Ask any question about EPFL courses, lectures, exercises, research, news, etc. or try the example questions below.
DISCLAIMER: The Graph Chatbot is not programmed to provide explicit or categorical answers to your questions. Rather, it transforms your questions into API requests that are distributed across the various IT services officially administered by EPFL. Its purpose is solely to collect and recommend relevant references to content that you can explore to help you answer your questions.
Search engines essentially rely on the structure of the graph of hyperlinks. Although accurate for the main trend, this is not effective when some query is ambiguous. Leveraging semantic information by the mean of interest matching allows proposing complem ...
Google AdSense, one of the most popular Online Advertise Networks, uses a mix of two techniques to deliver ads: contextual ads and behavioral ads, but it is not clear when or how much of the both they actually use. In this work, we raise several concerns r ...
Google's linguistic prosthesis have become common mediators between our intended queries and their actual expressions. By correcting a mistyped word or extending a small string of letters into a statistically plausible continuation, Google offers a valuabl ...
This paper presents a system to retrieve and browse images from the Internet containing only one particular object of interest: the human face. This system, called Google Portrait, uses Google Image search engine to retrieve images matching a text query an ...
Much of the Internet economy relies on online advertising for monetizing digital content: Users are expected to accept the presence of online advertisements in exchange for content being free. However, online advertisements have become a serious problem fo ...
We present a color thesaurus with over 9000 color names in ten different languages. Instead of using conventional psychophysical experiments, we use a statistical framework that is based on search results from Google Image Search. For each color name we co ...
