Paper: Variation Of Entropy And Parse Trees Of Sentences As A Function Of The Sentence Number

ACL ID W03-1009
Title Variation Of Entropy And Parse Trees Of Sentences As A Function Of The Sentence Number
Venue Conference on Empirical Methods in Natural Language Processing
Session Main Conference
Year 2003
Authors

In this paper we explore the variation of sentences as a function of the sentence number. We demonstrate that while the entropy of the sentence increases with the sentence number, it decreases at the para- graph boundaries in accordance with the Entropy Rate Constancy principle (intro- duced in related work). We also demon- strate that the principle holds for differ- ent genres and languages and explore the role of genre informativeness. We investi- gate potential causes of entropy variation by looking at the tree depth, the branch- ing factor, the size of constituents, and the occurrence of gapping.