Multi-lingual text processing is important for content-based and hybrid recommender systems. It helps recommender systems extract content information from broader sources. It also enables systems to recommend items in a user's native language. We propose a cross-lingual keyword recommendation method, which is built on an extended latent Dirichlet allocation model, for extracting latent features from parallel corpora. With this model, the proposed method can recommend keywords from text written in different languages. We evaluate the proposed method using a cross-lingual bibliographic database that contains both English and Japanese abstracts and keywords and show that the proposed method can recommend keywords from abstracts in a cross-lingual environment with almost the same accuracy as in a monolingual environment.
{"title":"Cross-lingual keyword recommendation using latent topics","authors":"A. Takasu","doi":"10.1145/1869446.1869454","DOIUrl":"https://doi.org/10.1145/1869446.1869454","url":null,"abstract":"Multi-lingual text processing is important for content-based and hybrid recommender systems. It helps recommender systems extract content information from broader sources. It also enables systems to recommend items in a user's native language. We propose a cross-lingual keyword recommendation method, which is built on an extended latent Dirichlet allocation model, for extracting latent features from parallel corpora. With this model, the proposed method can recommend keywords from text written in different languages. We evaluate the proposed method using a cross-lingual bibliographic database that contains both English and Japanese abstracts and keywords and show that the proposed method can recommend keywords from abstracts in a cross-lingual environment with almost the same accuracy as in a monolingual environment.","PeriodicalId":258506,"journal":{"name":"HetRec '10","volume":"50 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2010-09-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127121600","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}
In today's mobile applications, it becomes more and more important to have a broader view on knowledge about a certain domain when generating contextual and semantic recommendations. Data that provides additional and useful information to the traditional User x Item representation, such as taxonomies, implicit and indirect knowledge about a user's preferences or location information can immensely enhance the quality of recommendations. For this purpose, the generic recommender system of Fraunhofer Institute FOKUS, the SMART Recommendations Engine, has been extended by the SMART Ontology Extension and the Proximity Filter, which enable the recommender to use domain knowledge included in semantic ontologies and contextual information in the recommendation process in order to generate much more precise recommendations. The functionality of the extensions are demonstrated in the scope of a food purchase scenario.
在今天的移动应用程序中，在生成上下文和语义推荐时，对特定领域的知识有更广泛的了解变得越来越重要。为传统的User x Item表示提供额外有用信息的数据，如分类法、关于用户偏好或位置信息的隐式和间接知识，可以极大地提高推荐的质量。为此，Fraunhofer Institute FOKUS的通用推荐系统SMART推荐引擎被SMART本体扩展(SMART Ontology Extension)和邻近过滤器(Proximity Filter)扩展，使推荐器能够在推荐过程中使用包含在语义本体和上下文信息中的领域知识，以生成更精确的推荐。扩展的功能在食品购买场景的范围内进行了演示。
{"title":"Targeting more relevant, contextual recommendations by exploiting domain knowledge","authors":"A. Uzun, C. Räck, Fabian Steinert","doi":"10.1145/1869446.1869455","DOIUrl":"https://doi.org/10.1145/1869446.1869455","url":null,"abstract":"In today's mobile applications, it becomes more and more important to have a broader view on knowledge about a certain domain when generating contextual and semantic recommendations. Data that provides additional and useful information to the traditional User x Item representation, such as taxonomies, implicit and indirect knowledge about a user's preferences or location information can immensely enhance the quality of recommendations. For this purpose, the generic recommender system of Fraunhofer Institute FOKUS, the SMART Recommendations Engine, has been extended by the SMART Ontology Extension and the Proximity Filter, which enable the recommender to use domain knowledge included in semantic ontologies and contextual information in the recommendation process in order to generate much more precise recommendations. The functionality of the extensions are demonstrated in the scope of a food purchase scenario.","PeriodicalId":258506,"journal":{"name":"HetRec '10","volume":"8 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2010-09-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129166091","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：