Shallow Semantics for Extractive Summarization using Connexor Machinese Semantics

Abstract. Connexor Machinese Semantics is one of the most elaborate tools for providing semantic information about a sentence. It has been hypothesized that semantic analysis of sentences is required in order to make significant improvements in automatic summarization. In this work, we look at what shallow semantic features are available that
might help to improve the responsiveness of a summary. While this approach is not likely to perform as well as full semantic analysis, it is considerably easier to achieve and could provide an important stepping stone in the direction of deeper semantic analysis.