A semantic content based recommendation system for cross-lingual news

2017 IEEE International Conference on Imaging, Vision & Pattern Recognition (icIVPR) Pub Date : 1900-01-01 DOI:10.1109/ICIVPR.2017.7890880

Syeda Nyma Ferdous, M. Ali

{"title":"A semantic content based recommendation system for cross-lingual news","authors":"Syeda Nyma Ferdous, M. Ali","doi":"10.1109/ICIVPR.2017.7890880","DOIUrl":null,"url":null,"abstract":"News articles in web narrate important events happening worldwide. These articles are not only written in English, but also in different languages for different native people. In this paper, we propose an approach for an automated Bengali-English semantic recommender system based on ontology by analyzing news domain. News ontology is designed automatically by using information extraction techniques. Both the news title and news body are considered separately in the ontology creation process. First, important information from news is extracted and ontology is created from the source language document. Then, ontology is created from target language document following similar technique. Next, ontology matching is performed between the translated source ontology and target English Ontology. Matching can also be done with synonymous documents. A matching factor is calculated which can be taken as the semantic similarity measure between the cross-lingual documents. Recommendation of news items is done based on this matching factor. The experiment study verifies the proposed method adopted by us.","PeriodicalId":126745,"journal":{"name":"2017 IEEE International Conference on Imaging, Vision & Pattern Recognition (icIVPR)","volume":"51 1","pages":"0"},"PeriodicalIF":0.0000,"publicationDate":"1900-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"9","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"2017 IEEE International Conference on Imaging, Vision & Pattern Recognition (icIVPR)","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1109/ICIVPR.2017.7890880","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}

引用次数: 9

Abstract

News articles in web narrate important events happening worldwide. These articles are not only written in English, but also in different languages for different native people. In this paper, we propose an approach for an automated Bengali-English semantic recommender system based on ontology by analyzing news domain. News ontology is designed automatically by using information extraction techniques. Both the news title and news body are considered separately in the ontology creation process. First, important information from news is extracted and ontology is created from the source language document. Then, ontology is created from target language document following similar technique. Next, ontology matching is performed between the translated source ontology and target English Ontology. Matching can also be done with synonymous documents. A matching factor is calculated which can be taken as the semantic similarity measure between the cross-lingual documents. Recommendation of news items is done based on this matching factor. The experiment study verifies the proposed method adopted by us.

查看原文本刊更多论文

基于语义内容的跨语言新闻推荐系统

网络新闻报道世界范围内发生的重要事件。这些文章不仅是用英语写的，而且是用不同的语言为不同的当地人写的。本文通过对新闻领域的分析，提出了一种基于本体的孟加拉语-英语语义自动推荐系统。利用信息抽取技术自动设计新闻本体。在本体的创建过程中，新闻标题和新闻主体是分开考虑的。首先，从新闻中提取重要信息，并从源语言文档中创建本体。然后，采用类似的技术从目标语言文档中创建本体。然后，在翻译后的源本体和目标英语本体之间进行本体匹配。也可以对同义文档进行匹配。计算出一个匹配因子，作为跨语言文档之间的语义相似度度量。新闻项目的推荐基于这个匹配因子。实验研究验证了我们所采用的方法。

本文章由计算机程序翻译，如有差异，请以英文原文为准。

求助全文

约1分钟内获得全文求助全文

来源期刊

2017 IEEE International Conference on Imaging, Vision & Pattern Recognition (icIVPR)

自引率

0.00%

发文量