Matches in ScholarlyData for { ?s ?p ?o. }
- 92 title "Graph Theoretical Framework for Simultaneously Integrating Visual and Textual Features for Efficient Web Image Clustering".
- authorList type List.
- authorList hasFirstItem item-1.
- authorList hasItem item-1.
- authorList hasItem item-2.
- authorList hasLastItem item-2.
- item-1 type ListItem.
- item-1 hasContent manjeet-rege.
- item-1 next item-2.
- item-2 type ListItem.
- item-2 hasContent ming-dong.
- item-2 previous item-1.
- 956 creator ariel-fuxman.
- 956 creator kannan-achan.
- 956 creator panayiotis-tsaparas.
- 956 creator rakesh-agrawal.
- 956 type InProceedings.
- 956 label "Using the Wisdom of the Crowds for Keyword Generation".
- 956 sameAs 956.
- 956 abstract "In the sponsored search model, search engines are paid by businesses that are interested in displaying ads for their site alongside the search results. Businesses bid for different keywords, and their ad is displayed when the keyword is queried to the search engine. An important problem in this process is \emph{keyword generation}: given a business that is interested in being advertised with respect to a specific concept, suggest keywords that are related to this concept. We address this problem by making use of the query logs of the search engine. We identify queries related to a concept by exploiting the associations between queries and URLs as they are captured by the user's clicks. These queries form good keyword suggestions since they capture the ``wisdom of the crowd'' as to what is related to a site, and they can be directly monetized. We formulate the problem as a semi-supervised learning problem, and we propose two different algorithms within the Markov Random Field model. We perform extensive experiments with real query logs and we demonstrate that our algorithms can scale for large query logs, and produce meaningful results.".
- 956 hasAuthorList authorList.
- 956 hasTopic World_Wide_Web.
- 956 isPartOf proceedings.
- 956 keyword "click logs".
- 956 keyword "keyword generation".
- 956 keyword "markov random fields".
- 956 keyword "random walks".
- 956 title "Using the Wisdom of the Crowds for Keyword Generation".
- 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 ariel-fuxman.
- item-1 next item-2.
- item-2 type ListItem.
- item-2 hasContent panayiotis-tsaparas.
- item-2 next item-3.
- item-2 previous item-1.
- item-3 type ListItem.
- item-3 hasContent kannan-achan.
- item-3 next item-4.
- item-3 previous item-2.
- item-4 type ListItem.
- item-4 hasContent rakesh-agrawal.
- item-4 previous item-3.
- 1 type InProceedings.
- 1 label "A Dynamic Bayesian Network Click Model for Web Search Ranking".
- 1 sameAs 1.
- 1 abstract "As with any application of machine learning, web search ranking requires labeled data. The labels usually come in the form of relevance assessments made by editors. Click logs can also provide an important source of implicit feedback and can be used as a cheap proxy for editorial labels. The main difficulty however comes from the so called position bias — urls appearing in lower positions are less likely to be clicked even if they are relevant. In this paper, we propose a Dynamic Bayesian Network which aims at providing us with unbiased estimation of the relevance from the click logs. Experiments show that the proposed click model outperforms other existing click models in predicting both click-through rate and relevance.".
- 1 hasAuthorList authorList.
- 1 isPartOf proceedings.
- 1 keyword "Data Mining".
- 1 title "A Dynamic Bayesian Network Click Model for Web Search Ranking".
- authorList type List.
- authorList hasFirstItem item-1.
- authorList hasItem item-1.
- authorList hasItem item-2.
- authorList hasLastItem item-2.
- item-1 type ListItem.
- item-1 hasContent olivier-chapelle.
- item-1 next item-2.
- item-2 type ListItem.
- item-2 hasContent ya-zhang.
- item-2 previous item-1.
- 10 type InProceedings.
- 10 label "Latent Space Domain Transfer between High Dimensional Overlapping Distributions".
- 10 sameAs 10.
- 10 abstract "Transferring knowledge from one domain to another is challenging due to a number of reasons. Since both conditional and marginal distribution of the training data and test data are non-identical, model trained in one domain, when directly applied to a different domain, is usually low in accuracy. For many applications with large feature sets, such as text document, sequence data, medical data, image data of different resolutions, etc. two domains usually do not contain exactly the same features, thus introducing large numbers of "missing values" when considered over the union of features from both domains. In other words, its marginal distributions are at most overlapping. In the same time, these problems are usually high dimensional, such as, several thousands of features. Thus, the combination of high dimensionality and missing values make the relationship in conditional probabilities between two domains hard to measure and model. To address these challenges, we propose a framework that first brings the marginal distributions of two domains closer by "filling up" those missing values of disjoint features. Afterwards, it looks for those comparable sub-structures in the "latent-space" as mapped from the expanded feature vector, where both marginal and conditional distribution are similar. With these sub-structures in latent space, the proposed approach then find common concepts that are transferable across domains with high probability. During prediction, unlabeled instances are treated as "queries", the mostly related labeled instances from outdomain are retrieved, and the classification is made by weighted voting using retrieved out-domain examples. We formally show that importing feature values across domains and latentsemantic index can jointly make the distributions of two related domains easier to measure than in original feature space, the nearest neighbor method employed to retrieve related out domain examples is bounded in error when predicting in-domain examples. Software and datasets are available for download.".
- 10 hasAuthorList authorList.
- 10 isPartOf proceedings.
- 10 keyword "Data Mining".
- 10 title "Latent Space Domain Transfer between High Dimensional Overlapping Distributions".
- 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 hasLastItem item-5.
- item-1 type ListItem.
- item-1 hasContent sihong-xie.
- item-1 next item-2.
- item-2 type ListItem.
- item-2 hasContent wei-fan.
- item-2 next item-3.
- item-2 previous item-1.
- item-3 type ListItem.
- item-3 hasContent jing-peng.
- item-3 next item-4.
- item-3 previous item-2.
- item-4 type ListItem.
- item-4 hasContent olivier-verscheure.
- item-4 next item-5.
- item-4 previous item-3.
- item-5 type ListItem.