Show simple item record

dc.contributor.authorMaksoud, Mohamed Abdel
dc.contributor.authorPandey, Gaurav
dc.contributor.authorWang, Shuaiqiang
dc.date.accessioned2019-12-18T07:48:00Z
dc.date.available2019-12-18T07:48:00Z
dc.date.issued2017fi
dc.identifier.citationMaksoud, M. A., Pandey, G., & Wang, S. (2017). CitySearcher: A City Search Engine For Interests. In <em>SIGIR '17 : Proceedings of the 40th International ACM SIGIR Conference on Research and Development in Information Retrieval</em> (pp. 1141-1144). New York: ACM. <a href="https://doi.org/10.1145/3077136.3080742">doi:10.1145/3077136.3080742</a>fi
dc.identifier.otherTUTKAID_75266
dc.identifier.urihttps://jyx.jyu.fi/handle/123456789/66912
dc.description.abstractWe introduce CitySearcher, a vertical search engine that searches for cities when queried for an interest. Generally in search engines, utilization of semantics between words is favorable for performance improvement. Even though ambiguous query words have multiple semantic meanings, search engines can return diversified results to satisfy different users' information needs. But for CitySearcher, mismatched semantic relationships can lead to extremely unsatisfactory results. For example, the city Sale would incorrectly rank high for the interest shopping because of semantic interpretations of the words. Thus in our system, the main challenge is to eliminate the mismatched semantic relationships resulting from the side effect of the semantic models. In the previous case, we aim to ignore the semantics of a city's name which is not indicative of the city's characteristics. In CitySearcher, we use word2vec, a very popular word embedding technique to estimate the semantics of the words and create the initial ranks of the cities. To reduce the effect of the mismatched semantic relationships, we generate a set of features for learning based on a novel clustering-based method. With the generated features, we then utilize learning to rank algorithms to rerank the cities for return. We use the English version of Wikivoyage dataset for evaluation of our system, where we sample a very small dataset for training. Experimental results demonstrate the performance gain of our system over various standard retrieval techniques.fi
dc.format.extent1440
dc.format.mimetypeapplication/pdf
dc.language.isoeng
dc.publisherACM
dc.relation.ispartofSIGIR '17 : Proceedings of the 40th International ACM SIGIR Conference on Research and Development in Information Retrieval
dc.rightsIn Copyright
dc.subject.otherhakuohjelmatfi
dc.subject.othersuosittelujärjestelmätfi
dc.subject.othersemanttinen webfi
dc.subject.otherkaupungitfi
dc.subject.othersearch enginesfi
dc.subject.otherrecommender systemsfi
dc.subject.othersemantic webfi
dc.subject.othertowns and citiesfi
dc.titleCitySearcher: A City Search Engine For Interestsfi
dc.typeconferenceObject
dc.identifier.urnURN:NBN:fi:jyu-201912135251
dc.contributor.laitosInformaatioteknologian tiedekuntafi
dc.contributor.laitosFaculty of Information Technologyen
dc.contributor.oppiaineTietojenkäsittelytiede
dc.type.urihttp://purl.org/eprint/type/ConferencePaper
dc.date.updated2019-12-13T10:15:10Z
dc.relation.isbn978-1-4503-5022-8
dc.description.reviewstatuspeerReviewed
dc.format.pagerange1141-1144
dc.type.versionacceptedVersion
dc.rights.copyright© 2017 ACM
dc.rights.accesslevelopenAccessfi
dc.relation.conferenceInternational ACM SIGIR Conference on Research and Development in Information Retrieval
dc.format.contentfulltext
dc.rights.urlhttp://rightsstatements.org/page/InC/1.0/?language=en
dc.relation.doi10.1145/3077136.3080742


Files in this item

Thumbnail

This item appears in the following Collection(s)

Show simple item record

In Copyright
Except where otherwise noted, this item's license is described as In Copyright