Extractive summarization techniques cannot generate document summaries shorter than a single sentence, something that is often required. An ideal summarization system would understand each document and generate an appropriate summary directly from the results of that understanding. A more practical approach to this problem results in the use of an approximation: viewing summarization as a problem analogous to statistical machine translation. The issue then becomes one of generating a target document in a more concise language from a source document in a more verbose language. This paper presents results on experiments using this approach, in which statistical models of the term selection and term ordering are jointly applied to produce summaries in a style learned from a training corpus.

Current semantic Web reasoning systems do not scale to the requirements of their hottest applications, such as analyzing data from millions of mobile devices, dealing with terabytes of scientific data, and content management in enterprises with thousands of knowledge workers. In this paper, we present our plan of building the large knowledge collider, a platform for massive distributed incomplete reasoning that will remove these scalability barriers. This is achieved by (i) enriching the current logic-based semantic Web reasoning methods, (ii) employing cognitively inspired approaches and techniques, and (iii) building a distributed reasoning platform and realizing it both on a high-performance computing cluster and via "computing at home". In this paper, we will discuss how the technologies of LarKC would move beyond the state-of-the-art of Web scale reasoning.