Demo1: Decomposition of Human-written Summary Sentences

The Problem

Human summarizers often rely on cutting and pasting of the full document to generate summaries. Decomposing a human-written summary sentence requires determining: (1) whether it is constructed by cutting and pasting, (2) what components in the sentence come from the original document, and (3) where in the document the components come from.


Sample Output


The Hidden Markov Model (HMM) Based Solution

We reduce the decomposition problem to a problem of finding the most likely document origin for each word in a summary sentence, shown below, and then solve the problem using HMM.