Pub Date : 2022-06-16DOI: 10.1109/CyberneticsCom55287.2022.9865479
Hoang-Quan Dang, Duc-Duy-Anh Nguyen, Trong-Hop Do
In this article, we solved two tasks in the Vietnamese Aspect-based Sentiment Analysis problem: Aspect Category Detection (ACD) and Sentiment Polarity Classification (SPC). Besides, we proposed end-to-end models to handle the above tasks simultaneously for two domains (Restaurant and Hotel) in the VLSP 2018 Aspect-based Sentiment Analysis dataset using PhoBERT as Pre-trained language models for Vietnamese in two ways: Multi-task and Multi-task with Multi-branch approach. Both models give very good results when applied preprocessing. Specifically, the Multi-task model achieves state-of-the-art (SOTA) results in the Hotel domain of the VLSP 2018 ABSA dataset, with the F1-score being 82.55% for ACD and 77.32% for ACD with SPC. For the Restaurant domain, our Multi-task model also achieved SOTA in the ACD with SPC task by an F1-score of 71.55% and 83.29% for the ACD.
{"title":"Multi-task Solution for Aspect Category Sentiment Analysis on Vietnamese Datasets","authors":"Hoang-Quan Dang, Duc-Duy-Anh Nguyen, Trong-Hop Do","doi":"10.1109/CyberneticsCom55287.2022.9865479","DOIUrl":"https://doi.org/10.1109/CyberneticsCom55287.2022.9865479","url":null,"abstract":"In this article, we solved two tasks in the Vietnamese Aspect-based Sentiment Analysis problem: Aspect Category Detection (ACD) and Sentiment Polarity Classification (SPC). Besides, we proposed end-to-end models to handle the above tasks simultaneously for two domains (Restaurant and Hotel) in the VLSP 2018 Aspect-based Sentiment Analysis dataset using PhoBERT as Pre-trained language models for Vietnamese in two ways: Multi-task and Multi-task with Multi-branch approach. Both models give very good results when applied preprocessing. Specifically, the Multi-task model achieves state-of-the-art (SOTA) results in the Hotel domain of the VLSP 2018 ABSA dataset, with the F1-score being 82.55% for ACD and 77.32% for ACD with SPC. For the Restaurant domain, our Multi-task model also achieved SOTA in the ACD with SPC task by an F1-score of 71.55% and 83.29% for the ACD.","PeriodicalId":178279,"journal":{"name":"2022 IEEE International Conference on Cybernetics and Computational Intelligence (CyberneticsCom)","volume":"10 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-06-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132355927","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 : 2022-06-16DOI: 10.1109/CyberneticsCom55287.2022.9865436
Aman Doherey, Akansha Singh, Arun Kumar
An Network Intrusion Detection System can be perceived as a device, either software or hardware which is utilized to screen the organization for suspicious action or policy violation. In this era of digitization where everyone is using computers for all types of communications- personal, political, financial, etc., it becomes necessary to ensure that the medium of the communication is secure or not. Because nowadays every small scale enterprise, big companies, even personal households are having their own server. The new technologies are based on the concept of networking. So, an intrusion in such networks can cause bid risks like data breach financial risk or malfunctioning of the devices connected in that network. It might be possible for small networks to be checked manually because the total connection in such networks is less, but when it comes to the big networks where a lot of connections are sending and receiving requests, it is near to impossible for someone to check all the connections manually. In this paper dense neural network are used for detecting the network intrusion and NSL-KDD dataset are used to test the model. The proposed model achieved 98.29% accuracy.
{"title":"Intrusion Detection using Dense Neural Network in Network System","authors":"Aman Doherey, Akansha Singh, Arun Kumar","doi":"10.1109/CyberneticsCom55287.2022.9865436","DOIUrl":"https://doi.org/10.1109/CyberneticsCom55287.2022.9865436","url":null,"abstract":"An Network Intrusion Detection System can be perceived as a device, either software or hardware which is utilized to screen the organization for suspicious action or policy violation. In this era of digitization where everyone is using computers for all types of communications- personal, political, financial, etc., it becomes necessary to ensure that the medium of the communication is secure or not. Because nowadays every small scale enterprise, big companies, even personal households are having their own server. The new technologies are based on the concept of networking. So, an intrusion in such networks can cause bid risks like data breach financial risk or malfunctioning of the devices connected in that network. It might be possible for small networks to be checked manually because the total connection in such networks is less, but when it comes to the big networks where a lot of connections are sending and receiving requests, it is near to impossible for someone to check all the connections manually. In this paper dense neural network are used for detecting the network intrusion and NSL-KDD dataset are used to test the model. The proposed model achieved 98.29% accuracy.","PeriodicalId":178279,"journal":{"name":"2022 IEEE International Conference on Cybernetics and Computational Intelligence (CyberneticsCom)","volume":"30 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-06-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130793426","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：