Matches in ScholarlyData for { ?s ?p ?o. }
- 77 abstract "Recommending related news articles aims to engage with users afterthey read current ones and can improve user retention for newsproviders. Most of previous works on news relatedness focus on thearticle texts. In this paper, we study the benefit ofuser-generated comments on modeling news relatedness. Commentscontain rich text information which is provided by commenters andrated by readers with thumb-up or thumb-down, but the quality ofindividual comments varies widely. We compare different ways ofcapturing relatedness by leveraging both text and user interactioninformation in comments. Our evaluation based on an editorial dataset demonstrates that the text information in comments is veryeffective to model relatedness while community rating is quitepredictive of the comment quality.".
- 77 hasAuthorList authorList.
- 77 isPartOf proceedings.
- 77 isPartOf proceedings.
- 77 keyword "Community rating".
- 77 keyword "News Relatedness".
- 77 keyword "User comments".
- 77 title "Model News Relatedness through User Comments".
- authorList type List.
- authorList hasFirstItem item-1.
- authorList hasItem item-1.
- authorList hasItem item-2.
- authorList hasItem item-3.
- authorList hasItem item-4.
- authorList hasLastItem item-4.
- item-1 type ListItem.
- item-1 hasContent xuanhui-wang.
- item-1 next item-2.
- item-2 type ListItem.
- item-2 hasContent jiang-bian.
- item-2 next item-3.
- item-2 previous item-1.
- item-3 type ListItem.
- item-3 hasContent yi-chang.
- item-3 next item-4.
- item-3 previous item-2.
- item-4 type ListItem.
- item-4 hasContent belle-tseng.
- item-4 previous item-3.
- 82 creator eva-zangerle.
- 82 creator guenther-specht.
- 82 creator martin-buergler.
- 82 creator wolfgang-gassler.
- 82 type InProceedings.
- 82 label "SnoopyTagging: Recommending Contextualized Tags to Increase the Quality and Quantity of Meta-Information".
- 82 sameAs 82.
- 82 abstract "Current mass-collaboration platforms use tags to annotate and categorize resources enabling effective search capabilities. However, as tags are freely chosen keywords, the resulting tag vocabulary is very heterogeneous. Another shortcoming of simple tags is that they do not allow for a specification of context to create meaningful metadata. In this paper we present the SnoopyTagging approach which supports the user in the process of creating contextualized tags while at the same time decreasing the heterogeneity of the tag vocabulary by facilitating intelligent self-learning recommendation algorithms.".
- 82 hasAuthorList authorList.
- 82 isPartOf proceedings.
- 82 isPartOf proceedings.
- 82 keyword "Heterogeneity".
- 82 keyword "Recommender Systems".
- 82 keyword "Structure".
- 82 keyword "Tagging".
- 82 keyword "Tags".
- 82 title "SnoopyTagging: Recommending Contextualized Tags to Increase the Quality and Quantity of Meta-Information".
- authorList type List.
- authorList hasFirstItem item-1.
- authorList hasItem item-1.
- authorList hasItem item-2.
- authorList hasItem item-3.
- authorList hasItem item-4.
- authorList hasLastItem item-4.
- item-1 type ListItem.
- item-1 hasContent wolfgang-gassler.
- item-1 next item-2.
- item-2 type ListItem.
- item-2 hasContent eva-zangerle.
- item-2 next item-3.
- item-2 previous item-1.
- item-3 type ListItem.
- item-3 hasContent martin-buergler.
- item-3 next item-4.
- item-3 previous item-2.
- item-4 type ListItem.
- item-4 hasContent guenther-specht.
- item-4 previous item-3.
- 85 creator deepak-raj-murugaian.
- 85 creator geetha-manjunath.
- 85 creator koushik-sinha.
- 85 creator pooja-a.
- 85 creator raveesh-sharma.
- 85 creator viswanath-gangavaram.
- 85 type InProceedings.
- 85 label "Enabling Accent Resilient Speech based Information Retrieval".
- 85 sameAs 85.
- 85 abstract "Voice interfaces to browsers and mobile applications are becoming popular as typing with touch screens is cumbersome. The main issue of practical speech based interfaces is how to overcome speech recognition errors. This problem is more severe when the users are non-native speakers of English due to differences in pronunciations. In this paper, we describe a novel, intelligent speech interface design approach for IR tasks that is significantly robust to accent variations. Our solution uses phonemic similarity based word spreading and semantic information based filtering to boost the accuracy of any ASR. We evaluated our solution with Google Voice as the ASR for a web question-answering system developed in-house and the results are very encouraging.".
- 85 hasAuthorList authorList.
- 85 isPartOf proceedings.
- 85 isPartOf proceedings.
- 85 keyword "Phonemic spreading".
- 85 keyword "Question answering".
- 85 keyword "Semantic feedback".
- 85 keyword "Speech based information retrieval".
- 85 title "Enabling Accent Resilient Speech based Information Retrieval".
- authorList type List.
- authorList hasFirstItem item-1.
- authorList hasItem item-1.
- authorList hasItem item-2.
- authorList hasItem item-3.
- authorList hasItem item-4.
- authorList hasItem item-5.
- authorList hasItem item-6.
- authorList hasLastItem item-6.
- item-1 type ListItem.
- item-1 hasContent koushik-sinha.
- item-1 next item-2.
- item-2 type ListItem.
- item-2 hasContent geetha-manjunath.
- item-2 next item-3.