This article proposes a novel approach on how to rectify the photo image of the bound document. The surface of the document is modeled by a cylindrical surface. By the geometry of...
Sentence Clustering is often used as a first step in Multi-Document Summarization (MDS) to find redundant information. All the same there is no gold standard available. This paper...
We present the background and justi cation for a new approachto studying computation and computational complexity. We focus on categories of problems and categories of solutions w...
It is difficult to present new, complex ideas in ways that are informative and interesting in situations where a vast amount of information has to be delivered and understood quic...
A distributed system is described that reliably mines parallel text from large corpora. The approach can be regarded as cross-language near-duplicate detection, enabled by an init...
Jakob Uszkoreit, Jay Ponte, Ashok C. Popat, Moshe ...