{"title":"基于神经网络的维基百科文章检索","authors":"F. Al-akashi","doi":"10.4018/ijssci.2019070102","DOIUrl":null,"url":null,"abstract":"In this article, we propose a neural network model to create a Wikipedia article summarization for each query to allow users to find summary of the topic without going through the whole content in the article. Often, Wikipedia returns the articles related to a search query that makes obvious finding the relevant topic for the user. Text summarization is generated by extracting all those important sentences that are most significant in its topics and have a strong match in its content. Experimentally, each sentence in the article content is encoded as a set of features and presented as an input to the network. The proposed neural network is trained using a set of randomly selected typical articles from Wikipedia. The network output is then used to predict the sentences as a summary of content from the searched query. The results showed that the proposed approach is robust and efficient at finding relevant summaries for most searched queries. Evaluation of the proposal yields accuracy scores of 0.10317 in ROUGE-N and 0.13998 in ROUGE–L.","PeriodicalId":432255,"journal":{"name":"Int. J. Softw. Sci. Comput. Intell.","volume":"42 1","pages":"0"},"PeriodicalIF":0.0000,"publicationDate":"2019-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"2","resultStr":"{\"title\":\"Abstract Retrieval over Wikipedia Articles Using Neural Network\",\"authors\":\"F. Al-akashi\",\"doi\":\"10.4018/ijssci.2019070102\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"In this article, we propose a neural network model to create a Wikipedia article summarization for each query to allow users to find summary of the topic without going through the whole content in the article. Often, Wikipedia returns the articles related to a search query that makes obvious finding the relevant topic for the user. Text summarization is generated by extracting all those important sentences that are most significant in its topics and have a strong match in its content. Experimentally, each sentence in the article content is encoded as a set of features and presented as an input to the network. The proposed neural network is trained using a set of randomly selected typical articles from Wikipedia. The network output is then used to predict the sentences as a summary of content from the searched query. The results showed that the proposed approach is robust and efficient at finding relevant summaries for most searched queries. Evaluation of the proposal yields accuracy scores of 0.10317 in ROUGE-N and 0.13998 in ROUGE–L.\",\"PeriodicalId\":432255,\"journal\":{\"name\":\"Int. J. Softw. Sci. Comput. Intell.\",\"volume\":\"42 1\",\"pages\":\"0\"},\"PeriodicalIF\":0.0000,\"publicationDate\":\"2019-07-01\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"2\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"Int. J. Softw. Sci. Comput. Intell.\",\"FirstCategoryId\":\"1085\",\"ListUrlMain\":\"https://doi.org/10.4018/ijssci.2019070102\",\"RegionNum\":0,\"RegionCategory\":null,\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"\",\"JCRName\":\"\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"Int. J. Softw. Sci. Comput. Intell.","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.4018/ijssci.2019070102","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
Abstract Retrieval over Wikipedia Articles Using Neural Network
In this article, we propose a neural network model to create a Wikipedia article summarization for each query to allow users to find summary of the topic without going through the whole content in the article. Often, Wikipedia returns the articles related to a search query that makes obvious finding the relevant topic for the user. Text summarization is generated by extracting all those important sentences that are most significant in its topics and have a strong match in its content. Experimentally, each sentence in the article content is encoded as a set of features and presented as an input to the network. The proposed neural network is trained using a set of randomly selected typical articles from Wikipedia. The network output is then used to predict the sentences as a summary of content from the searched query. The results showed that the proposed approach is robust and efficient at finding relevant summaries for most searched queries. Evaluation of the proposal yields accuracy scores of 0.10317 in ROUGE-N and 0.13998 in ROUGE–L.