Matches in ScholarlyData for { ?s ?p ?o. }
- item-2 previous item-1.
- 71 creator abhinav-mishra.
- 71 creator rajeev-rastogi.
- 71 type InProceedings.
- 71 label "Semi-Supervised Correction of Biased Comment Ratings".
- 71 sameAs 71.
- 71 abstract "In many instances, offensive comments on the internet attract a disproportionate number of positive ratings from highly biased users. This results in an undesirable scenario where these offensive comments are the top rated ones. In this paper, we develop semi-supervised learning techniques to correct the bias in user ratings of comments. Our scheme uses a small number of comment labels in conjunction with user rating information to iteratively compute user bias and true ratings for unlabeled comments. We show that the running time of each iteration is linear in the number of ratings, and the system converges to a unique fixed point. To select the comments to label, we devise an active learning algorithm based on Empirical risk minimization. Our active learning method incrementally updates the risk for neighboring comments each time a comment is labeled, and thus can easily scale to large comment datasets. On real-life comments from Yahoo! News, our semi-supervised and active learning algorithms achieve higher accuracy than simple baselines, with few labeled examples.".
- 71 hasAuthorList authorList.
- 71 isPartOf proceedings.
- 71 keyword "Active Learning".
- 71 keyword "Bias Correction".
- 71 keyword "Iterative Techniques".
- 71 keyword "Semi-supervised Learning".
- 71 title "Semi-Supervised Correction of Biased Comment Ratings".
- 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 abhinav-mishra.
- item-1 next item-2.
- item-2 type ListItem.
- item-2 hasContent rajeev-rastogi.
- item-2 previous item-1.
- 715 creator natalie-aizenberg.
- 715 creator oren-somekh.
- 715 creator yehuda-koren.
- 715 type InProceedings.
- 715 label "Build Your Own Music Recommender by Modeling Internet Radio Streams".
- 715 sameAs 715.
- 715 abstract "In the Internet music scene, where recommendation technology is key for navigating huge collections, large market players enjoy a considerable advantage. Accessing a wider pool of user feedback leads to an increasingly more accurate analysis of user tastes, effectively creating a ``rich get richer'' effect. This work aims at significantly lowering the entry barrier for creating music recommenders, through a paradigm coupling a public data source and a new collaborative filtering (CF) model. We claim that Internet radio stations form a readily available resource of abundant fresh human signals on music through their playlists, which are essentially cohesive sets of related tracks. In a way, our models rely on the knowledge of a diverse group of experts in lieu of the commonly used wisdom of crowds. Over several weeks, we aggregated publicly available playlists of thousands of Internet radio stations, resulting in a dataset encompassing millions of plays, and hundreds of thousands of tracks and artists. This provides the large scale ground data necessary to mitigate the cold start problem of new items at both mature and emerging services. Furthermore, we developed a new probabilistic CF model, tailored to the Internet radio resource. The success of the model was empirically validated on the collected dataset. Moreover, we tested the model at a cross-source transfer learning manner - the same model trained on the Internet radio data was used to predict behavior of Yahoo! Music users. This demonstrates the ability to tap the Internet radio signals in other music recommendation setups. Based on encouraging empirical results, our hope is that the proposed paradigm will make quality music recommendation accessible to all interested parties in the community.".
- 715 hasAuthorList authorList.
- 715 isPartOf proceedings.
- 715 keyword "collaborative filtering".
- 715 keyword "cross source learning".
- 715 keyword "internet radio stations".
- 715 keyword "music recommendation".
- 715 keyword "playlist generation".
- 715 title "Build Your Own Music Recommender by Modeling Internet Radio Streams".
- authorList type List.
- authorList hasFirstItem item-1.
- authorList hasItem item-1.
- authorList hasItem item-2.
- authorList hasItem item-3.
- authorList hasLastItem item-3.
- item-1 type ListItem.
- item-1 hasContent natalie-aizenberg.
- item-1 next item-2.
- item-2 type ListItem.
- item-2 hasContent yehuda-koren.
- item-2 next item-3.
- item-2 previous item-1.
- item-3 type ListItem.
- item-3 hasContent oren-somekh.
- item-3 previous item-2.
- 734 creator jie-tang.
- 734 creator juanzi-li.
- 734 creator zhichun-wang.
- 734 creator zhigang-wang.
- 734 type InProceedings.
- 734 label "Crosslingual Knowledge Linking Across Wiki Knowledge Bases".
- 734 sameAs 734.
- 734 abstract "As a large scale cross-lingual knowledge base, Wikipedia has promoted the knowledge sharing in different languages on the Web. Cross-lingual links in Wikipedia connect equivalent articles written in different languages, which have been widely exploited in various applications. However, the available articles in different languages are quite unbalanced. For example, up to now the articles in English Wikipedia has reached 3.8 million, while the available articles in Chinese Wikipedia are less than half million. On the other hand, there are more than 3.9 million articles in Baidu Baike and Hudong, another two popular encyclopedias in Chinese. Therefore, finding cross-lingual links between Wikipedia and these Wiki knowledge bases can largely enrich the cross-lingual knowledge. In this paper, we formalize the cross-lingual knowledge linking problem into a linkage factor graph model. Features are defined according to some interesting observations. Experiments on the Wikipedia data set show that our approach can achieve high precision 85.80% with a recall of 88.10%. In addition, we find 202,141 new cross-lingual links between English Wikipedia and Baidu Baike using the proposed approach, which are almost as many as existing ones in Wikipedia.".
- 734 hasAuthorList authorList.
- 734 isPartOf proceedings.
- 734 keyword "Cross-lingual".
- 734 keyword "Knowledge Linking".
- 734 keyword "Knowledge sharing".
- 734 keyword "Wiki knowledge base".
- 734 title "Crosslingual Knowledge Linking Across Wiki Knowledge Bases".
- 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 zhichun-wang.
- item-1 next item-2.
- item-2 type ListItem.
- item-2 hasContent juanzi-li.
- item-2 next item-3.
- item-2 previous item-1.
- item-3 type ListItem.
- item-3 hasContent zhigang-wang.
- item-3 next item-4.
- item-3 previous item-2.
- item-4 type ListItem.
- item-4 hasContent jie-tang.
- item-4 previous item-3.
- 743 creator jinpeng-huai.
- 743 creator shuai-ma.
- 743 creator tianyu-wo.
- 743 creator yang-cao.
- 743 type InProceedings.
- 743 label "Distributed Graph Pattern Matching".
- 743 sameAs 743.
- 743 abstract "Graph pattern matching is often defined in terms of subgraph isomorphism, which is \NP-complete, and is often too restrictive to catch sensible matches in emerging applications. Graph simulation has been adopted for pattern matching to reduce the complexity and capture the need of novel applications. In light of the rapid development of the Web and social networks, data is typically distributed over multiple machines. Hence a natural question raised is how to evaluate graph simulation on distributed data. To our knowledge, no such distributed algorithms are in place yet. This paper settles this question by providing evaluation algorithms and optimizations for graph simulation in a distributed setting. (1) We study the impacts of components and data locality on the evaluation of graph simulation. (2) We give an analysis of a large class of distributed algorithms for graph simulation captured by a message-passing model. We also identify three complexity measures: visit times, makespan and data shipment, for the analyses of these distributed algorithms, and show that these measures are controversial with each other. (3) We propose distributed algorithms and optimization techniques which exploit the properties of graph simulation and the analyses of distributed algorithms. (4) We experimentally verify the effectiveness and efficiency of these algorithms, using both real-life and synthetic data.".