Matches in ScholarlyData for { ?s ?p ?o. }
- 638 title "Video Suggestion and Discovery for YouTube: Taking Random Walks Through the View Graph".
- 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 hasItem item-7.
- authorList hasItem item-8.
- authorList hasLastItem item-8.
- item-1 type ListItem.
- item-1 hasContent shumeet-baluja.
- item-1 next item-2.
- item-2 type ListItem.
- item-2 hasContent rohan-seth.
- item-2 next item-3.
- item-2 previous item-1.
- item-3 type ListItem.
- item-3 hasContent sivakumar-d.
- item-3 next item-4.
- item-3 previous item-2.
- item-4 type ListItem.
- item-4 hasContent yushi-jing.
- item-4 next item-5.
- item-4 previous item-3.
- item-5 type ListItem.
- item-5 hasContent jay-yagnik.
- item-5 next item-6.
- item-5 previous item-4.
- item-6 type ListItem.
- item-6 hasContent shankar-kumar.
- item-6 next item-7.
- item-6 previous item-5.
- item-7 type ListItem.
- item-7 hasContent deepak-ravichandran.
- item-7 next item-8.
- item-7 previous item-6.
- item-8 type ListItem.
- item-8 hasContent mohamed-aly.
- item-8 previous item-7.
- 643 creator foad-hamidi.
- 643 creator kin-fun-li.
- 643 creator leo-spalteholz.
- 643 creator nigel-livingston.
- 643 type InProceedings.
- 643 label "KeySurf: A character controlled browser for people with physical disabilities".
- 643 sameAs 643.
- 643 abstract "For many users with a physical disability, using a computer mouse or other pointing device to navigate the web is cumbersome or impossible due to problems with pointing accuracy. At the same time, keyboard accessibility in major browsers is rudimentary, requiring many key presses to select links or other elements. We present KeySurf, our character controlled web navigation system which addresses this situation by presenting an interface which allows a user to activate any web page element with only two or three keystrokes. Through an implementation of a user centric incremental search algorithm, elements are matched according to user expectation as characters are entered into the interface. We show how our interface can also be integrated with a speech recognition input, as well as with specialized on-screen keyboards for people with disabilities. Using the user's browsing history, we improve the efficiency of the selection process and find potentially interesting page links for the user within their web pages. We present the results from a pilot study evaluating the performance of various components of our system.".
- 643 hasAuthorList authorList.
- 643 hasTopic World_Wide_Web.
- 643 isPartOf proceedings.
- 643 keyword "Keyboard Access".
- 643 keyword "Web Accessibility".
- 643 keyword "Web Navigation".
- 643 title "KeySurf: A character controlled browser for people with physical disabilities".
- 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 leo-spalteholz.
- item-1 next item-2.
- item-2 type ListItem.
- item-2 hasContent kin-fun-li.
- item-2 next item-3.
- item-2 previous item-1.
- item-3 type ListItem.
- item-3 hasContent nigel-livingston.
- item-3 next item-4.
- item-3 previous item-2.
- item-4 type ListItem.
- item-4 hasContent foad-hamidi.
- item-4 previous item-3.
- 645 creator massimiliano-ciaramita.
- 645 creator vanessa-murdock.
- 645 creator vassilis-plachouras.
- 645 type InProceedings.
- 645 label "Online Learning from Click Data for Sponsored Search".
- 645 sameAs 645.
- 645 abstract "Sponsored search is one of the enabling technologies for today's Web search engines. It corresponds to matching and showing ads related to the user query on the search engine results page. Users are likely to click on topically related ads and the advertisers pay only when a user clicks on their ad. Hence, it is important to be able to predict if an ad is likely to be clicked, and maximize the number of clicks. We investigate the sponsored search problem from a machine learning perspective with respect to three main sub-problems: how to use click data for training and evaluation, which online learning framework is more suitable for the task, and which features are useful for existing models. We perform a large scale evaluation based on data from a commercial Web search engine. Our results show that it is possible to learn and evaluate directly and exclusively on click data. Even with a small number of features, we can improve the ranking of ads over an information retrieval baseline. To the best of our knowledge this is the first study in sponsored search using learning and evaluation from click-data.".
- 645 hasAuthorList authorList.
- 645 hasTopic World_Wide_Web.
- 645 isPartOf proceedings.
- 645 keyword "Click data".
- 645 keyword "Machine learning".
- 645 keyword "Ranking".
- 645 keyword "Semantics".
- 645 keyword "Sponsored search".
- 645 title "Online Learning from Click Data for Sponsored Search".
- authorList type List.
- authorList hasFirstItem item-1.
- authorList hasItem item-1.
- authorList hasItem item-2.
- authorList hasItem item-3.
- authorList hasLastItem item-3.