Opinion Mining and Sentiment Analysis in Natural Language Processing (NLP) are challenging, as they require deep understanding. Understanding involves methods that could differentiate between the facts of explicit and implicit, regular and irregular, syntactical and semantic language rules. Researches oriented towards Natural Language Processing and Sentiment Analysis have many unresolved problems like co-reference resolution, negation handling, anaphora resolution, named-entity recognition, and word-sense disambiguation. This paper is proposed to develop an Optimized Partial Ancestral Graph (O-PAG) which is capable of mining patterns in human interactions and compare it with an existing tree based pattern mining approach. The experimental results are exposed to number of frequent interactions made and execution time. Results indicate that the overall performance can reach considerable improvements on using O-PAG approach.
{"title":"COMPARATIVE ANALYSIS OF HUMAN INTERACTION PATTERN MINING APPROACHES","authors":"S. Uma, J. Suguna","doi":"10.21917/ijsc.2020.0293","DOIUrl":"https://doi.org/10.21917/ijsc.2020.0293","url":null,"abstract":"Opinion Mining and Sentiment Analysis in Natural Language Processing (NLP) are challenging, as they require deep understanding. Understanding involves methods that could differentiate between the facts of explicit and implicit, regular and irregular, syntactical and semantic language rules. Researches oriented towards Natural Language Processing and Sentiment Analysis have many unresolved problems like co-reference resolution, negation handling, anaphora resolution, named-entity recognition, and word-sense disambiguation. This paper is proposed to develop an Optimized Partial Ancestral Graph (O-PAG) which is capable of mining patterns in human interactions and compare it with an existing tree based pattern mining approach. The experimental results are exposed to number of frequent interactions made and execution time. Results indicate that the overall performance can reach considerable improvements on using O-PAG approach.","PeriodicalId":30616,"journal":{"name":"ICTACT Journal on Soft Computing","volume":"1 1","pages":""},"PeriodicalIF":0.0,"publicationDate":"2020-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"41361676","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 conversation agent acts as core interfaces between a system and user in answering users queries with proper responses. Question answering system acquires an important role in the information retrieval field. The deep learning approach enhances the accuracy in answering complex questions. As outcome, the user is receiving the precise answer instead of large document collections. The aim of this paper is to develop a model with deep learning approach for improving answer selection process which supports more relevant answer displaying by conversation agents. To achieve this, word2vector used for word representation and biLSTM attentive model is used for training, testing and disclosure play precise answer. Question type is identified using POS-tagger based Question Pattern analysis (T-QPA) model. The knowledgebase is created from the bench mark datasets bAbI Facebook (simple QA tasks), TREC QA, Yahoo! Answer, Insurance QA dataset. The proposed framework is built by embedding of questions and answers based on bidirectional long short-term memory (biLSTM) attentive models. The similarity between questions and answers has been measured by semantic and cosine similarity. The proposed model reduces the search gap in extracting among user queries and answer sentences in the education domain. The system results are evaluated with the standard metrics MAP, Top 1 accuracy, F1- Score for the answer selection.
{"title":"DEEP LEARNING APPROACHES FOR ANSWER SELECTION IN QUESTION ANSWERING SYSTEM FOR CONVERSATION AGENTS","authors":"K. Karpagam, K. Madusudanan, A. Saradha","doi":"10.21917/ijsc.2020.0289","DOIUrl":"https://doi.org/10.21917/ijsc.2020.0289","url":null,"abstract":"The conversation agent acts as core interfaces between a system and user in answering users queries with proper responses. Question answering system acquires an important role in the information retrieval field. The deep learning approach enhances the accuracy in answering complex questions. As outcome, the user is receiving the precise answer instead of large document collections. The aim of this paper is to develop a model with deep learning approach for improving answer selection process which supports more relevant answer displaying by conversation agents. To achieve this, word2vector used for word representation and biLSTM attentive model is used for training, testing and disclosure play precise answer. Question type is identified using POS-tagger based Question Pattern analysis (T-QPA) model. The knowledgebase is created from the bench mark datasets bAbI Facebook (simple QA tasks), TREC QA, Yahoo! Answer, Insurance QA dataset. The proposed framework is built by embedding of questions and answers based on bidirectional long short-term memory (biLSTM) attentive models. The similarity between questions and answers has been measured by semantic and cosine similarity. The proposed model reduces the search gap in extracting among user queries and answer sentences in the education domain. The system results are evaluated with the standard metrics MAP, Top 1 accuracy, F1- Score for the answer selection.","PeriodicalId":30616,"journal":{"name":"ICTACT Journal on Soft Computing","volume":" ","pages":""},"PeriodicalIF":0.0,"publicationDate":"2020-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"44934889","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}
Security is one of the major challenges in open network. There are so many types of attacks which follow fixed patterns or frequently change their patterns. It is difficult to find the malicious attack which does not have any fixed patterns. The Distributed Denial of Service (DDoS) attacks like Botnets are used to slow down the system performance. To address such problems Collaborative Network Security Management System (CNSMS) is proposed along with the association mining rule. CNSMS system is consists of collaborative Unified Threat Management (UTM), cloud based security centre and traffic prober. The traffic prober captures the internet traffic and given to the collaborative UTM. Traffic is analysed by the Collaborative UTM, to determine whether it contains any malicious attack or not. If any security event occurs, it will reports to the cloud based security centre. The security centre generates security rules based on association mining rule and distributes to the network. The cloud based security centre is used to store the huge amount of tragic, their logs and the security rule generated. The feedback is evaluated and the invalid rules are eliminated to improve the system efficiency.
{"title":"COLLABORATIVE NETWORK SECURITY MANAGEMENT SYSTEM BASED ON ASSOCIATION MINING RULE","authors":"Nisha Mariam Varughese","doi":"10.21917/IJSC.2014.0112","DOIUrl":"https://doi.org/10.21917/IJSC.2014.0112","url":null,"abstract":"Security is one of the major challenges in open network. There are so many types of attacks which follow fixed patterns or frequently change their patterns. It is difficult to find the malicious attack which does not have any fixed patterns. The Distributed Denial of Service (DDoS) attacks like Botnets are used to slow down the system performance. To address such problems Collaborative Network Security Management System (CNSMS) is proposed along with the association mining rule. CNSMS system is consists of collaborative Unified Threat Management (UTM), cloud based security centre and traffic prober. The traffic prober captures the internet traffic and given to the collaborative UTM. Traffic is analysed by the Collaborative UTM, to determine whether it contains any malicious attack or not. If any security event occurs, it will reports to the cloud based security centre. The security centre generates security rules based on association mining rule and distributes to the network. The cloud based security centre is used to store the huge amount of tragic, their logs and the security rule generated. The feedback is evaluated and the invalid rules are eliminated to improve the system efficiency.","PeriodicalId":30616,"journal":{"name":"ICTACT Journal on Soft Computing","volume":"4 1","pages":"787-790"},"PeriodicalIF":0.0,"publicationDate":"2014-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"68392189","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}
{"title":"OPINION MINING AND SENTIMENT CLASSIFICATION: A SURVEY","authors":"ChandraKala S., S. C.","doi":"10.21917/ijsc.2012.0065","DOIUrl":"https://doi.org/10.21917/ijsc.2012.0065","url":null,"abstract":"","PeriodicalId":30616,"journal":{"name":"ICTACT Journal on Soft Computing","volume":"29 1","pages":"420-427"},"PeriodicalIF":0.0,"publicationDate":"2012-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"68392100","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}
Data mining techniques used in many applications as there is an incredible growth in records and it is not feasible to find a solution manually. Amongst them, the medical records in data mining gains more popularity and have many missed values due to emergency cases or complicated situation etc. These missing values have a great influence in the desired output. The traditional mining procedure has to be enhanced to handle that between them and adjust the parameters to minimize the errors. The activation function in the neuron performs the non-linear transformation function making it capable to learn and perform more complex tasks. This function plays a vital role in the output process. This work focus on this function and made some enhancement by applying multi logit regression with Maximum A posteriori method in activation function to handle multi-class classification The proposed Enhanced Activation Function in Multi layer Perceptron is implemented in WEKA 3.9.6. and is compared with traditional MLP with suitable evaluation metrics.
{"title":"CATEGORIZATION OF LUNG CARCINOMA USING MULTILAYER PERCEPTRON IN OUTPUT LAYER","authors":"S. Karthigai, K. Sundaram","doi":"10.21917/ijsc.2020.0288","DOIUrl":"https://doi.org/10.21917/ijsc.2020.0288","url":null,"abstract":"Data mining techniques used in many applications as there is an incredible growth in records and it is not feasible to find a solution manually. Amongst them, the medical records in data mining gains more popularity and have many missed values due to emergency cases or complicated situation etc. These missing values have a great influence in the desired output. The traditional mining procedure has to be enhanced to handle that between them and adjust the parameters to minimize the errors. The activation function in the neuron performs the non-linear transformation function making it capable to learn and perform more complex tasks. This function plays a vital role in the output process. This work focus on this function and made some enhancement by applying multi logit regression with Maximum A posteriori method in activation function to handle multi-class classification The proposed Enhanced Activation Function in Multi layer Perceptron is implemented in WEKA 3.9.6. and is compared with traditional MLP with suitable evaluation metrics.","PeriodicalId":30616,"journal":{"name":"ICTACT Journal on Soft Computing","volume":"5 1","pages":""},"PeriodicalIF":0.0,"publicationDate":"1900-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"68392256","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：