We define the problem of decomposing human-written summary sentences and propose a novel Hidden Markov Model solution to the problem. Human summarizers often rely on cutting and ...
Abstract. This paper discusses an approach to topic-oriented multidocument summarization. It investigates the effectiveness of using additional information about the document set ...
This paper presents a means of automatically deriving a hierarchical organization of concepts from a set of documents without use of training data or standard clustering technique...
Automatic summarization evaluation is critical to the development of summarization systems. While ROUGE has been shown to correlate well with human evaluation for content match in...
Written opinion on products and other entities can be important to consumers and researchers, but expensive and difficult to analyze. We present a multimedia interface designed t...