incorporated at this point in the process. The ACM manuscript template is a single column document that allows authors to type their content into the pre-existing set of paragraph formatting styles applied to the sample placeholder text here. Throughout the document you will find further instructions on how to format your text.","PeriodicalId":138087,"journal":{"name":"Proceedings of the 2022 5th International Conference on Education Technology Management","volume":"103 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-12-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124181527","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：