There has been mixed success in applying semantic component analysis (LSA, PLSA, discrete PCA, etc.) to information retrieval. Previous experiments have shown that high-fidelity language models do not imply good quality retrieval. Here we combine link analysis with discrete PCA (a semantic component method) to develop an auxiliary score for information retrieval that is used in post-filtering documents retrieved via regular Tf.Idf methods. For this, we use a topic-specific version of link analysis based on topics developed automatically via discrete PCA methods. To evaluate the resultant topic and link based scoring, a demonstration has been built using the Wikipedia, the public domain encyclopedia on the web.
The most common and least intelligent tools of this sort are the search engines that provide keyword search capabilities to a large segment of the information on the Web. While search engines are proving critical to day to day use, they have significant limitations. First, search engines require users to characterize their goals in terms of keywords or other search expressions. This is a very difficult task for many users, and is particularly difficult in domain areas with large vocabularies where documents may exist that are relevant to the user's goal but do not use the particular words selected. This limitation ha spurred a number of research initiatives that are developing intelligent agents to address this problem. The most common approach is to have an agent learn an interest profile for a user, relieving the user of the need to construct search strings [Holte and Drummond, 1994; Knoblock and Arens, 1994; Levy et.
Netflix has mysteriously been removed from the American film industry's search engine for legal streaming sites. WhereToWatch, which was set up by the Motion Picture Association of America (MPAA) in 2014, lets users search a range of legal streaming services for their favourite TV shows and films. The idea was to provide internet users with a handy resource which would steer them away from illegal streams and downloads, protecting them from potential legal trouble and helping the studios at the same time. However, as TorrentFreak reports, Netflix has been removed from the WhereToWatch search results, despite being the one of the most-used legal streaming services in the world. Netflix results have also been removed from the UK equivalent of the site, FindAnyFilm, although some Netflix results are still available on GoWatchIt, the search engine which powers WhereToWatch.
Everything in our online life is indexed. Every idle tweet, status update, or curious search query feeds the Google database. The tech giant recently bought a leading artificial-intelligence research outlet, and it already has a robotics company on its books. So what if Google, or Facebook, or any of the companies we entrust our information to, wanted to use our search histories to create an artificially intelligent robot? Writer and director Alex Garland's new film, Ex Machina, looks at just that.