Pub Date : 2022-12-18DOI: 10.1109/IEIR56323.2022.10050039
Yan Hu, Jian Shen, Rui Hou, Huan-Tian Huang
This study investigated formative assessment for hybrid course. The participants were 379 students who took the "college Physics" hybrid course in the fall of 2022 in a university of China. Most students were learning with face-to-face teaching, while a few students were learning remotely in smart classrooms. Data were collected from the cognitive presence survey within community of inquiry framework and online self-regulatory learning questionnaire during the middle term. The result indicated that remote students’ cognitive presence were lower than students with face-to-face teaching in the smart classroom, and there were strong positive correlation between students’ online self-regulatory learning and cognitive presence. It was suggested that cognitive presence were measured again at the end of the semester to examine whether the cognitive presence of remote students in the final semester is better than that of the middle semester after intervention.
{"title":"Formative assessment for hybrid course in smart classroom: A cognitive presence perspective","authors":"Yan Hu, Jian Shen, Rui Hou, Huan-Tian Huang","doi":"10.1109/IEIR56323.2022.10050039","DOIUrl":"https://doi.org/10.1109/IEIR56323.2022.10050039","url":null,"abstract":"This study investigated formative assessment for hybrid course. The participants were 379 students who took the \"college Physics\" hybrid course in the fall of 2022 in a university of China. Most students were learning with face-to-face teaching, while a few students were learning remotely in smart classrooms. Data were collected from the cognitive presence survey within community of inquiry framework and online self-regulatory learning questionnaire during the middle term. The result indicated that remote students’ cognitive presence were lower than students with face-to-face teaching in the smart classroom, and there were strong positive correlation between students’ online self-regulatory learning and cognitive presence. It was suggested that cognitive presence were measured again at the end of the semester to examine whether the cognitive presence of remote students in the final semester is better than that of the middle semester after intervention.","PeriodicalId":183709,"journal":{"name":"2022 International Conference on Intelligent Education and Intelligent Research (IEIR)","volume":"15 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-12-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116104249","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}
With the development of blockchain technology, more and more attention has been paid to the intersection of blockchain and education, and various educational evaluation systems and E-learning systems are developed based on blockchain technology. Among them, Ethereum smart contract is favored by developers for its “event-triggered” mechanism for building education intelligent trading systems and intelligent learning platforms. However, due to the immutability of blockchain, published smart contracts cannot be modified, so problematic contracts cannot be fixed by modifying the code in the educational blockchain. In recent years, security incidents due to smart contract vulnerabilities have caused huge property losses, so the detection of smart contract vulnerabilities in educational blockchain has become a great challenge. To solve this problem, this paper proposes a graph neural network (GNN) based vulnerability detection for smart contracts in educational blockchains. Firstly, the bytecodes are decompiled to get the opcode. Secondly, the basic blocks are divided, and the edges between the basic blocks according to the opcode execution logic are added. Then, the control flow graphs (CFG) are built. Finally, we designed a GNN-based model for vulnerability detection. The experimental results show that the proposed method is effective for the vulnerability detection of smart contracts. Compared with the traditional approaches, it can get good results with fewer layers of the GCN model, which shows that the contract bytecode and GCN model are efficient in vulnerability detection.
{"title":"Smart Contract Vulnerability Detection for Educational Blockchain Based on Graph Neural Networks","authors":"Zhifeng Wang, Wanxuan Wu, Chunyan Zeng, Jialong Yao, Yang Yang, Hongmin Xu","doi":"10.1109/IEIR56323.2022.10050059","DOIUrl":"https://doi.org/10.1109/IEIR56323.2022.10050059","url":null,"abstract":"With the development of blockchain technology, more and more attention has been paid to the intersection of blockchain and education, and various educational evaluation systems and E-learning systems are developed based on blockchain technology. Among them, Ethereum smart contract is favored by developers for its “event-triggered” mechanism for building education intelligent trading systems and intelligent learning platforms. However, due to the immutability of blockchain, published smart contracts cannot be modified, so problematic contracts cannot be fixed by modifying the code in the educational blockchain. In recent years, security incidents due to smart contract vulnerabilities have caused huge property losses, so the detection of smart contract vulnerabilities in educational blockchain has become a great challenge. To solve this problem, this paper proposes a graph neural network (GNN) based vulnerability detection for smart contracts in educational blockchains. Firstly, the bytecodes are decompiled to get the opcode. Secondly, the basic blocks are divided, and the edges between the basic blocks according to the opcode execution logic are added. Then, the control flow graphs (CFG) are built. Finally, we designed a GNN-based model for vulnerability detection. The experimental results show that the proposed method is effective for the vulnerability detection of smart contracts. Compared with the traditional approaches, it can get good results with fewer layers of the GCN model, which shows that the contract bytecode and GCN model are efficient in vulnerability detection.","PeriodicalId":183709,"journal":{"name":"2022 International Conference on Intelligent Education and Intelligent Research (IEIR)","volume":"90 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-12-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129440815","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 : 2022-12-18DOI: 10.1109/ieir56323.2022.10050040
{"title":"IEIR 2022 Cover Page","authors":"","doi":"10.1109/ieir56323.2022.10050040","DOIUrl":"https://doi.org/10.1109/ieir56323.2022.10050040","url":null,"abstract":"","PeriodicalId":183709,"journal":{"name":"2022 International Conference on Intelligent Education and Intelligent Research (IEIR)","volume":"16 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-12-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122385648","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 : 2022-12-18DOI: 10.1109/IEIR56323.2022.10050083
Shishun Wu, Xuebi Xu, Rui Liu, Guanghua Liang, Hao Meng, Bin He
To provide the step by step tutoring service like a human tutor, an intelligent tutoring system (ITS) for math word problem solving (MathITS) is proposed in this paper. The proposed MathITS has an ability of automatically generate tutorial solutions for any user input problems and thus could be widely used in after-class tutoring. An improved math word problem solver is applied to generate the tutorial solution, which transforms expression solutions into logic sequences of arithmetic operations with illustrating texts. In stage of adaptive tutoring, hints and suggestions are generated and launched to students rather giving them explicit solutions. Finally, an evaluation module is provided which gives immediate feedback on the evaluation of the whole process of multi-turn tutoring interaction. A pioneer experiment is conducted and the results demonstrate the efficiency of the proposed system.
{"title":"An Intelligent Tutoring System for Math Word Problem Solving with Tutorial Solution Generation","authors":"Shishun Wu, Xuebi Xu, Rui Liu, Guanghua Liang, Hao Meng, Bin He","doi":"10.1109/IEIR56323.2022.10050083","DOIUrl":"https://doi.org/10.1109/IEIR56323.2022.10050083","url":null,"abstract":"To provide the step by step tutoring service like a human tutor, an intelligent tutoring system (ITS) for math word problem solving (MathITS) is proposed in this paper. The proposed MathITS has an ability of automatically generate tutorial solutions for any user input problems and thus could be widely used in after-class tutoring. An improved math word problem solver is applied to generate the tutorial solution, which transforms expression solutions into logic sequences of arithmetic operations with illustrating texts. In stage of adaptive tutoring, hints and suggestions are generated and launched to students rather giving them explicit solutions. Finally, an evaluation module is provided which gives immediate feedback on the evaluation of the whole process of multi-turn tutoring interaction. A pioneer experiment is conducted and the results demonstrate the efficiency of the proposed system.","PeriodicalId":183709,"journal":{"name":"2022 International Conference on Intelligent Education and Intelligent Research (IEIR)","volume":"4 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-12-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125339890","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 : 2022-12-18DOI: 10.1109/IEIR56323.2022.10050070
Yuyu Zheng, Leyuan Liu
Autism spectrum disorders (ASD) impact the development of children’s language, motor, and expression abilities, causing great adverse effects on children’s growth. The incidence of autism screening is still quite poor, nevertheless, due to the traditional method’s time and financial requirements for child guardians. If symptoms of autism are detected early, children with autism usually return to normal development after effective medical intervention. Furthermore, the likelihood of accurately identifying children with autism grows if deep learning is used to recognize face images of autistic children. In this study, the dataset of autistic children’s faces in the Kaggle database [1] is selected to classify the typically developing children and autistic children through the face recognition model. On model selection, VGG19 [1], VGG16 [2], ResNet18 [3], ResNet101 [4], and DenseNet161 [5] are candidates. After training, among the five models, ResNet101 and DenseNet161 have better performance, and the recall rate of ResNet101 is higher in these two networks.
{"title":"Rapid Screening of Children With Autism Spectrum Disorders Through Face Image Classification","authors":"Yuyu Zheng, Leyuan Liu","doi":"10.1109/IEIR56323.2022.10050070","DOIUrl":"https://doi.org/10.1109/IEIR56323.2022.10050070","url":null,"abstract":"Autism spectrum disorders (ASD) impact the development of children’s language, motor, and expression abilities, causing great adverse effects on children’s growth. The incidence of autism screening is still quite poor, nevertheless, due to the traditional method’s time and financial requirements for child guardians. If symptoms of autism are detected early, children with autism usually return to normal development after effective medical intervention. Furthermore, the likelihood of accurately identifying children with autism grows if deep learning is used to recognize face images of autistic children. In this study, the dataset of autistic children’s faces in the Kaggle database [1] is selected to classify the typically developing children and autistic children through the face recognition model. On model selection, VGG19 [1], VGG16 [2], ResNet18 [3], ResNet101 [4], and DenseNet161 [5] are candidates. After training, among the five models, ResNet101 and DenseNet161 have better performance, and the recall rate of ResNet101 is higher in these two networks.","PeriodicalId":183709,"journal":{"name":"2022 International Conference on Intelligent Education and Intelligent Research (IEIR)","volume":"45 23 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-12-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127632748","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}
Under the current educational background of “double subtraction in order to effectively improve students’ ability to write standardized Chinese characters and solve the problem of shortage of teachers for writing education, an intelligent scoring method for standardized Chinese character writing based on template Chinese character eigenvalue similarity is proposed. The method consists of three steps: firstly, a Chinese character evaluation classification model is established based on the eigenvalue information of handwritten Chinese character samples and expert pre-evaluation results, and the standard interval of Chinese character eigenvalue is determined based on the classification results of the model. Secondly, a multiple linear regression model is established based on the scores of individual writing rules of Chinese characters and the overall scores of experts on handwritten Chinese character samples. Through the model, the influence weight of each writing rule on the evaluation of whole character writing is determined. Thirdly, combining the similarity of eigenvalues, the difference of eigenvalues and the influence weight ofwriting rules, we can score the handwritten Chinese characters, include overall score and quantifiable details.
{"title":"Research on Intelligent Scoring Method of Standardized Chinese Character Writing","authors":"Jiangbo Shu, Shuaicheng Lu, Jianran Li, Jingli Zeng","doi":"10.1109/IEIR56323.2022.10050043","DOIUrl":"https://doi.org/10.1109/IEIR56323.2022.10050043","url":null,"abstract":"Under the current educational background of “double subtraction in order to effectively improve students’ ability to write standardized Chinese characters and solve the problem of shortage of teachers for writing education, an intelligent scoring method for standardized Chinese character writing based on template Chinese character eigenvalue similarity is proposed. The method consists of three steps: firstly, a Chinese character evaluation classification model is established based on the eigenvalue information of handwritten Chinese character samples and expert pre-evaluation results, and the standard interval of Chinese character eigenvalue is determined based on the classification results of the model. Secondly, a multiple linear regression model is established based on the scores of individual writing rules of Chinese characters and the overall scores of experts on handwritten Chinese character samples. Through the model, the influence weight of each writing rule on the evaluation of whole character writing is determined. Thirdly, combining the similarity of eigenvalues, the difference of eigenvalues and the influence weight ofwriting rules, we can score the handwritten Chinese characters, include overall score and quantifiable details.","PeriodicalId":183709,"journal":{"name":"2022 International Conference on Intelligent Education and Intelligent Research (IEIR)","volume":"5 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-12-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128048263","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 : 2022-12-18DOI: 10.1109/IEIR56323.2022.10050077
Hongye Zhu, Jinhua Zhao, L. Niu
AI and big data analysis for student classroom behavior recognition can be used as auxiliary means to improve teaching quality. Recognition in classroom scenarios suffers from issues such as tiny targets and complex environmental interference. To tackle these problems, an efficient model based on YOLOv4-tiny is proposed in this paper. Specifically, we design a new module named ResBlock-S to reduce the floating point operations (FLOPs) of the model to improve the speed. Then, the introduction of the Convolutional Block Attention Module (CBAM) mechanism to obtain extra local information of images during the training process, which can ensure the recognition accuracy. As most available public datasets are not applicable to this work, we construct a classroom behavior dataset. Experiments were conducted on the public dataset and our self-built dataset to verify the performance of our model in general scenarios and classroom scenarios, respectively. Compared with YOLOv4-tiny and other lightweight CNN models such as MobileNetv2, MobileNetv3 and ShuffleNetv2, the mean Average Precision (mAP) of our approach on the self-built dataset is higher and up to 89.9%. Additionally, the detection speed of our approach is faster than the aforementioned methods, which is up to 167 fps.
{"title":"An Efficient Model For Student Behavior Recognition in Classroom","authors":"Hongye Zhu, Jinhua Zhao, L. Niu","doi":"10.1109/IEIR56323.2022.10050077","DOIUrl":"https://doi.org/10.1109/IEIR56323.2022.10050077","url":null,"abstract":"AI and big data analysis for student classroom behavior recognition can be used as auxiliary means to improve teaching quality. Recognition in classroom scenarios suffers from issues such as tiny targets and complex environmental interference. To tackle these problems, an efficient model based on YOLOv4-tiny is proposed in this paper. Specifically, we design a new module named ResBlock-S to reduce the floating point operations (FLOPs) of the model to improve the speed. Then, the introduction of the Convolutional Block Attention Module (CBAM) mechanism to obtain extra local information of images during the training process, which can ensure the recognition accuracy. As most available public datasets are not applicable to this work, we construct a classroom behavior dataset. Experiments were conducted on the public dataset and our self-built dataset to verify the performance of our model in general scenarios and classroom scenarios, respectively. Compared with YOLOv4-tiny and other lightweight CNN models such as MobileNetv2, MobileNetv3 and ShuffleNetv2, the mean Average Precision (mAP) of our approach on the self-built dataset is higher and up to 89.9%. Additionally, the detection speed of our approach is faster than the aforementioned methods, which is up to 167 fps.","PeriodicalId":183709,"journal":{"name":"2022 International Conference on Intelligent Education and Intelligent Research (IEIR)","volume":"37 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-12-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"134322891","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 : 2022-12-18DOI: 10.1109/IEIR56323.2022.10050051
Si Zhang, Y. Zhang, Xinyue He, Tongyu Guo, Yiyao Wang
Recognizing boundaries of online professional learning communities can help to provide teachers with a meaningful online learning environment that improves their training performance. This study proposed an automated discourse analysis approach for recognizing boundaries of the online learning communities, that combines both Topic Modelling approach (Latent Dirichlet Allocation) and Social Network Analysis. The study examined online discourse data of 1843 teachers participating in an online training program. The findings revealed that teachers mainly responded to others’ posts and the pattern of teachers’ response could be mainly divided into four types. The semantic network formed by discourse unit was high-density with low average network distance and high degree centrality, and the cohesion parameter of the semantic network was relatively stable during the whole process of online discourse. The findings of the study also can provide insights into creating online learning communities and teacher education.
{"title":"Recognizing boundaries of online professional learning communities in an automated discourse analysis approach","authors":"Si Zhang, Y. Zhang, Xinyue He, Tongyu Guo, Yiyao Wang","doi":"10.1109/IEIR56323.2022.10050051","DOIUrl":"https://doi.org/10.1109/IEIR56323.2022.10050051","url":null,"abstract":"Recognizing boundaries of online professional learning communities can help to provide teachers with a meaningful online learning environment that improves their training performance. This study proposed an automated discourse analysis approach for recognizing boundaries of the online learning communities, that combines both Topic Modelling approach (Latent Dirichlet Allocation) and Social Network Analysis. The study examined online discourse data of 1843 teachers participating in an online training program. The findings revealed that teachers mainly responded to others’ posts and the pattern of teachers’ response could be mainly divided into four types. The semantic network formed by discourse unit was high-density with low average network distance and high degree centrality, and the cohesion parameter of the semantic network was relatively stable during the whole process of online discourse. The findings of the study also can provide insights into creating online learning communities and teacher education.","PeriodicalId":183709,"journal":{"name":"2022 International Conference on Intelligent Education and Intelligent Research (IEIR)","volume":"3 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-12-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133268952","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 : 2022-12-18DOI: 10.1109/IEIR56323.2022.10050078
Fan Luo, Xinguo Yu
In the process of survey writing, searching for scientific documents related to a topic and fully understanding these documents are two critical but time-consuming steps. Automatic paper collection and summarization technologies can help to improve work efficiency and work quality. Therefore, this work-in-progress paper integrates the citation recommendation model, the structured content extraction model, and the long scientific documents summarization model to propose an automatic scientific document collection and summarization system. This system can extract topics from single or multiple paragraphs, collect relevant papers, and generate a summary table for the collected papers to benefit survey writing.
{"title":"Scientific Documents Collection and Summarization for Survey Writing","authors":"Fan Luo, Xinguo Yu","doi":"10.1109/IEIR56323.2022.10050078","DOIUrl":"https://doi.org/10.1109/IEIR56323.2022.10050078","url":null,"abstract":"In the process of survey writing, searching for scientific documents related to a topic and fully understanding these documents are two critical but time-consuming steps. Automatic paper collection and summarization technologies can help to improve work efficiency and work quality. Therefore, this work-in-progress paper integrates the citation recommendation model, the structured content extraction model, and the long scientific documents summarization model to propose an automatic scientific document collection and summarization system. This system can extract topics from single or multiple paragraphs, collect relevant papers, and generate a summary table for the collected papers to benefit survey writing.","PeriodicalId":183709,"journal":{"name":"2022 International Conference on Intelligent Education and Intelligent Research (IEIR)","volume":"90 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-12-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122535945","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 : 2022-12-18DOI: 10.1109/IEIR56323.2022.10050058
Shengnan Chen, Pingheng Wang, Mengyuan Zhou, Zirui Wang, Bin He
Benefit from the neural network research, a couple of neural solvers have been developed for automatically solving math word problems (MWPs). These neural solvers are evaluated on several benchmark datasets with diverse characteristics, which leads to a poor comparability of the performance of each solver. To address the problem, a comparative analysis is conducted in this paper to explore the performance variations of neural solvers in solving different characteristic MWPs. The architectures of the typical neural solvers are studied and a four-dimensional index model is proposed to characterize the benchmark dataset into different subsets. The experimental results show that the Seq2Seq-based model solvers perform well on most of the subsets, while Graph2Tree based solvers seem to have more potential in solving problems with complex expression structures.
{"title":"A Comparative Analysis of Math Word Problem Solving on Characterized Datasets","authors":"Shengnan Chen, Pingheng Wang, Mengyuan Zhou, Zirui Wang, Bin He","doi":"10.1109/IEIR56323.2022.10050058","DOIUrl":"https://doi.org/10.1109/IEIR56323.2022.10050058","url":null,"abstract":"Benefit from the neural network research, a couple of neural solvers have been developed for automatically solving math word problems (MWPs). These neural solvers are evaluated on several benchmark datasets with diverse characteristics, which leads to a poor comparability of the performance of each solver. To address the problem, a comparative analysis is conducted in this paper to explore the performance variations of neural solvers in solving different characteristic MWPs. The architectures of the typical neural solvers are studied and a four-dimensional index model is proposed to characterize the benchmark dataset into different subsets. The experimental results show that the Seq2Seq-based model solvers perform well on most of the subsets, while Graph2Tree based solvers seem to have more potential in solving problems with complex expression structures.","PeriodicalId":183709,"journal":{"name":"2022 International Conference on Intelligent Education and Intelligent Research (IEIR)","volume":"53 6 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-12-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126767633","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：