We present a syntactic and lexically based discourse segmenter (SLSeg) that is designed to avoid the common problem of over-segmenting text. Segmentation is the first step in a di...
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 investigate the expressiveness of existing XML keyword search semantics and propose Meaningful Connected Network (MCN) as a new semantics to capture meaningful relationships of ...
Junfeng Zhou, Zhifeng Bao, Tok Wang Ling, Xiaofeng...
Iterative learning algorithms that approximate the solution of support vector machines (SVMs) have two potential advantages. First, they allow for online and active learning. Seco...
To overcome over-synchronization in synchronous programs, we recently introduced clock refinement to our synchronous programming language Quartz. This extension basically allows p...