Guangzhi Zhang, Tao Jiang, R. Bie, Xiaochun Liu, Zhichun Wang, Junyang Rao
{"title":"The Architecture of ProMe Instant Question Answering System","authors":"Guangzhi Zhang, Tao Jiang, R. Bie, Xiaochun Liu, Zhichun Wang, Junyang Rao","doi":"10.1109/CyberC.2013.46","DOIUrl":null,"url":null,"abstract":"An instant question answering system ProMe is proposed in this paper which sets automated question answering system as prototype and combines with the search engines and instant messenger. For any question queried by a user, ProMe looks for the answers in the flow of three methods. The first one is to match questions in FAQ database with TF-IDF (Term Frequency-Inverse Document Frequency) algorithm. If still not found, submit it to some search engines and get the answers by extracting information from the web pages returned by the search engine. If the answer is not found or not satisfied after evaluation, it will be sent to other users who are probably interested in it through instant messengers, and get the final answers. Experimental results show that ProMe greatly improves the effectiveness of the automated question answering systems. It can be applied for information searching to provide real-time and personalized information search services for mobile Internet users.","PeriodicalId":133756,"journal":{"name":"2013 International Conference on Cyber-Enabled Distributed Computing and Knowledge Discovery","volume":"38 1","pages":"0"},"PeriodicalIF":0.0000,"publicationDate":"2013-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"1","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"2013 International Conference on Cyber-Enabled Distributed Computing and Knowledge Discovery","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1109/CyberC.2013.46","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
引用次数: 1
Abstract
An instant question answering system ProMe is proposed in this paper which sets automated question answering system as prototype and combines with the search engines and instant messenger. For any question queried by a user, ProMe looks for the answers in the flow of three methods. The first one is to match questions in FAQ database with TF-IDF (Term Frequency-Inverse Document Frequency) algorithm. If still not found, submit it to some search engines and get the answers by extracting information from the web pages returned by the search engine. If the answer is not found or not satisfied after evaluation, it will be sent to other users who are probably interested in it through instant messengers, and get the final answers. Experimental results show that ProMe greatly improves the effectiveness of the automated question answering systems. It can be applied for information searching to provide real-time and personalized information search services for mobile Internet users.